NeurIPS 2026 Schedule

Skip to yearly menu bar Skip to main content

Filter Events

WED 9 DEC

7 p.m.

Paris Oral Session 1 [7:00-8:30]

(ends 8:30 PM)

9 p.m.

Paris Oral Session 2 [9:00-10:00]

(ends 10:00 PM)

10:30 p.m.

Paris Poster Session 1 [10:30-12:30]

Posters 10:30-12:30

$\delta$-Mem: : Efficient Online Memory For Large Language Models

3D-VITAL: Visibility-aware Identity Training from Artificial Liftings of 3D Reconstruction model for Cross-View Object Re-Identification

Achieve Latency-Efficient Temporal-Coding Spiking LLMs via Discretization-Aware Conversion

Active Learning for Gaussian Process Regression Under Self-Induced Boltzmann Weights

Active Probabilistic Reasoning in Humans and LLMs

AdaCubic: An Adaptive Cubic Regularization Optimizer for Deep Learning

Adaptive Realizable Regression from Two Online Learners

Adaptive Scheduling Pipeline For Multi-Instance Asynchronous Reinforcement Learning

A General Concept-based Decomposition for Vision–Language Embeddings

AgentCBO: Causal Belief Routing for Bayesian Optimization under Unknown Graphs

A Grid Efficient Transport Optimization Model for the Wasserstein Barycenter Problem

A Hierarchical World Model for Driving

Aligned LoRA Updates via Intrinsic Geometry for Federated Low-Rank Adaptation

Aligning Language Model Benchmarks with Pairwise Preferences

AmaraSpatial-10K: A Spatially and Semantically Aligned 3D Dataset for Spatial Computing and Embodied AI

A method to automatically discover symbolic local learning rules

Amortized Linear-time Exact Shapley Value for Product-Kernel Methods

Approximate Bayesian inference with exchangeable distributions for neurosymbolic AI

A Reproducible Evaluation Protocol for Quantum Non-Linearity in Variational Quantum Models

ASO Atlas 2.0: Evaluating antisense oligonucleotide prediction across the preclinical pipeline

A Theory of Online Learning with Autoregressive Chain-of-Thought Reasoning

Auditing AI peer reviewers: a dose-response and false-positive benchmark on real scientific papers

Auditing Attention Head Masking for Out-of-Distribution Detection: Cross-Architecture Wins, Failures, and Polarity Inversions

AuGhostmentation: The Eyes Never Stand Still—$\textit{Why Should CNNs?}$

A Unified Framework for Uniform-Price Resource Allocation Mechanisms

Automatic Constraint Policy Optimization based on Continuous Constraint Interpolation Framework for Offline Reinforcement Learning

Automatic Textbook Formalization

Bellman Contraction under MMD: A Unified Framework

Benchmarking sequence-to-ensemble predictors on UNICORNEdb, a UniProt-grouped database of PDB-derived conformational ensembles

Beyond Modality Fusion: Deep Ensembles for Multimodal Classification

Beyond the Half Approximation: Fair and Efficient Online Class Matching

Bian Que: An Agentic Framework with Flexible Skill Arrangement for Online System Operations

BIAS-ID: A Framework for Analyzing Transformation Biases in AI-Generated Image Detectors

Black-Box Followers, White-Box Leaders: Partial Zeroth-Order Methods for MPECs

Boosting Brain-to-Image Decoding with TRIBE v2 Data Augmentation

Boundary-Induced Forgetting in Large Language Model Tool Chains: Measuring Field-Routing Failures

Bug or Feature$^2$: Weight Drift, Activation Sparsity, and Spikes

Can an LLM Reason Like a Lawyer? Benchmarking the ability of LLMs to map the facts of a case to the elements of the applicable legal rule

Causal Evaluation of Membership Inference Attacks

Causal Gradient Steering: Exposing Shortcut Gradients by Destroying Causal Signal

Causal pieces: analysing and improving spiking neural networks piece by piece

Certified Single-Level Reformulation for Tri-Level Cyber-Physical Grid Security

Characterizing the Edge of Stability in Variational Training Without Priors

CLoSeR: Closing the Loop for Long-Context Streaming Reconstruction

Clustered Randomized Smoothing for Stochastic Prediction Functions

Competing Event Models: Next Event Prediction Under Interventions

ContextShift: A Controlled Benchmark for Context Dependence in Object Detection

Convergence Guarantees for Federated SARSA with Local Training and Heterogeneous Agents

Correct but Unselectable: The Hidden Interface Tax in Multi-Candidate Reasoning

CroissantMiner: Automated Extraction and Validation of Croissant Metadata for ML Datasets

Crowded in B-Space: Calibrating Shared Directions for LoRA Merging

Diff-CA: Separating Common and Salient Factors with Diffusion Models

Diffusion fine-tuning with Rewarded Moment Matching Distillation

Discrete Diffusion Models Exploit Asymmetry to Solve Lookahead Planning Tasks

Disentangling the Good From the Bad: Quantization-Induced Flips Are Not Random

Distribution Free Fourier Sparsity Testing

Does Weight Decay Enhance Training Stability?

Domination-Avoiding Learning Agents Cannot Collude

Dual-Pronged LoRA: Achieving Near-Zero Forgetting and High-Performance Adaptation for MLLMs

Dynamic Video Generation: Shaping Video Generation Across Time and Space

Dyna-Style Safety Augmented Reinforcement Learning: Staying Safe in the Face of Uncertainty

Effective Context in Transformers: An Analysis of Fragmentation and Tokenization

Efficiently Aligning Draft Models via Parameter- and Data-Efficient Adaptation

Emergence of Distortions in High-Dimensional Guided Diffusion Models

EM-NeSy: Expectation Maximization for Neurosymbolic Learning

Enhancing Tabular Learners with Context-Aware Semantic Embeddings

Escaping the Curse of Dimensionality in One‑Step Flow-Based Generative Models

ESS-Flow: training-free guidance as Bayesian inference in source space

Evaluating and Understanding Scheming Propensity in LLM Agents

Evaluating Multimodal Narrative Understanding of Popular Hollywood Films

Exploration as Constrained Policy-Space Optimization

Externalized CPDAG Summaries Improve LLM Causal Deduction

Fast Wasserstein rates for estimating probability distributions of probabilistic graphical models

Federated Dataset Simulation: Inducing Label-Free Heterogeneity Across Tasks

FineRMoE: Dimension Expansion for Finer-Grained Expert with an Upcycling Approach

ForesightFlow: Self-Guided Flow Matching for Improving Vision-Language-Action Models

Frank-Wolfe Beyond 1/t Convergence

FrED: External Data Influence Estimation via Domain Knowledge Graph Grounding

Frequency Domain Reservoir Computing

From Approximation to Computation: Universal Power of Deep Narrow Networks at Constant Width

From Experts to Sub-experts: Fine-grained Parameter-Efficient Fine-Tuning for MoE LLMs

From Isolated feature to Orbits:\\Discovering Music Concepts via Multi-SAE Alignment

From sequences to schemas: low-rank recurrent dynamics underlie abstract relational representations

FunctionEvolve: Structure-Guided Symbolic Regression with LLMs

GAUGECAST++: A Physics-Informed Latent Forecasting System for Localized Flood Prediction

Generating Financial Time Series by Matching Random Convolutional Features

GISA: A Benchmark for General Information-Seeking Assistant

GNNs Meet Sequence Models Along the Shortest-Path: an Expressive Method for Link Prediction

Gradient Span Algorithms Make Predictable Progress in High Dimension

Grokking or Glitching? How Low-Precision Drives Slingshot Loss Spikes

Group-Aware Matrix Estimation and Latent Subspace Recovery

GT-Free OCR Metrics: A Reference-Free Evaluation Framework for Document OCR Systems

HalluciText: Mitigating Text Hallucinations in Diffusion-Based Image Restoration

haphazard: A unified library and benchmark for online learning under varying feature availability

HARC: Coupling Harmfulness and Refusal Capabilities for Robust Safety Alignment

Heterogeneity-aware Distillation for Federated Continual Learning

Hierarchical Agglomerative Clustering via Relaxed Representatives

High-dimensional Limit of SGD for Diagonal Linear Networks

How deep is your network? Deep vs. shallow learning of transfer operators

HPE: Hallucinated Positive Entanglement for Backdoor Attacks in Federated Self-Supervised Learning

HumanStereo: A Benchmark for Metric Facial Depth Estimation and Its Evaluation

idSCD: Identifying Training Datasets through Semantic Correlation Descriptors

Improved Regret bounds in Tabular Reinforcement Learning under Local Differential Privacy

Inferotemporal Cortex Collaborates Before It Codes: Non-Serial Inter-Area Synergy in the Macaque Ventral Stream

Integral Probability Boundaries

Intent Factored Generation: Unleashing the Diversity in Your Language Model

Inverse Linear Bandits via Linear Programs

Jaguar: Fast Private CNN Inference with Power-of-Two Homomorphic Arithmetic

JAXtari: High-Throughput and Easy-to-Modify Arcade Learning Environment

KDASO: Knowledge-Data Dual-Driven Automated Skill Optimization for Liability Adjudication Task

KnowEvo: Knowledge Evolution for Protein Optimization

Latent Motion Alignment for Video Diffusion

Learning Acceptable Lotteries via Queries: Minimizing Aggregated Violation Distances

Learning Domain Trajectories with Flow Matching for Gradual Domain Adaptation

Learning Lotteries with Minimal Violations from Membership Queries

Learning to Complete Extremal Mathematical Structures

Learning to Decide with AI Assistance under Human-Alignment

Lifting Biomolecular Data Acquisition

Linear-time rule mining under formal guarantees

Logical Distillation of Transformer Encoders

Mapping Uncharted Symmetries: Machine Discovery in Combinatorics

MAPS: Margin-Aware Priors and Verifier-Guided Search for Embodied Planning

Martine: Benchmarking Multi-View 3D Surface Reconstruction Across Viewpoint Coverage, Resolution, and Lighting

MatchEx: Model-Level GNN Explanations with Multi-Granular Insights

Maximin Robust Bayesian Experimental Design

MemReg: Streaming Outdoor LiDAR Point Cloud Registration with Hybrid Memory Buffers

Meta-memorization and memorization scaling laws in transformers

Module-Aware Optimization for Graph Neural Networks

MSR-3D: Multi-Mode Semantic Representation for Open-Vocabulary 3D Scene Understanding

Multilevel and Sequential Monte Carlo for Training-Free Diffusion Guidance

Multimodal Foundation Agents Should Use Brain Data as Privileged Supervision

Multiple Descent of Generalization Curve for Optimally Regularized Ridge Regression

Neural Networks With Dense Weights Are Not Universal Approximators

Noisy isomorphism: Robust expressivity of GNNs under structural perturbation

Nonparametric Distribution Matching for Self-Supervised Whole-Slide Image Condensation

Observable Neural ODEs for Identifiable Causal Forecasting in Continuous Time

On Differentially Private Mechanisms for Linear Regression

On Generation in Metric Spaces

OpenSearcher: Democratizing Deep Search through a Fully Offline Pipeline with Programmatic Verification

OPERA: An Agent for Image Restoration with End-to-End Joint Planning–Execution Optimization

Optimal Experiments for Partial Causal Effect Identification

Optimal scaling laws in learning hierarchical multi-index models

OrthoReg: Orthogonal Regularization for Hybrid Symbolic-Neural Dynamical Systems

Parameterized Complexity of Stationarity Testing for Piecewise-Affine Functions and Shallow CNN Losses

PASSAGE: A Real-Terrain Benchmark for Trustworthy Constrained Path Planning

Patching Up Circuit Learning on Images

Penalize to Verify: A Multi-Domain Benchmark for Trustworthy LLM Evaluation

PLLS-CP: Unsupervised Hallucination Detection with Layer Selection and Cross-Domain Conformal Guarantees

Plug-and-Play ADMM for Inverse Problems with Flow Matching Denoiser

Position: Anthropomorphic Language in AI Discourse Can Be Constructive

Position: Lottery Tickets Do Not Explain Overparameterization. How About Escape Dimensions?

Position: The Road to Generalizable Neuro-Symbolic Learning Should be Paved with Foundation Models

Prior as Geometry, Not Generator: Weak-Diffusion Test-Time Reconstruction for Dynamic MRI

Property-Guided LLM Program Synthesis for Planning

Proteus: Incremental Memory Activation for Long-Context Sequence Modeling

Provable Speedups From Dynamic Population Sizes in Evolutionary Algorithms for Multiobjective Optimization

Pseudo-Labeling for Unsupervised Domain Adaptation with Kernel GLMs

Quantile Benchmarking Heterogeneous Web Corpora in Open LLM Pretraining

Rare Events, Real Signals: Functional Ensembles as Units of Computation in Deep Spiking Networks

RASS: Risk-Audited Budget Selection for Compact NeRF Benchmark Subsets

RayTun3R: Online Camera Adaptation in 3D Foundation Models

Regret Minimization in Single-Dimensional Contract-Design with Binary Actions

Replay-buffer engineering for noise-robust quantum circuit optimization

RESCAST-100K: A Comprehensive Dataset for Cross-Domain Residential Load and Indoor Temperature Forecasting

SafePro: Generation of Safe and Functional Proteins via Cross-Task Conflict-Aware Alignment

Same Function, Different Mechanism: Implementation-Local Geometry Beyond Accuracy

Scalable Distributed Stochastic Optimization via Bidirectional Compression: Beyond Pessimistic Limits

Scaling Full Conformal Image Classifiers

Scaling Genomic Language Modeling with Unified Corpus and Evaluation in Bacteria

SD-Search: Hindsight Self-Distillation for Search-Augmented Reasoning

Secure Seed-Based Multi-bit Watermarking for Diffusion Models from First Principles

Self-Distillation of Hidden Layers for Masked Self-Supervised Representation Learning

SetAD: Semi-Supervised Anomaly Learning in Contextual Sets

Similarity-Constrained Reweighting for Complex Query Answering on Knowledge Graphs

SMOG: Scalable Meta-Learning for Multi-Objective Bayesian Optimization

SP$^3$: Spherical Priors for Plug-and-Play Restoration

Space-Aware World Models: Spatial Persistence Through Factored Scene Representations

Spatially Feasible 3D Indoor Scene Generation via Interaction-Oriented Human Proxy

Spectral Alignment in Forward–Backward Representations via Temporal Abstraction

Spiking neural network initialization for scale-invariant maximization of entropy

STABLE: A Continual Learning Optimizer with Adaptive Drift Control

Stochastic Matching Bandits with Rare Optimization Updates

Stochastic Matching via Local Sparsification

Subcritical Signal Propagation at Initialization in Normalization-Free Transformers

SynthForensics: Benchmarking and Evaluating People-Centric Synthetic Video Deepfakes

Tabular Foundation Model for Generative Modelling

Taking Low-Rank LLM Compression a Step Further: A Global Perspective with Fused Inference

TempoPFN: Synthetic Pre-training of Linear RNNs for Zero-shot Time Series Forecasting

Test-Time Conditioning with Representation-Aligned Visual Features

The Algorithm Is Not the Behavior: Learned Priors Override Look-Ahead in a Chess-Playing Neural Network

The BatchNorm Illusion: Diagnosing Normalization Artifacts in Machine Unlearning Evaluation

The Bayesian Learning Rule Beyond KL Geometry

The Geometric Inductive Bias of Grokking: Bypassing Phase Transitions via Architectural Topology

The risk of KV cache compression

The Sign Code: The Hidden Binary Nature of Deep Networks

The Window for Preventive Action Before AI Saturates Most Cognitive Benchmarks is Closing

Thinking with Visual Primitives

ThousandWorlds: A benchmark for emulating the climates of potentially habitable exoplanets

Tight Generalization Bounds for Noiseless Inverse Optimization

Token-to-Token Alignment of Text Embeddings for Semantic Blending

ToMAToMP: Robust and Multi-Parameter Topological Clustering

Topological Periodicity Test (TopPT) via Confidence Bound of Time-Delay Embeddings

Towards Understanding and Measuring Cognitive Atrophy in LLM Behaviour

Trustworthy Retrosynthesis: Eliminating Hallucinations with a Diverse Ensemble of Reaction Scorers

Understanding Multi-View Transformers

Understanding the Interplay between Memorization and Learning in Large Language Models

Unlearning That Lasts: Utility-Preserving, Robust, and Almost Irreversible Forgetting in LLMs

ViewSAM: Learning View-aware Semantics for Weakly Supervised Cross-view Referring Multi-Object Tracking

Wavelet Flow Matching for Multi-Scale Physics Emulation

What Can Labels Alone Audit and Edit in Frozen Representations?

What Drives Compositional Generalization? The Importance of Continuous Training Objectives in Visual Generative Models

When Graph Anomalies Learn to Hide: Test-Time Cloaking in Graph-Level Anomaly Detection

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation

World Models as Adversaries: Multi-Agent Self-Play Fine-Tuning for Robust Motion Planning

World Models as Group Actions

xWhy: Causal Learning from Explanations

(ends 12:30 AM)

THU 10 DEC

12:30 a.m.

Paris Invited Talk:

Why informative explanations only exist for simple functions and what this means for the European AI Act

Ulrike Luxburg

(ends 1:30 AM)

1:30 a.m.

Paris Oral Session 3 [1:30-3:30]

(ends 3:30 AM)

3 a.m.

Paris Poster Session 2 [3:00-5:00]

Posters 3:00-5:00

$\pi^2$: A Simple Framework for 2D-to-3D Registration

ACER: Towards Generalizable Protein-ligand Co-folding

A Critical $\beta$-Scale for Posterior Collapse in Dirichlet $\beta$-VAEs

Active Context Selection Improves Simple Regret in Contextual Bandits

ADAPT: Hybrid Prompt Optimization for LLM Feature Visualization

Adaptive Robust Estimator for Policy Optimization in Reinforcement Learning

AI Behavioral Evaluation Should Be Grounded in Psychophysics Across Marr’s Levels

AI-Generated Content Should Be Evaluated by Its Substance, Not Its Source

A Mahalanobis Margin \texorpdfstring{$\gamma_{\min}$}{gamma\_min} Bound on Task Confusion in Pretrained Class-Incremental Learning: From Infeasibility to Exponential Attenuation

AMARIS: Merging Generalist and Specialist LLMs via Adaptive Subspace Inheritance

Amortized Molecular Optimization via Group Relative Policy Optimization

An Õptimal Differentially Private PAC Learner for Concept Classes with VC Dimension 1

Antibody Generation via Redistributed Latent Diffusion

ARC-Encoder: learning compressed text representations for large language models

AR-Edit: Training-Free Streaming Video Editing without Inversion

Assessing Per-Sample Membership Inference Vulnerability without Retraining

Asymptotic Anytime-Valid Inference for U-statistics

A Theoretical Bridge Between Long-Tailed Recognition and Continual Learning

A Unified Perturbation Framework for Analyzing Leaderboard Stability and Manipulation

Automata from Agent Traces: Failure and Next-Step Prediction

Balancing Frequencies and Pixels in Flow Matching

BalCapRL : A Balanced Framework for RL-Based MLLM Image Captioning

Belief Engine: Configurable Stance Dynamics for Multi-Agent LLM Deliberation

Benchmarking Attention for Tabular Foundation Models

Beyond Kemeny Medians: Consensus Ranking Distributions. Definition, Properties and Statistical Learning

Binding Multiple Modalities via Multimodal Wasserstein Barycenter

BLANP: Memory-Efficient Backpropagation-Free Local Training via Antithetic Node Perturbation

BO-Arena: An Evolving Benchmark for High-Dimensional Bayesian Optimisation

Building Transformation Layers for Riemannian Neural Networks

Calibrated Target Noise Recovers Curvature from the Gradients

CANDO: Cooperative Agentic Network for Layout Design Optimization

CanViT: Toward Active-Vision Foundation Models

Causal Discovery via Transformed Low-Rank Quantile Surfaces

CENDRe: Concept Extraction with Natural Domain Representations

Cephalonauts One: A deep fMRI dataset for decoding naturalistic speech in the human brain

CHAIN: Continual Heterogeneous Cooperation with Information Bottleneck for Multi-Agent Reinforcement Learning

ChainSpace: A Chained-Reasoning Paradigm for Spatial Intelligence

CHASM: Cross-frequency Harmonized Axis-Separable Mixing for Spectral Token Operators

Complexity Aware Continuous Level of Details for Gaussian Splatting

Consistency-Verified Backdoor Defense for Federated Graph Learning via Cross-Layer Drift

Consistent 3D Surface Flow Model with Global State

Consistent One-vs-All Losses Robust to Misspecification of the Weak Label Transition Model

Constrained Bombieri Point Processes

Contrastive Hypergraph Source-free Domain Adaptive Object Detection in Adverse Weathers

Controlling for Omitted Variable Bias in Deep Neural Networks

Control Under the Wrong Model Is Better Than Under the Correct One

CS-DICE: Offline Reinforcement Learning with Coherent Occupancy Regularization

DACE: Diversity-Driven Adversarial Co-Evolution for Robust LLM Safety Alignment

Dandelions: A Spherical Flower for Neural Simulation of Planetary Dynamics

Decision-Aware Proximal Bridge Learning for Optimal Treatment Selection

Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning

Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors

Disentangling generalization and memorization in large language models using chess

Doomed to Re-Annotate, Forever: The ImageNet Story

Dynamic Regret in Online Convex Optimization with Indicator Switching Costs

E²Gen: Evidential Energy-Based Generation for Fair Federated Graph Learning

EEGFaceSem: An EEG Benchmark with Paired Generative Latents for Semantic Visual Modeling

Efficient Matrix Product State Learning in Logarithmic Depth

Euclidean Embedding of Data Using Local Distances

Evaluating Epistemic Uncertainty: Beyond OOD Detection and Active Learning

Expected Batch Optimal Transport Plans and Consequences for Flow Matching

Explanation of Dynamic Physical Field Predictions using WassersteinGrad: Application to Autoregressive Weather Forecasting

Expressive Power of Deep Homomorphism Networks over Relational Databases

FACBench: A Benchmark for Formal-Anchor Collisions in Multilingual Mathematical Grounding

Fail-Closed Alignment for Large Language Models

𝑓-Differential Privacy Filters: Validity and Approximate Solutions

FedTrace: Generated-Content-Based Watermark Verification for Traitor Tracing in Federated Learning

FIVE-VLA: Fast and EffectIVE Closed-Loop Autonomous Driving with Recurrent Action Memory

Focus, Align, and Diffuse: Time-Series-Aware Keyframe Diffusion for Cardiac Dynamic Synthesis from Sparse Observations

Focused Forcing: Content-Aware Per-Frame KV Selection for Efficient Autoregressive Video Diffusion

FogGS: Physics-Grounded 3D Foggy Effects

From Anti-Forgetting to Fast Adaptation: Continual Reinforcement Learning with World Models

From Baselines to Transport Geodesics: Axiomatic Attribution via Optimal Generative Flows

From Persistence to Survival: Hypothesis Testing, Effect Sizes and Vectorisation for Topological Features

From Structural Feedback to Prompt Policies: Learning Faithful Text-to-Image Prompt Editors

GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models

GEM: A Dual-Scale Architecture for Graph-Level Hierarchical Representation Learning

Gender Artifacts from Art History to Text-to-Image Generation

Generalization in Neural Networks Through the Lens of Magnitude Potential

Generalized Adaptive Boosting and the Geometry of Mistakes

Generative Object Detection with Co-Training

GeoBiaset: A Counterfactual Benchmark for Demographic Bias in World-Level Geolocalization

GeoCurv-TTT: Geometry-Aware Deformation Restoration for 3D Test-Time Training

Geometry-Guided Semantic Reconstruction for 3D Instance Segmentation

Gradient-Guided Smoothing for LLM Safety Defense

GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling

Honeyval: A Comprehensive Evaluation Framework for LLM-powered HTTP Honeypots

Hypergraph Generation via Structured Stochastic Diffusion

IDEAFix: Evaluation Framework for Creative Defixation Prompting in LLMs

I Have a Stream: Making Self-Supervised Learning Work on Continuous Video

Implicit Bias of Mirror Flow in Homogeneous Neural Networks: Sparse and Dense Feature Learning

In-Context Black-Box Optimization with Unreliable Feedback

Incremental Learning in Transformers for In-Context Associative Recall

Independent Learning of Nash Equilibria in Partially Observable Markov Potential Games with Decoupled Dynamics

Instantiation of Human Values in Image Generation

Intersectional Fairness via Mixed-Integer Optimization

IRPO: Boosting Image Restoration via Post-training GRPO

Joint Adaptive Neighborhood Constraint for Offline Multi-Agent Reinforcement Learning

k-th Order Deep Homomorphism Networks

KV Packet: Recomputation-Free Context-Independent KV Caching for LLMs

LayoutBridge: Anisotropic Brownian Bridges for Public Indoor Floorplan Generation

Learning Compositional Latent Structure with Vector Networks

Learning to Undo: Transfer Reinforcement Learning under State Space Transformations

Learning Transferable Representations from Operating System Entities via Provenance Graph Distillation

Learning Where to Simulate: Generative Active Sampling for Online PDE Surrogate Training

LithoBench: Benchmarking Large Multimodal Models for Remote-Sensing Lithology Interpretation

LLM-AutoSciLab: Closed-Loop Scientific Law Discovery via Active Experimentation with LLMs

Lost in the Slots: Revisiting Object-Centric Representations in the era of Foundation Models

Macrocanonical Generator Networks: data-efficient neural surrogates for amortized physics simulation

Mamba Flow Matching Neural Processes: Linear-Time Inference for Irregularly Observed Spatial Fields

Many Circuits, One Mechanism: Input Variation and Evaluation Granularity in Circuit Discovery

Membership Inference on Synthetic Single-Cell Genomic Data

MEMEVO: A Memory-Evolved Video Agent for Long Video Understanding

MemPlan: Memory-Conditioned PDDL Planning for Partially Observable Text Environments

Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents

MID: Mask-Image Distributional Divergence for Evaluating Medical Image Segmentation

Mildly Overparameterized ReLU Networks on Orthogonal Data: Incremental Learning and Implicit Bias

Mirror descent actor-critic methods for entropy regularised MDPs in general spaces: stability and convergence

Mitigating Saliency Collapse: Robust Saliency-Aware Long-Text Image-Text Alignment

More Value per Key: Asymmetric Sparse Attention for Faster LLM Decoding

Mouse Total Capture: A multi-view Dataset for 3D Motion and Expression Capture of Freely Moving Mouse

Multi-Bridge Denoising Diffusion Probabilistic Models

Multi-Environment POMDPs with Finite-Horizon Objectives

NashDreamer: Model-Based Reinforcement Learning for Zero-Sum Imperfect-Information Games

Neural Galerkin Normalizing Flows for Bayesian Inference of Diffusions with Inaccessible Boundaries

Not All Gap Correction Helps: A Geometric View of External Information in LLM Inference

ObjView-Bench: Rethinking Difficulty and Deployment for Object-Centric View Planning

OneSearch-V2: The Latent Reasoning Enhanced Self-distillation Generative Search Framework

On Length Bias in EEG-to-Text Decoding

Online Active Testing: Adaptive Importance Sampling for Unbiased Risk Estimation in Data Streams

On Observation Time for Recovering Latent Hawkes Networks

On the Construction and Implications of Low-Loss Valleys in LoRA-based Bayesian Inference

On the Rademacher Complexity of Graph Neural Networks: Unifying Expressivity and Geometry

Optimal algorithmic complexity of inference in quantum kernel methods

Optimal In-context Adaptivity and Distributional Robustness of Transformers

Optimized Forward-Backward Rematerialization for Memory-Efficient Pipeline Parallel Training

OTEdit: Entropic Transport Corrected Trajectory for Inversion-Free Flow-Based Image Editing

ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning

Pareto DNN Verification: Fast for Most Queries

Pathways of Visual Information Flow in Vision-Language Models

P-EAGLE: Parallel-Drafting EAGLE with Scalable Training

Playing Markov Games Without Observing Payoffs

Poison-then-Hide: Finetuning-Activated Backdoor Attack on Pretrained Vision Encoders

Position: AI Efficiency Gains Must Be Quantitatively Evaluated Against Rebound Effects

Position: Fair Representations Cannot Hold What They Promise

Prediction-Powered Active Testing

Principia: Relational Physics Tests for Video Models

Privacy Amplification Persists under Unlimited Synthetic Data Release

Privacy by Postprocessing the Discrete Laplace Mechanism

Privacy Guarantees in Posterior Sampling under Contamination

PurpleAudit: A Co-Evolutionary Auditing Framework for Task Hijacking in Multi-Agent Systems

QGround: Condition-Wise Evidence Aggregation for 3D Grounding with 2D VLMs

Quantitative Local Convergence of Mean-Field Stein Variational Gradient Flow

Read-Only Zero-Shot Classifier Expansion from Pairwise Semantics

Recovering Clean Evaluation Metrics from Contaminated Benchmarks

ReefNet: A Large-Scale Dataset and Benchmark for Fine-Grained Coral Reef Recognition

Reinforcement Learning for Long-Horizon Unordered Tasks: From Boolean to Coupled Reward Machines

Resource-Aware Parameter-Efficient Model Adaptation for Onboard High-Dimensional Data

RigRecon: Efficient Rig-Aware Street Reconstruction via Dual-Path Spatio-Temporal Interaction

Robot Demonstration Videos Should Include Transparency Disclosures

Robust Amortized Simulation-Based Inference via Learned Error Models

Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation

RubiConv - Efficient Boundary-Respecting Convolutions

Safe Few-Step Generation via Velocity Editing

SciR: A Controllable Benchmark for Scientific Reasoning in LLMs

SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers

Self-Improvement Imitation with Biologically Guided Search for Protein Design Under Oracle Budgets

SemanticDLM+: Improving Diffusion LLMs through Bias-variance Trade-off in Transition Kernel Design

Settling the Sample Complexity of Deterministic Agnostic PAC Learning

Show Me What You Don’t Know: Efficient Sampling from Invariant Sets for Model Validation

Simultaneous Gradient Learning in First-Price Auctions

SLAyiNG: A Diverse and Community-validated Dataset of Queer Slang

SLVMBench: Skill Learning from Video Memory

SP-CACW: Convergence-Aware Client Weighting for Selfish Personalized Learning

Spectral Re-Basin for Linear Mode Connectivity

SR-GRPO: Stable Rank as an Intrinsic Geometric Reward for Large Language Model Alignment

Stabilizing Policy Optimization via Logits Convexity

Statistical Convergence of Spherical First Hitting Diffusion Models

StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs

Stop the Sampler! Classifier-Based Adaptive Stopping for Sampling Kernels

Subset-Conditioned Boundary Compensation for Missing-Modality Multimodal Classification

Surprise, Episodic Context, and Catastrophic Forgetting in LLM Fine-Tuning: An Empirical Study

TerraMesh-Masks: Open‑Vocabulary Segmentation for Earth Observation

The Constitutional Coverage Trilemma in AI Governance

The Grounding Gap: How LLMs Anchor the Meaning of Abstract Concepts Differently from Humans

The Long-Run Distribution of Regularized Learning in Non-Concave Games: A Large Deviations Approach

The Post-Training Dilemma: Why We Should Rethink the Sequential SFT-RL Paradigm

The Ruler and the Judge: Benchmark-Conditional Evaluation of LLM-as-a-Judge

The SEC Filings Dataset: Reconstructing U.S. Corporate and Financial Disclosures into Layout-Faithful and Token-Efficient Pretraining Data

The Smart Buildings Control Suite: A Diverse Open Source Benchmark to Evaluate and Scale HVAC Control Policies for Sustainability

To Align or Not To Align: Check Your COMPASS Before You Train

Toward Optimal Regret in Robust Pricing: Decoupling Corruption and Time

Towards Convergence of PPO: An Approximate Descent Approach

Training Data Attribution in Diffusion Models via Mirrored Unlearning and Noise-Consistent Skew

Training-free Focus-Ambient Retention for Memory-Efficient Video Large Language Models

TropNNC: Structured Neural Network Compression Using Tropical Geometry

TS-ICL: A Flexible Time-Indexed Foundation Model for Time Series via In-Context Learning

TUBE: Tangent Upper Bound on Evidence for Discrete Diffusion Language Models

Unbiased First-Order Randomized Smoothing for Differentiable Simulation

Unbounded Streaming Text-To-Speech with Prefixed Sliding Window Attention

Uncertainty as an Underconstrained Axis in Lossy Compression

Uncovering Challenges of Solving the Continuous Gromov-Wasserstein Problem

Unifying Goal-Conditioned RL and Unsupervised Skill Learning via Control-Maximization

Unrestrained Simplex Denoising for Discrete Data. A Generative Method Applied to Graphs.

V-GIFT: Boosting Visual Instruction Tuning with Self-Supervised Guidance

VISTA: Support-Anchored Value Targeting for Fast Flow-Based Vision-Language-Action Policies

WaveMamba: Wave-Inspired Cross-Modal Fusion for Robust event-image Semantic Segmentation

WayPOP: A Panoramic Open-Set Panoptic Tracking Benchmark

Weighted Sampling for Online Causal Discovery

What’s Holding Back Latent Visual Reasoning?

When Does Trimming Help Conformal Prediction? A Retained-Law Diagnostic under Calibration Contamination

When Must AI Training Stage Checkpoints? A Distributional Model of Durability Boundaries at Scale

Who Needs Labels? Adapting Vision Foundation Models With the Metadata You Already Have

X-Palm: Paired Multispectral-to-Smartphone Dataset for Cross-Domain Palmprint Authentication

Your Self-Supervised Projection Head Captures Object Co-Occurrence Statistics

(ends 5:00 AM)

6:30 p.m.

Paris Invited Talk:

Is Mathematics Solved?

Timothy Gowers

(ends 7:30 PM)

7:30 p.m.

Paris Oral Session 4 [7:30-8:00]

(ends 8:00 PM)

8:30 p.m.

Paris Oral Session 5 [8:30-9:30]

(ends 9:30 PM)

10:30 p.m.

Paris Poster Session 3 [10:30-12:30]

Posters 10:30-12:30

$\text{A}^3$-VLA: Automatic Perception-Guided Attention Alignment for Robot Manipulation

Adaptive Coordinate Transforms for Neural Operators

A Faster Algorithm for the Half-Trek Criterion in Structural Causal Models

A Hierarchy of Entropy-Shapley Games for Multivariate Predictive Uncertainty

AI Agents May Always Fall for Prompt Injections

AIs with Secret Loyalties are a Serious but Addressable Threat

Alloy Agents Can Be More Dangerous Than Either Model Alone

A New Perspective on XAI: Scientific Theory Building for Auditable Artefacts

An Open-Source Training Dataset for Foundation Models for Black-box Optimization

Approximate Envy-Free Allocations up to any k Goods

A Quantitative Visual Taxonomy of Worldwide Writing Systems

Are We Making Progress in Multimodal Domain Generalization? A Comprehensive Benchmark Study

ASTOR: Multi-Task Code Reinforcement Learning via Utility-Driven Coordination

Atoms and Pivot Based Correlation Clustering

A typed tensor language for federated learning

AudioSphere: Towards Self-Supervised Spatial Audio Representation Models

Auditing Sabotage Bench: A Benchmark for Detecting and Fixing Research Sabotage in ML Codebases

Auteur: Language-Driven Cinematographic Framing for Human-Centric Video Generation

Avoiding Feature Collapse in Graph ODEs via Hysteretic Topology Evolution

Beyond Isolation: Neighbor-Consistent Data Pruning for Multivariate Time Series Forecasting

Beyond Oversquashing: Understanding Signal Propagation in GNNs Via Observables

Beyond the Golden Teacher: Enhancing Graph Learning through LLM-GNN Co-teaching

Black-Box Inference of LLM Architectural Properties with Restrictive API Access

BraveATA: Benchmarking Broad and Verifiable End-to-End Automated Theoretical Analysis of Large Language Models

CalArena: A Large Scale Post-Hoc Calibration Benchmark

Can Circuit Alignment Predict OOD Generalization?

Can Hybrid-Parallel Planning Support Alternating Model–Strategy Design? Dependency-Keyed Per-Layer Primitives for Re-Planning

Causal Edit Serialization

Certified Policy Optimisation for Nested Causal Bandits via PAC-Bayes Risk

Chaining 2-FWL GNNs for Combinatorial Graph Alignment

Complexity of Classical Acceleration for $\ell_1$-Regularized PageRank

COMPOSE: Hypergraph Cover Optimization for Multi-view 3D Human Pose Estimation

Compute-Optimal Pretrain--Fine-tune in Ridge Gradient Flow

Concepts Worth Having: Refining VLM-Guided Concept Bottleneck Models with Minimal Annotations

Controlling Temporal Pseudo-Label Marginals for Stable Online Test-Time Adaptation

Curriculum Multiple Shooting for Robust Training of Neural and Universal Differential Equations

Data-Driven Soft Labeling Scales DNA Read Classification to Whole-Body Cell-Type Deconvolution

Debiased Counterfactual Generation via Flow Matching from Observations

DeCoRL: Decomposed Consistency Reinforcement Learning for Multi-Image Composition

Dense Structural Compression of Transformers via Gauge-Correct Channel Removal

Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer Dynamics

Do LLMs Bind Episodes? Probing Cross-Episode Parametric Retrieval Through Shared Cues

Do Not Let Spikes Flip: Margin-Resculpted Learning for Robust Spiking Neural Networks

DriveHierarchy: A Benchmark for Diagnosing VLM Driving Capabilities from Open-Loop Understanding to Closed-Loop Execution

Driving on Memory

DynamAuction: a reinforcement learning environment for repeated auction with dynamic value

DynaPFN: Zero-Shot Dynamical System Forecasting with Tabular Prior-Fitted Networks

DynaProto: Dynamic Prototypical Contrast for Temporally Consistent Object-Centric Learning

EchoKV: Efficient KV Cache Compression via Similarity-Based Reconstruction

EditJudge-Bench: Auditing VLM Image-Edit Judges with Synthetic Ground Truth

Efficient Knowledge Transfer in Federated Bayesian Optimization through Neural Network Surrogates

Energy-Guided Transport for Projection-Free Physics-Informed Flow Matching

Euclidean Score-Based Generative Modeling with Permutation Semantics

Evaluation Awareness in Language Models Has Limited Effect on Behaviour

Events as Triggers for Behavioral Diversity in Multi-Agent Reinforcement Learning

Exact Combinatorial Optimization for Partial Permutation Synchronization

ExpertNavigator: Functionally Coherent Expert Grouping and Pairwise-Ranked Routing for High-Fidelity Dense-to-MoE Conversion

Exploring the Limitations of Layer Synchronization in Spiking Neural Networks

Exponential Map Models as an Interpretable Framework for Generating Neural Spatial Representations

Factual recall in linear associative memories: sharp asymptotics and mechanistic insights

FakeParts: a New Family of AI-Generated Video Forgeries

Fast and Stable Triangular Inversion for Delta-Rule Linear Transformers

Fast Gauss-Newton for Multiclass Cross-Entropy

FedProG: Federated Graph Learning via Server-Side LLM Semantic Bridging and Uncertainty-Aware Distillation

FFTSparse: Relative-Position Correlation Guided Sparse Attention for Long-Context Language Models

Finding Simple Proofs for First-Order Optimization

Finite Resources False Discovery Rate Control on Structured Hypothesis Spaces

Fluxtrapolation: A benchmark on extrapolating ecosystem fluxes

From Claims to Context: Holistic Information Verification Requires Contextual Signals

From Cortical Synchronous Rhythm to Brain Inspired Learning Mechanism: An Oscillatory Spiking Neural Network with Time-Delayed Coordination

From Topology to Retrieval: Decoding Embedding Spaces with Unified Signatures

From Uncertain Judgments to Calibrated Rankings: Conformal Elo Estimation for LLM Evaluation

Generalized Wasserstein Flow Matching: Transport Plans, Everywhere, All at Once

Generative Modeling under Non-Monotone MAR Missingness via Approximate Wasserstein Gradient Flows

Geometric Factual Recall in Transformers

Geometry-Aware Directional Alignment for Coherent Model Merging

Gibbs Gradient Descent: A Langevin Approach to Optimization

GPU-Accelerated Synthesis of Mixed-Boolean Arithmetic: Beyond Caching

Graph Distance Based on Cause-Effect Estimands with Latents

Handwritten Text Recognition Lives in the High-Pixel Variance Subspace

Harnessing Data Asymmetry in Manifold Learning

Hierarchical Task Network Planning with LLM-Generated Heuristics

How Language Models Compress and Compare: Understanding Selection with Token Covariance Maps

Human-Inspired, Task-Dimension-Guided Exploration for Efficient Learning and Transfer in High Dimensions

Identifiable alignment of unpaired representations

Improved Baselines with Representation Autoencoders

Improving Causal Explanations

Is Text All You Need? Text as a Universal Information Bottleneck for Speech LLMs

It Just Takes Two: Scaling Amortized Inference to Large Sets

Itô maps for any-step SDEs

Jacobian Descent for Multi-Objective Optimization

K-prop: Deep Online Learning by Backpropagating Temporal Kernels

Langevin-Informed Transfer Learning: Replacing the Target Samples by Black-Box Feedback

LEAN: Library-Based Adaptation for Asynchronous, Federated Fine-Tuning

Learning-Augmented Coordination Mechanisms

Learning Density Operator Latent Variable Models via Quantum Information Projection

Learning Subspace-Preserving Sparse Attention Graphs from Heterogeneous Multiview Data

Learning to Evolve Scenes: Reasoning about Human Activities with Scene Graphs

Learning to Search, Searching to Learn: A Closed-Loop Framework for Large-Scale Vehicle Routing

Learning to target with network interference

Less is More: Fewer Tokens and Blocks Make AIGI Detection Faster and More Generalizable

Locality-Controlled OOD Guidance for Robust Regulatory DNA Sequence Design

Localize Any Object in X-Ray Security Scans without Human Annotation

Long-Rollout Stability in AI Weather Models: A Quantitative Benchmark and Analysis

M4Bench: Evaluating Procedural Specification for Clinical EHR Derivation Agents

MAGE: Towards Generalizable Multi-timescale EEG Representations

Managing Self-Learning Experts under Per-Round Budget Constraints

Marginal-Nonuniform Multiclass Learning

Mechanistic Insights into LoRA: Layer Sparsity for Adaptive Fine-Tuning via Path Patching

Mini-batch kernel $k$-means

Min-Max Optimization Requires Exponentially Many Queries

MOBO-CAPS: Multi-objective Bayesian Optimization with Cardinality-Aware Pareto Selection

MSAlign: Aligning Molecular and Mass Spectra Foundation Models for Metabolite Identification

NEAT: Neighborhood-Guided, Efficient, Autoregressive Set Transformer for 3D Molecular Generation

Neural Slack Variables for Shape Constraints

NeuroFaith: Evaluating Mechanistic Faithfulness of LLM Free Text Self-Explanation at the Concept Level

Neurosymbolic Object-Centric Learning with Distant Supervision

Neutral-atom quantum features as complementary structural encodings for graph learning

NicheIB: Targeted Spatial Bottlenecks for Predictive Microenvironment Discovery

No-Regret Caching with Delayed Hits

Normalized Architectures are Natively 4-Bit

No Triangulation Without Representation: Generalization in Topological Deep Learning

Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders

One Temperature to Rule Them All?

Online Learning of Group-Stable Coalition Structures

Online Resource Allocation With General Constraints

Online Set Learning from Precision and Recall Feedback

On the Existence of Uniformly Optimal Policies in MDPs under Epistemic Uncertainty

On the Robustness of Watermarking for Autoregressive Image Generation

Optimal Dimension-Free Sampling for Regularized Classification

OTformer: Non-Stationarity-Aware Adaptive Optimal Transport Attention for Time Series Forecasting

Overcoming Rank Collapse in Feedback Alignment

Parameter symmetries determine representational geometry in overparameterized nonlinear networks

Parametric Meets Non-parametric: Bridging Dual Prediction Spaces for Semi-supervised Medical Image Segmentation

Parasite Features: Causal Abstraction Through Spurious Pathways

Pattern-Based Matrix Analysis Under Permutations

Peer Review of Applied Machine Learning Papers Must Include Code Execution

Physics-Informed Optimal Control by Control-Only Supervision with Error Guarantees on Value and Policy

Plan4D: Generative Plannable 4D Worlds

Primal-Dual Guided Decoding for Constrained Discrete Diffusion

Prior Text-Informed Gate Attention Framework for Multimodal Psychiatric Disorder Diagnosis

PRISM: Asymmetric Precision-Recall Optimization for Million-Scale Root Cause Analysis

Privately Estimating Monotone Statistics in Polynomial Time

Probabilistic Guarantees for Adversarial Linear Contextual Bandits

RAMA: Resistance-Aware Multi-Hop Aggregation Graph Representation Learning for Robust Ethereum Account Classification

Random-Set Graph Neural Networks

Realism VS Accuracy: Event Sequence Forecasting from a Generative Modeling Perspective

Recon: Reconstruction-Guided Reasoning Synthesis for User Modeling

Recursively Trained Diffusion Models: Limiting Collapse Distribution and Spectral Characterization

ReFree-S2V: Towards Realistic Co-Speech Video Generation via Reward-Free RL and Multilevel Speech Guidance

Regret minimization in Linear Bandits with offline data via extended D-optimal exploration.

Rehearsal-Free Statistical Prototype Regularization for Federated Incremental Learning

Restoring the RNA-Ligand Interaction Manifold via Topology-Preserving Contrastive Learning under Epistemic Uncertainty

Rethinking Radar 3D Perception: Representation Learning from Raw Spectra

ROAR: Benchmarking LMM Agents under Real-Time Constraints in Multiplayer Action-Shooter Games

Robust Task-Aware State Estimation from Pre-trained Perception

Securing AI Agents with Information-Flow Control

Select-then-differentiate: Solving Bilevel Optimization with Manifold Lower-level Solution Sets

Semantic Priors Meet Statistical Evidence: Robust Forests for Few-Shot Tabular Learning

Sharp feature-learning transitions and Bayes-optimal neural scaling laws in extensive-width networks

Space Group Conditional Flow Matching

Sparse Sum-of-Squares Layers for Certified Learning

Spectral Annealing: Normalization-Path Exploration for Large-Scale Ising Optimization

Spectral Geometry of Attention: From Information Routing to Uncertainty

SS3D: End2End Self-Supervised 3D from Web Videos

Stable and Scalable Probabilistic Numerical Solvers for Stiff and High-Dimensional ODEs

stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation

STAC-R: Subspace-Tracked Activation Compression with Residuals

StarWM: Self-Supervised Trained Attention Routing for Robust World Models

State-Action Selection in General Stochastic Games under Regularized Policy Gradient Methods

Statistical Inference in Causal Partial Identification under Smooth Densities

Stochastic Grouping Conformal Prediction for Effective Subgroup Reliability

Strongly Adaptive Online Learning with Time-Varying Movement Cost

Structure vs. Chaos: Asymmetric Entropic Optimization for Enforcing Instruction Hierarchy

Sublinear Variational Optimization of Gaussian Mixture Models with Millions to Billions of Parameters

Support-Safe Variational Hybrid Filtering for Contact-Mode and Sparse-Law Recovery

Surprisingly consistent failures of post-hoc OOD detectors reveal security concerns in open-set recognition with modern CNNs and ViTs, stemming from representation mismatch

TabK: Amortized Bayesian Estimation of the Number of Clusters in Tabular Data

Targeted Synthetic Control Method

TARP: Trace-Anchored Regularization Prior for Retaining Stepwise Reasoning

Task-Driven Bayesian Experimental Design Yields Singly Intractable Objectives for Joint Policy Training

Temporal Consistency Improves Generalization in Contextual Offline Meta Reinforcement Learning

Terminal Failure Is Not Computational Failure: A Pre-Collapse Readout Regime in Nonlinear Dynamical Learners

The Bayesian Origin of the Probability Weighting Function in Human Representation of Probabilities

The Communication Bottleneck: A Round-Trip Study of Compositional Serialization in Language Models

The Multi-Block DC Function Class: Theory, Algorithms, and Applications

The Optimal Control Foundation of Early Exits – Turnpikes and ResNets

The PFAD Not Taken: Measuring Polysemanticity via Feature Affine Decomposition

The Ringelmann Effect in Multi-Agent LLM Systems: A Scaling Law for Effective Team Size

The Structural Bias of $\ell_2$-Regularized Cross-Entropy Heads in Class-Incremental Learning: Characterization, Limits, and a Gauge-Anchoring Fix

Timing Is All You Need: SpikeCore, Learnable Delays, and Gain Control for Neuromorphic Classification

Tokenizer-Generator Coupling in Medical Image Generation

ToS: Tree-of-Skill Reinforcement Learning driven by Behavior Tree for Long-Horizon Manipulation

Towards Unified Dynamic Face Landmark Detection

Training-Free Dynamic Upcycling of Expert Language Models

Tree-Ensemble Repair through Constrained Optimization

TrialAgentBench: Evaluating AI Agents for Clinical-Trial Analysis and Long-Horizon Drug-Development Decisions

Trust Guided Decision Transformer

Twisted Schrödinger Bridge Matching

Understanding the Co-evolutionary Solution Exchange of the MOEA/D: Minimal Communication Gives Maximal Speed-Ups

Uniform Diffusion Models revisited: Leave-One-Out Denoiser and Absorbing State Reformulation

UniverSat: Resolution- and Modality-Agnostic Transformers for Earth Observation

Unlocking the Duality between Flow and Field Matching

Unlocking Volition: Proactive Intention Decoding via Interpretable Graph Learning of Multi-Region ECoG

Unrolled gradients in disguise: bridging interpolation-based and Jacobian regularization for stable neural dynamics

Weight Space Learning needs to unify benchmarking! A taxonomy of evaluation practices

Weisfeiler and Leman Follow the Arrow of Time: Expressive Power of Message Passing in Temporal Event Graphs

What’s in a Smoothness Constant? Tight Rates for Local SGD with Bounded Second-order Heterogeneity

When Empathy Misses the Goal: A Benchmark for Goal Displacement in LLM Advice

Why Decoding Sharpens Without Resolving: Lock-in and Confusion in Autoregressive Reasoning

WildBox: A Dataset and Benchmark for Aerial Monocular 3D Detection of African Savanna Wildlife

WorldCoder-Bench: Benchmarking Physically Grounded 3D World Synthesis

Placeholders 10:30-12:30

Paris Temp BTF Poster Holder 1-1

Paris Temp BTF Poster Holder 2-1

Paris Temp BTF Poster Holder 3-1

Paris Temp BTF Poster Holder 4-1

Paris Temp BTF Poster Holder 5-1

Paris Temp BTF Poster Holder 6-1

(ends 12:30 AM)

FRI 11 DEC

12:30 a.m.

Paris Invited Talk:

Claire Monteleoni

Claire Monteleoni

(ends 1:30 AM)

2 a.m.

Paris Oral Session 6 [2:00-3:30]

(ends 3:30 AM)

3:30 a.m.

Paris Poster Session 4 [3:30-5:30]

Posters 3:30-5:30

Adapting to Conflict: Equilibrium Structure and Adaptive Learning in Harmonic Games

Adaptive Multi-view Graph Contrastive Learning via Fractional Continuous Dynamics

Affine Tracing: A New Paradigm for Probabilistic Linear Solvers

A General Filter-Enhanced Approach to Smartphone Hyperspectral Imaging

A Generalized Tikhonov Layer for Interpretable-by-design Graph Neural Networks

AgentKernelArena: Benchmarking Performance and Generalization of AI Coding Agents on GPU Kernels Optimization

AgentRoom: Concurrent Multi-Agent Coding in a CRDT-Backed Shared Workspace

Algebraic Machine Learning: learning as computing subsets of the subdirect decomposition from Abstract Algebra

An Educated Guess: Deriving Statistically Aligned Gradient Estimates for Zeroth-Order Optimization

An Information-Theoretic Evaluation Framework for Benchmark and Model Diagnosis in Knowledge Tracing

A Revisit of Hamiltonian Monte Carlo Efficiency on Bayesian Neural Networks

Articraft: An Agentic System for Scalable Articulated 3D Asset Generation

A Spectral Framework for Closed-Form Relative Density Estimation

Attention-based PCA

Attention Trajectories as a Diagnostic Axis for Deep Reinforcement Learning

Beyond Masked Sparsity: SNACK Enables Truly Sparse Neural Networks on GPU

Beyond Parameter Aggregation: Semantic Consensus for Federated Fine-Tuning of LLMs

Beyond Single-Step Likelihood: Gibbs Variational Last Layers for Long-Horizon Dynamics Learning

Beyond Worst-Case Coreset Bounds for $k$-Clustering via Determinantal Sampling

BlockFormer: Transformer-based inference from interaction maps

BRACE: Bipolar Reference-Aware Calibration and Estimation for Incomplete Multimodal Learning

Breaking Adversarial Transferability in Fine-Tuned Speech Recognition

Causal Abstractions, Categorically Unified

Causal Attribution via Activation Patching

Causal Representation Learning for Generalisable Recommendation

CECAR: Cache & Expert Co-Aware Routing Accelerates On-Device Inference of MoE LLMs

Cheap Per-Component Testing for PLS, Stable Under Rotation

Chem-PerturBridge: a harmonized compendium of small molecule perturbation transcriptomic effects

Cluster with Auctions for Vector Search

Computing Thiele Rules on Interval Elections and their Generalizations

Conservative Continuous-Time Treatment Optimization

Consistent Geometric Deep Learning via Hilbert Bundles and Cellular Sheaves

Constrained MDPs with Trajectory Constraints

Continuous-Time Distribution Matching for Few-Step Diffusion Distillation

Control Reinforcement Learning: Token-Level Mechanistic Analysis via Learned SAE Feature Steering

CoPE-VideoLM: Leveraging Codec Primitives For Efficient Video Language Modelling

Cosine is Human: The Reproducibility Ceiling of Perceptual Similarity

COVD: Continual Open-Vocabulary Object Detection with Novel Concept Injection

Curvature-Dependent Lower Bounds for Frank-Wolfe

D2D: Detector-to-Differentiable Critic for Improved Numeracy in Text-to-Image Generation

DAG-Biased Graph Learning for Multimodal Survival on EHR

Dancing in Fetters: Pareto-Optimal On-Device LLMs under Hardware Constraints

DC-DiT: Adaptive Compute and Elastic Inference for Visual Generation via Dynamic Chunking

Decentralized $\mu^2$-SGD: Narrowing the Parallelism Gap to Centralized Learning

Decentralized Ranking Aggregation via Gossip: Convergence and Robustness

Decoupled Mode Connectivity for Base-to-Novel Generalization in Vision-Language Models

Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depth

Difference of Convex Programming in the Wasserstein Space with Applications to MMD Optimization

Dimension-Uniform Discretization Analysis of Preconditioned Annealed Langevin Dynamics for Multimodal Gaussian Mixtures

Diversity Curves for Graph Representation Learning

Do Heavy Tails Help Diffusion? On the Subtle Trade-off Between Initialization and Training

DP-EGGROLL: Centered Fitness-Vector Privatization for Backprop-Free Differentially Private Optimization

Early Detection of Backbone Divergence via Neighborhood Structure in Learned Embeddings

Effective Biological Representation Learning by Masking Gene Expression

Efficient and Robust Physical 3DGS-MPM Simulation via Interior Filling and Text-Physics Optimization

Efficient One-to-many Domain Translation via Diffusive Entropic Optimal Transport

Emergent Semantic Role Understanding in Language Models

Endowing Your Vision-Language-Action Model with a Predictive Mind

Enhanced convergence guarantees of score-based generative models in $\mathcal{W}_2$-distance beyond log-concavity

Exact Regular-Constrained Sampling for Variable-Order Markov Generation

Eyes on VLM: Benchmarking Gaze Following and Social Gaze Prediction in Vision Language Models

FacePhys: State of the Heart Learning

Fast Alignment of Embeddings: Computational Guarantees for Anisotropic Procrustes-Wasserstein

Fast, Relaxation‑ and Hyperparameter‑Free Pairwise Worst-Case Class Separation

Few Channels Draw The Whole Picture: Revealing Massive Activations in Diffusion Transformers

FiLM-CAM: Keyed Feature Modulation for Conditional-Access Watermarking

Fixed-Point Masked Generative Modeling

Flow-Transformed Implicit Processes for Function-Space Variational Inference

Follow the Winners: Conservative Policy Improvement with the Cross-Entropy Method for Critic-Free RFT

Foveated BagNet: Inherent Interpretability Does Not Exclude Global Context

Frame the adversary: a structure-aware attack methodology

Generalized Bayes for Causal Inference

Generate in Reconstruction Space, Match in Semantic Space: Transport Geometry for One-Step Generation

GeoDial: A Multimodal Dialog Tutoring Dataset for Geometry Problem-Solving with Visual Tutor Turns

Global Convergence in Deep Networks via the Second Law of Thermodynamics

GradShield: Alignment Preserving Finetuning

Half-Truths Break Similarity-Based Retrieval

Hard Attention Transformers and BSS-Machines

HARP: Training-Free Dual-Profile Agentic Communication for LLM-Based Recommendation

HelpBench: Assessing the Ability of LLMs to Provide Privacy, Safety, and Security Advice

Hierarchical Conformal Classification

Hybrid Probabilistic Zonotopes for Identifiable and Refinable Predictive Uncertainty

Image Generation for Automotive Lidar Open-vocabulary Semantic Segmentation

InCLAD: A Continual Learning Benchmark for Industrial Visual Anomaly Detection

Know What You Need: Efficient Activation Checkpointing

Large language models suffer from a curse of ambiguity

Latent Debate: A Surrogate Framework for Interpreting LLM Thinking towards Binary Decisions

Learning Better Certified Models from Empirically-Robust Teachers

Lethe: Link Inference Attacks For Evaluation of Edge Unlearning Methods

Likelihood-free inference of phylogenetic tree posterior distributions

ListQA: A Benchmark for Evaluating List-Formatted Factual Knowledge Retrieval in Large Language Models

LLM-Enhanced Random Forests in Orthogonal Hyperbolic Subspaces for Tabular Learning

LoopRPT: Reinforcement Pre-Training for Looped Language Models

Lost or Hidden? A Concept-Level Forgetting in Supervised Continual Learning

Match the Geometry, Skip the Surrogate: Extreme Low-Budget Optimization in High Dimensions

Mean-Field Control on Sparse Graphs: From Local Limits to GNNs via Neighborhood Distributions

Measuring Black-Box Confidence via Reasoning Trajectories: Geometry, Coverage, and Verbalization

Memory-Driven Contrastive Embedding Enhancement for Fine-Grained Open-Set Semi-Supervised Learning

Mesh Invaiant Infinite Dimensional Adaptive MCMC for Latent Gaussian Processes

Meta-Learning Preferences for Multilingual LLM Alignment

Midpoint Generative Models

Minimax Optimal Early-Stopped Gradient Descent for Gaussian Mixture Classification

(Mis)generalization of Helpful-Only Fine-Tuning

Mixture of Attribute-Aware Attention Experts for Fine-grained E-Commerce Composed Image Retrieval

Momentum Smooths the Path to Gradient Equilibrium

MONET: A Massive, Open, Non-redundant and Enriched Text-to-image dataset

Mosaic: A Benchmark Suite for Differentiable Physics Solvers

Muon Dynamics as a Spectral Wasserstein Flow

Mutable Transcripts: Mitigating Context Pollution through Editable Conversation State

Near-Optimal Decentralized Stochastic Convex Optimization over Networks

Neural Fractional Stochastic Differential Equations

NeuroNTP - A Generalizable Multimodal Foundation Model for Epilepsy

Neurosymbolic Learning for Inference-Time Argumentation

NOCE-Net: Representation Learning for Battery Operational Context via Nested Sequence Modelling

Normative Networks for Source Separation via Local Plasticity and Dendritic Computation

One View Is Enough: In-the-Wild Monocular Pretraining for Novel View Generation

On the Bias of Group-Based Advantage Estimation

OpenMedReason: Scientific Reasoning Supervision for Medical Vision–Language Models

Optimal Convergence Analysis of DDPM for General Distributions

Optimal Rates for Adaptive Private $k$-PCA

Optimizing Social Utility in Sequential Experiments

Partition Tree: Conditional Density Estimation over General Outcome Spaces

PDHFormer: Progressive Dual-Head Transformer for Behavioral Choice Prediction

PENEX: AdaBoost-Inspired Neural Network Regularization

Perception for Action in Latent World Models

Personalized Safety in Federated Fine-Tuning of Large Language Models

PE-SHAP: Causally Interpretable Path-Wise Shapley Explanations

POETS: Uncertainty-Aware LLM Optimization via Compute-Efficient Policy Ensembles

Polar Transformers: $SO(2)^K$-Equivariant Angular Attention for Cryo-EM Image-Set Processing

Positional Encoding Is All You Need For Scalable Equivariance Constraint Relaxation

Prediction-Intervention Games and Invariant Sets

Preference-Guided Adversarial Policy Optimization for Long-Tail Robust Driving

Private Prediction via Shrinkage

ProSearch: Benchmarking Multi-Constraint Protocol Retrieval in Experimental Science

Provable State Estimation with Recurrent Models

Pure Exploration Beyond Reward Feedback: The Role of Post-Action Context

QMaxCal: Path-Space Regularization for Open Quantum Control via Girsanov's Theorem

Qrita: High-performance Top-k and Top-p using Pivot-based Truncation and Selection

Quantifying Concentration Phenomena of Mean-Field Transformers in the Low-Temperature Regime

Quantizing With Randomized Hadamard Transforms: Efficient Heuristic Now Proven

Redefining Instance Matching: A Unified Framework for Part-Aware Matching in Panoptic Segmentation Evaluation

Referring and Reasoning Camouflaged Object Segmentation in Audio-Visual Scenes

Reflected Schrödinger Bridge Matching

Reinforced Evidence-Aware Long Video Understanding

Residual Expertise Is Not Decision Value

Rethinking Attention in Depth for Operator Learning

Rethinking Expressivity and Efficiency in Test-Time Training

Rethinking Layer-wise Model Merging through Chain of Merges

Retrieval from Within: An Intrinsic Capability of Attention-Based Models

Robust Flow Matching under Target Corruption and Label Noise

RoSA: Rotational Sparse Adaptation for Memory-Efficient Fine-Tuning

Routing Subspaces: Auditing Evaluation-to-Deployment Mismatch in Fine-Tuned Language Models

ScrapeGraphAI-100k: Dataset for Schema-Constrained LLM Generation

Selling Information While Being an Interested Party

Semantic Motion Anchors: Bridging Motion and Meaning in Co-Speech Gestures

Shared Modular Recurrence in Contextual MDPs for Universal Morphology Control

Skip the Hessian, Keep the Rates: Globalized Semismooth Newton with Lazy Hessian Updates

SOLA: A Structured Operator Library for Attention in Pretrained Vision Transformers

Solving Stochastic Control under Multiplicative and Internal Noise via Constrained Optimization

Sparse Attention as Compact Kernel Regression

Speeding up Log-Sum-Exp: Kernel Fusion at the Memory Wall, Integer Arithmetic at the Compute Wall

Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation

StemBind: When MLLMs Get Lost Between Rules and Instances in Abstract Visual Reasoning

Strategic PAC Learnability via Geometric Definability

Sub-Gaussian Confidence Intervals for Heavy-Tailed Data: Characterizing the Limits of Inference

Submodular Multi-Agent Reinforcement Learning for Effective Online Distributed Task Allocation

TabBioMed: A Large-Scale Benchmark for Biomedical Tabular Learning

TabPrep: Closing the Feature Engineering Gap in Tabular Benchmarks

TAMEing the Open-World Personalization: Towards Open-Set Personalized MLLM Assistant

Temporal-Scale Sensitivity in Time-Series Tokenization and Scale-Robust Token Estimation by Gated Sum

Tessellations of Semi-Discrete Flow Matching

Text-to-CAD Evaluation with CADTests

The BV4 Benchmark for Unsupervised Anomaly Detection in High-Dimensional Spectral Data Streams

The Deadline Effect: Identifying and Correcting Temporal Bias in Human Evaluation

The Dead Salmons of AI Interpretability: The Need for a Statistical Inference Perspective

The Future of Facts: Tracing the Factual Generation-Verification Gap

The Horizon Threshold in Cooperative Multi-Agent Reward-Free Exploration

The Neural Race Model

Theoretical guidelines for annealed Langevin dynamics in compositional simulation-based inference

The Panel Complexity of Sortition: Is 12 Angry Men Enough?

The Sampling Complexity of Condorcet Winner Identification in Dueling Bandits

Think2SQL: Blueprinting Reward Density and Advantage Scaling for Effective Text-to-SQL Reasoning

Thinking in Boxes: 3D Editing in Real Images Made Easy

TIDE: Asymmetric Neural Circuits for Stabilized Temporal Inhibitory-Excitatory Dynamics

Too Early for AI-Assisted Peer Review: A Systematic Account of the Limits and Opportunities of Automating Human Judgment

TopoFisher: Learning Topological Summary Statistics by Maximizing Fisher Information

Towards Complementary Keypoint Detection via Mixture of Detectors

Towards High Semantic Fidelity: Hyperdimensional Symbolic Messages in Multi-Agent Communication

Towards more general control of diffusion models using Jeffrey Guidance

Tracing Actual Causes with Counterfactual Witness Maps

Training a Predictive Coding Network on ImageNet using Equilibrium Propagation

TRIM: A Theory of Retrieval with Incremental Memory -- Defect, Benefit, and Critical Horizon

Unifying Sparsity and Discreteness: One-Shot Pruning for Quantized LLMs via Discrete Optimization

Unpaired Canonical Correlation Analysis

Velocity Ambiguity Profiles: Time-Resolved Bayes-Risk Diagnostics for Flow Matching

VeriGraph: Towards Verifiable Data-Analytic Agents

ViroGym: Realistic Large-Scale Benchmarks for Evaluating Viral Proteins

Virtual Double Oracle: Faster Convergence by Leveraging Strategies That Were Watching All Along

VolCo: Volumetric Contact for High-Fidelity Human Grasp Generation

WebArena-Pro: A Heterogeneous, Multimodal, Reproducible Benchmark for Web Agents

We Need to Improve Benchmarks in AI for Mathematics

We Need to Rethink Benchmarking in Anomaly Detection

When Attention Collapses: Residual Evidence Modeling for Compositional Inference

Why Do Time Series Models Need Long Context Windows?

Within-Model vs Between-Prompt Variability in Large Language Models for Creative Tasks

You Don’t Need Aligned Representations: Knowledge Distillation via Random Prototype Spaces

Your Neighbors Know: Leveraging Local Neighborhoods for Backdoor Detection in Decentralized Learning

Placeholders 3:30-5:30

Paris Temp BTF Poster Holder 1-2

Paris Temp BTF Poster Holder 2-2

Paris Temp BTF Poster Holder 3-2

Paris Temp BTF Poster Holder 4-2

Paris Temp BTF Poster Holder 5-2

Paris Temp BTF Poster Holder 6-2

(ends 5:30 AM)

7 p.m.

Paris Oral Session 7 [7:00-7:30]

(ends 7:30 PM)

8:30 p.m.

Paris Oral Session 8 [8:30-10:00]

(ends 10:00 PM)

Paris Invited Talk:

What Abundance Hides: Lessons from Building AI Under Constraint

Pelonomi Moiloa

(ends 9:30 PM)

9:30 p.m.

Paris Poster Session 5 [9:30-11:30]

Posters 9:30-11:30

$\varphi$TD: Distributional Reinforcement Learning using Characteristic Functions

2-Step Agent: How a Bayesian Decision Maker Learns from AI-Decision Support

Accelerating Long-Context LLM Prefill via Layer-wise Progressive Token Pruning in Local Deployment

ACDP: Architecture-aware Cross-Dataset Performance Predictor for NAS

A dynamical systems theory of reward-modulated learning in linear recurrent networks

AIRA 2: Overcoming Bottlenecks in AI Research Agents

Amortized Structured Stochastic Variational Inference for Gaussian Process Latent Variable Models

Annealing in variational inference mitigates mode collapse: a theoretical study on Gaussian mixtures

APM: Evaluating Style Personalization in LLMs with Arbitrary Preference Mappings

Are Easier or Harder Examples Better? Rethinking Data Selection for Reward Models and Preference Optimization

A Separation Principle for Cooperative Multi-Agent Reinforcement Learning

A Topological Sorting Criterion for Random Causal Directed Acyclic Graphs

AudioGS: High-Fidelity Neural Audio Compression via Continuous Gaussian Splatting

Auditing is not Evaluating: LLM Audit Requires Dynamic, Contextual, Budget-aware and Reliable Evidence

Autofocus Retrieval: An Effective Pipeline for Multi-Hop Question Answering With Semi-Structured Knowledge

Batched Stochastic Linear Bandits with 1-Bit Communication Constraints

Beyond Bag-of-Words: Diagnosing Compositional Binding Failures in Vision-Language Models

Beyond Chamfer Distance: Granular Order-aware Evaluation Metric For Online Mapping

Beyond Isotropy in JEPAs: Hamiltonian Geometry and Symplectic Prediction

Boosting Inference with Guided Reasoning: Stochastic Exploration for Recursive Models

Calibrated Safe Policy Improvement for Continuous Offline Reinforcement Learning

Canonical Predictive Quotients: A Theory of Prediction under Hidden Predictive State Uncertainty with ICL Implications

Causal-VLM: Dense Causal Captioning in Videos

Certifiably Optimal Robust Angular Synchronization

C-LoRA: Continual Low-Rank Adaptation for Pre-trained Visual Models

Coherence Mechanisms for Provable Self-Improvement

Computationally Efficient Replicable Learning of Parities and Applications

ConfDet: Learning Reliable Confidence for MLLM-based Detection

Consistency Regularised Gradient Flows for Inverse Problems

Contextual Flow Matching: Adaptive Step Selection in Flow Models for Efficient Visual Generation

Conveyance: A Versatile Framework for Learning in Structured Class Spaces

Corruptions of Supervised Learning Problems: Typology and Mitigations

Counterfactual Maps: What They Are and How to Find Them

CRAFT: Conflict-Resolved Aggregation for Federated Training

CurveBench: A Benchmark for Exact Topological Reasoning over Nested Jordan Curves

Data-Driven Covariate Selection for Nonparametric and Cycle-Agnostic Causal Effect Estimation

Dataset Collections: Challenges of Large-Scale Data Aggregation in 3D Medical Image Datasets

Decentralized AI Governance Must Decouple Policy Processing from Capability Enforcement

Decomposing One Professional-Framing Pipeline: Which Components Shift LLM Safety Boundaries?

DeFlowCritic: Dense Latent Reward Alignment for Text-to-Image Flow Matching Models

DepthGraft: Structural Regularization through Hierarchical Cross-Layer KV Reconstruction

Differentiable Knapsack and Top-k Operators via Dynamic Programming

Differentiable Nonlinear Model Predictive Control

DiLaDiff: Distilled Latent-augmented Diffusion for Language Modeling

DNS-Calibrated Local Stochastic Transition Closure for PDE-Free Long-Horizon Turbulence Diffusion

DPPE: Rethinking Camera-Based Positional Encoding for Scaling Multi-View Transformers

DynaSub: Adaptive Subgrouping for Scalable Representation Learning

Echo learning enables biologically plausible temporal credit assignment

Ensemble Distributionally Robust Bayesian Optimisation

Entropy-Gated Latent Recursion

Even More Guarantees for Variational Inference in the Presence of Symmetries

Factorized Self-Supervised Speech Tokenization

Fast Learning Rates for Physics-Informed Kernel Methods

Feature-Context Consistency: Unsupervised Adversarial Detection with Drift Stability on Attributed Graphs

Federation Is the Way Forward for AI Agents

Feedback Forensics: A Toolkit to Measure AI Personality

Filtered-Trace Online Variational Training for Probabilistic Spiking Neural Networks

Flexible Intensities Matter: A comprehensive re-evaluation of Classical and Neural Temporal Point Processes

From Inexact Gradients to Byzantine Robustness: Acceleration and Optimization under Similarity

FusionProt: Fusing Sequence and Structural Information for Unified Protein Representation Learning

GDMD: Guiding Distribution Matching Distillation with Gradient-Based Reinforcement Learning

General Agent Evaluation

Generalization Dynamics of Linear Diffusion Models

Generalizing the Geometry of Model Merging Through Fréchet Averages

Geometric Inductive Biases for Semi-Supervised Equalization: The Constellation-Aware Transformer

GRASP: Guided Residual Adapters with Sample-wise Partitioning

GridDiffuser: Constraint-Guided Graph Diffusion for AC Optimal Power Flow

GT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game Theory

Harnessing Accurate and Automatic Trend Detection in Data Streams via Tbps-Level Inference

Heterogeneous Agent Collaborative Reinforcement Learning

High-Probability Minimax Adaptive Estimation in Besov Spaces via Online-to-Batch

How Do Language Models Understand Tables? A Mechanistic Analysis of Cell Location

How LLMs Distinguish Threats from Offers

How Should Parallel Langevin Chains Share Noise?

Hypernetworks for Dynamic Feature Selection

Hyperparameter Transfer for Dense Associative Memories

Improved Algorithms for Online Classification with Surrogate Losses

In-Context Learning for Remote Sensing Vision: A Semantic-Aware Rotation-Robust Diffusion Framework

Inference-Time Refinement Closes the Synthetic-Real Gap in Tabular Diffusion

Instability of Meta-Learning Intrinsic Rewards for Policy Gradient Reinforcement Learning

Integrating Local and Global Entropy for Uncertainty Quantification in LLMs

Interpretability-by-Design with Accurate Locally Additive Models and Conditional Feature Effects

Interpretable Machine Learning Evaluates Differential Therapy Effects in Parkinsonian Gait

It's All Training: A Fully Synthetic Single-Stage Recipe for LLMs

JaSpec-LID: Local Intrinsic Dimension Estimation via Jacobian Spectra of ODE-based Generative Models

JEPAWG: Interpretable Hypernetworks for Weight-Space Physics

KINDER: Kernel-based Independence for Fair Representation Learning via Prototype-space Erasure

LAtte: Hyperbolic Lorentz Attention for Joint-Subject EEG Classification

Learning Global Probabilistic Explanations

Learning Reusable Options by Decomposing Neural Policies

Learning to Bid in Repeated Second-Price Auctions with Dynamic Values and Aggregated Feedback

Learning to Drive in New Cities Without Human Demonstrations

Learning to Learn from Multimodal Experience

Length Generalization for Transformers via Compression

LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

Liars' Bench: Evaluating Lie Detectors for Language Models

Listening to the Retriever: Perturbation-Sensitive Question Selection for Interactive Person Retrieval

Long-Range Spatio-Temporal Graph Propagation Through Oscillations

LSC-Parlament: An Automatically Aligned Catalan Sign Language Dataset from Parliament Videos.

Market-Based Runtime Resource Allocation for LLM Multi-Agent Systems

Maxitive Donsker-Varadhan Formulation for Possibilistic Variational Inference

MedFlowSeg: Flow Matching for Medical Image Segmentation with Frequency-Aware Attention

MedZERO: Self-Evolving Agents for Open-Ended Medical Reasoning Through Controlled Knowledge Accumulation

Memoir: Let the Model Direct Its Own Story for Robust Cross-Domain Knowledge Editing

Minimax Private Estimation of Smooth Optimal-Transport Maps

Mining Logic under Uncertainty: Probabilistic Soft Logic with Energy-Based Inference for Chain-of-Thought Verification

Mixed-Curvature Geometric Latent Diffusion Model for Graph Generation

Models That Know How Evaluations Are Designed Score Safer

MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image

Nautilus: From One Prompt to Plug-and-Play Robot Learning

Near-Optimal Stochastic Linear Bandits with Delay

NeRFix: fixing subtle mistakes in the quadrature of the NeRF volumetric integral

Neural Chameleons: Language Models Can Learn to Hide Their Thoughts from Unseen Activation Monitors

Neural Fourier Transform for Multiple Time Series Prediction

Neuromodulated Constrained Autoencoders for Context-Dependent Manifold Learning

Not Another Text Benchmark: Putting the “Visual" Back in Visual Question Answering for Large Video Models

NTK Regression under dual power-law model: Deterministic Equivalents via SDE and PDE Methods

Off-Policy Evaluation of Large Language Models via Learned Semantic Bottleneck Embeddings

OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence

One World, Dual Timeline: Decoupled Spatio-Temporal Gaussian Scene Graph for 4D Cooperative Driving Reconstruction

On objective mismatch in molecular retrieval from tandem mass spectrometry

On Rate-Optimal Partitioning Classification from Observable and from Privatised Data

On the Pitfalls of Instance-Based Dynamic Curricula

ORCAID: Oblique Rule-Based Continuous-Action Interpretation for Deep RL Policies

Outcome-Based RL Provably Leads Transformers to Reason, but Only With the Right Data

OWCE: Revealing Language Model Complementarity via Online Weakness-Conditioned Evaluation

PAC-Bayesian Bounds for Learning Partially Observed Stochastic Linear Time-Invariant State-Space Systems with Inputs and Sub-Gaussian Noise

Performative Prediction with Selective Labels

PhysRemover: A Unified Framework for Physically Realistic Object Removal

Position: Let’s Strengthen Verifiability if We Can’t Enforce Reproducibility

Predictive Geometry of Hidden Trajectories in Transformers

Predict-Project-Renoise: Sampling Diffusion Models under Hard Constraints

Prefill-Guided Trace Allocation for Sample-Efficient Test-Time Scaling

Principled Federated Random Forests for Heterogeneous Data

PRISM: Polarimetric Road-surface Intelligent Sensing and Measurement Dataset

Probabilistic Data-Driven Modelling of Astrophysical Transients: The Neural Process Family for Ultrafast and Class-Agnostic Light Curve Reconstruction

Probing for Representation Manifolds in Superposition

Probing Persona-Dependent Preferences in Language Models

ProgramBench: Can Language Models Rebuild Programs From Scratch?

Progressive Signal Calibration for Medical Image Segmentation: Diagnosing and Correcting Structural Misalignment in Training Signals

Prune to Protect: Faster Training and Enhanced Privacy by Dynamic Data Pruning

PVFormer: Proper Velocity Transformer for Stable and Scalable Hyperbolic Representation Learning

RamanBench: A Large-Scale Benchmark for Machine Learning on Raman Spectroscopy

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning

REFORM-3D: A Representation-Centric Evaluation Framework for 3D Medical Vision Foundation Models

Resilient Byzantine Agreement with Predictions

Retrieve-then-Rerank Inference for Vocabulary-Based End-to-End Driving

Revisiting Cross-View Completion: Self-Supervised Pre-Training via Reconstruction Error Comparison

Reviving the Discarded High-Resolution Feature for Transformer-Based Tiny Object Detection

RL-Guided Contraction of Symbolic Tensor Networks for Quantum Circuit Equivalence

Robust and Scalable Collaborative Learning via Pull-Based Epidemic Communication

Routers Learn the Geometry of Their Experts: Geometric Coupling in Sparse Mixture-of-Experts

Safe Offline Reinforcement Learning using Behavior Regularisation and Latent Feasibility-Guidance

Scalable Multi-Agent Contrastive Reinforcement Learning

Scaling Generative Foundation Models for Chest Radiography with Rectified Flow Transformers

Scheming Is a Symptom: Alignment Research Should Probe Reflexive Fragility

Selectivity and Shape in the Design of Forward-Forward Goodness Functions

Shuffle and Joint Differential Privacy for Generalized Linear Contextual Bandits

Simplifying Transformer-Based U-Net Neural Physics Simulators

SING-CH: Task-Scale-Agnostic Lifelong Cross-Modal Hashing on Statistical Manifolds

Smooth Piecewise Cutting for Neural Operator to Handle Discontinuities and Sharp Transitions

Soft Forward-Backward Representations for Zero-shot Reinforcement Learning with General Utilities

SOPO: Socratic Guided Policy Optimization for Span-Level Hallucination Detection

Sparse Video Generation Propels Real-World Beyond-the-View Vision-Language Navigation

Spectral Quantum Memory for Implicit Neural Representations

SPRING: Solver-guided Process Rewards for Novel Logical Reasoning Steps Generation

Stein Transport for Generative Modeling

Super-Level-Set Regression: Conditional Quantiles via Volume Minimization

Supervised Distributional Reduction via Optimal Transport and Dependence Maximization

Surjective Pseudo-Invertible Neural Networks

SyncLight: Single-Edit Multi-View Relighting

Target-Budget Best-Function Identification for Scaling-Law-Guided Model Selection

Test-Time Compute Games

Test-Time Personalization: A Diagnostic Framework and Probabilistic Fix for Scaling Failures

TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection

The Benefits of Temporal Correlations: SGD Efficiently Learns k-Juntas from Random Walks

The Causal Description Gap: Information-Theoretic Separations Across Pearl's Hierarchy

The Geometry of Linear Program Compression: An Exact Characterization and Learning Algorithm

The Hidden Power of Scaling Factor in LoRA Optimization

THEIA: A Multimodal Dataset and Benchmark for Vision-Language Analysis of Layout

The Labeling Problem in Hallucination Detection Benchmarks: An Empirical Evaluation

Theoretical guarantees for Banded Approximations of Gaussian Processes

Theory of Optimal Learning Rate Schedules and Scaling Laws for a Random Feature Model

The Pareto Frontier of Randomized Learning-Augmented Online Bidding

The Power of Second Order Methods for Sequence Preconditioning

The Sample Complexity of Multiple Change Point Identification under Bandit Feedback

Think about how AIs think about themselves

TIDES: Implicit Time-Awareness in Selective State Space Models

Tight $L_\infty$ Sample Complexity for Low-Degree and Sparse Boolean Polynomials

Tight PAC-Bayes Generalisation Guarantees for Large Language Model Safety Monitoring

TORNADO: Adaptive Latent Stochastic Transport for Calibrated Probabilistic PDE Forecasting

Toward Embodied World Agents via Embodied-Planning Dataset and Interactive World Models

Towards Understanding Self-Pretraining for Sequence Classification

Training-Free Active Test-Time Adaptation for Vision-Language Models

Transporting the Past: An Optimal Transport View of Backtracking Counterfactuals

UGGRH: Unsupervised Generative Completion and Graph-attention Refinement for Incomplete Cross-modal Hashing

Umbilic Multinomial Logistic Regression

UncertainGen: Scalable Uncertainty-Aware Representation Learning of DNA Sequences

Understanding diffusion models requires rethinking (again) generalization

Understanding the Curse of Unrolling

UniPrefill: Universal Long-Context Prefill Acceleration via Block-wise Dynamic Sparsification

UniVR: Thinking in Visual Space for Unified Visual Reasoning

Validating Causal Abstraction Metrics on Simulated Complex Systems

Virtual-Flow: Virtual Microphone-based Speech Enhancement via Unsupervised Flow Matching

What DNA Foundation Models Learn Beyond Sequence Composition

What to Predict for Efficient Scheduling on Parallel Machines

When Streaming Fails: Dynamic Algorithms for Unconstrained Submodular Maximization

When to Align, When to Predict: A Phase Diagram for Multimodal Learning

World-Model-Inspired Flicker State Modeling for Burst Flicker Removal

X2HDR: HDR Image Generation in a Perceptually Uniform Space

ZEBRA: Zero-shot Budgeted Resource Allocation for LLM Orchestration

Zero-Shot Burst Restoration via Diffusion MAP Inference with Poisson-Gaussian Noise Likelihood

Zero-Shot Quantization via Weight-Space Arithmetic

(ends 11:30 PM)

11:30 p.m.

Paris Oral Session 9 [11:30-1:00]

(ends 1:00 AM)

SAT 12 DEC

12:30 a.m.

Paris Poster Session 6 [12:30-2:30]

Posters 12:30-2:30

2D Spatial Reasoning with Adaptive Neural Cellular Automata

Accuracy of Noise Ceiling Estimators for Brain Scores

A Comprehensive View of Fairness through Distributional Stability

A Dynamic Decomposition Strategy for the MOEA/D With Proven Performance Guarantees

A Free Lunch in LLM Compression: Revisiting Retraining after Pruning

AI-Mediated Communication Can Steer Collective Opinion

A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks

AM-Bench: A Unified Taxonomy and Evaluation Suite for Agentic Misalignment

Amortized Bayesian Experimental Design with In-Context Knowledge Conditioning

Anatomy-Activated Mixture-of-Experts for 3D Medical Vision-Language Pre-training

An exact information theory of generalization phase transitions in Bayesian diffusion models

A probabilistic model of visual segmentation explains early visual cortical dynamics

A Scalable Nonparametric Continuous-Time Survival Model through Numerical Quadrature

Assessing the robustness of heterogeneous treatment effects in survival analysis under informative censoring

Attention-Based Soft Answer Sets

Attribution-Guided Exit Policy for Reliable Early-Exit Inference

AutoExpert: Automating 3D LiDAR Annotation from Expert-Crafted Guidelines

Backbone-Equated Diffusion OOD via Sparse Internal Snapshots

Bayesian Low-Rank Posteriors for Scalable Membership Inference

Behaviour4All: A Dependency-Aware Toolkit for in-the-wild Facial Behaviour Analysis

Benchmarking Sensor-Fault Robustness in Forecasting

Bench-MFG: A Benchmark Suite for Learning in Stationary Mean Field Games

BESS-Bench: Benchmarking Spectral Representations for Be-Star Variability

Best Arm Identification for Bandits with Shifting Means

Beyond MMSE: Enhancing PnP Restoration with ProxiMAP

Beyond Pixel-wise Supervision: Local Structure Regularization for Semantic Segmentation

Beyond Raw Context Transfer: Representation-based Federated Retrieval-Augmented Generation

Beyond Success Rates: Trainability and Extractability in Offline GCRL

Beyond the Linear Separability Ceiling: Aligning Representations in VLMs

BLADE: Scalable Bi-level Adaptive Data Selection for LLM Training

Breaking BAD: Heterogeneous Byzantine-Robust Federated Learning via Gather and Scatter Scores

Can LLMs Take Retrieved Information with a Grain of Salt?

Can Metadata Fix the Gauge? Calibration Turns Sparse Multi-Source Learning from Sparse PCA into Sparse Mean Recovery

Can the Parts Fool the Test? Counterfactual Pairing Cycles for Relational OOD

CAREBench: Evaluating LLMs' Emotion Understanding by Assessing Cognitive Appraisal Reasoning

Casper: A Projection-Based Neurosymbolic Layer for Scalable & Guaranteed Constraint Satisfaction

Claims of emergence in AI should be grounded in information decomposition

Closed-Form Last Layer Optimization

Closing the Indexing-Decoding Gap in Multimodal Generative Retrieval via Prefix Retention Optimization

Coherent Hierarchical Multi-Label Learning to Defer for Medical Imaging

CoLaX: Context-Aware Local Explanations for Time Series Classification

Comparing Explanations is not Enough,Explain the Change: New Standards are Needed to Explain Behavioral Shifts in Large Language Models

CompleteRXN: Toward Completing Open Chemical Reaction Databases

Concise and Logically Consistent Conformal Sets for Neuro-Symbolic Concept-Based Models

Confidence-Based Decoding is Provably Efficient for Diffusion Language Models

Constraint Retrieval Is Not Constraint Enforcement in Large Language Models

CoRDS: Coreset-Based Representative and Diverse Selection for Streaming Video Understanding

Coresets for Clustering Using Noisy Comparisons and Few Distance Queries

CorridorLight: Cooperation as Task Negotiation with Causal Gating for Traffic Signal Control

CRISP: Fixing Flying Pixels in Latent LiDAR Generation via Diffusion Decoding

CryoGeo: Latent Pose Equivariance for Amortized Ab Initio Cryo-EM Reconstruction

DART: Domain-Agnostic Residual Transfer for Generalist Anomaly Detection

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention

Decoupled Prototype Contrastive Alignment Hashing for Cross-Modal Retrieval

Dense Cross-Tokenizer Distillation via Semantic Optimal Local Alignment

Derivative-Informed Training of Neural Operators On-the-Fly via Sketched Tangent Consistency

Detecting RLVR Training Data via Structural Convergence of Reasoning

DiDE: Direct Injection with Color-Texture DEcoupling for 3D Stylization

Direction-Aware Offline-to-Online Learning in Linear Contextual Bandits

Discovering Mechanistic Models of Neural Activity: System Identification in an in Silico Zebrafish

Discrete Flow Matching: Convergence Guarantees Under Minimal Assumptions

Distilling LLM Feedback for Lean Theorem Proving

Divide et Calibra: Multiclass Local Calibration via Vector Quantization

Do Composed Image Retrieval Benchmarks Require Multimodal Composition?

Does Seeing More Mean Knowing More? Mono-Anchored Advantage Normalization for Multi-Source Visual Reasoning

Dynamic Optimistic Constrained OCO with Memory via Delay Equivalence

Dynamics of Collective Diversity in Human–AI Co-Creation for Creative Tasks

EENAS: Zero-Shot Energy-Efficiency-Aware Neural Architecture Search

Efficient Adaptive Data Acquisition via Pretrained Belief Representations

Efficient Generative Transformer Operators for Million-Point PDEs

Efficient Image Synthesis with Sphere Latent Encoder

End-to-End Verification of Neuro-symbolic Automata via Contrastive Logit-Gaps

Entropy Minimization without Model Collapse: Mitigating Prediction Bias in Medical Imaging

Epistemic Pairwise Maximin Share

Escaping Parameter Space: Tight Generalization Bounds via Representation Quality

Fairness in limited resource prediction-driven decisions

Federated Learning by Utility-Constrained Stochastic Aggregation for Improving Rational Participation

Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Models

FineVision: Open Data Is All You Need

FlexTab: A Flexible Encoder-Decoder Architecture for In-Context Learning Across Diverse Tabular Tasks

Flow-based Spectral Kernel Learning for Nonstationary Attention

FlowBatt: Flow Matching for Probabilistic Battery Degradation Prediction

Flow Matching with In-Context Priors for Out-of-Distribution Brain Dynamics

FMMI: Flow Matching Mutual Information Estimation

FocusNav: Learning Task-directed Perception via Action-Aware Future Reconstruction in Vision-and-Language Navigation

From Representation to Intervention: Using Emotion Vectors to Monitor and Guide Language Models

Generating Symmetric Materials using Latent Flow Matching

Geometric Alignment without Functional Equivalence: A Layer-wise Analysis of the Speech-Text Modality Gap

Geometry-Aware Optimal Transport: Fast Intrinsic Dimension and Wasserstein Distance Estimation

Geometry of Relaxed Fair Regression: A Unified Framework for Aware and Unaware Settings

GeoX: Mastering Geospatial Reasoning Through Self-Play and Verifiable Rewards

GitInject: Real-World Prompt Injection Attacks in AI-Powered CI/CD Pipelines

GLUT: 3D Gaussian Lookup Table for Continuous Color Transformation

Gradient-based Graph Structure Optimisation for Research Networks

Hardware-Friendly Token-Group Activation Quantization for Low-Bit Mamba Super-Resolution

Harmonic Torsional Diffusion for Flexible Protein-Ligand Docking

Harnessing Textual Refusal Directions for Multimodal Safety

Hidden Positives: Why Code Retrieval Benchmarks Underestimate Model Quality

Hierarchical Graph Representation Learning with Pooling-Induced Substructures

How to Scale Mixture-of-Experts: From muP to the Maximally Scale-Stable Parameterization

How to Train Your Latent Diffusion Language Model Jointly With the Latent Space

IDEAL: Interaction Dynamics and Force-Aware Learning for Dual-Humanoid Collaborative Manipulation

i-DEQ: A stable inertial Deep Equilibrium model for image restoration

Implicit-Euler Value Iteration: Long-Horizon Planning via Stable Integration of the Bellman Residual Flow

Improving Diffusion Posterior Samplers with Lagged Temporal Corrections for Image Restoration

Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs

Interpretable but Fragile? Robustness of Concept Bottlenecks under Geometric-Semantic Perturbations

It Cancels: O(r²) Cholesky Updates for Whitened Operators

Joint Treatment Effect Estimation from Incomplete Healthcare Data: Temporal Causal Normalizing Flows with LLM-driven Evolutionary MNAR Imputation

Kernel Granger Component Analysis for Nonlinear Directed Component Discovery

Language Models Can Coarsely Modulate Entropy Under Instruction

Large language models can not and should not be banned from peer review

Layer Free-Riding in Forward-Forward Networks: Real, Repairable, but Not Accuracy-Dominant

Learning from Ranking Feedback: Improved Regret Bounds via Independence Preserving Rank Breaking

Learning interpretable Schur forms of recurrent weight matrices

Learning to Discover Iterative Spectral Algorithms

Ledger: A Path-Validated, Database-Grounded Benchmark for Enterprise Web Agents

LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments

Looking Under the Streetlight: Evaluation in Generative Molecular Dynamics

Markovian Dynamics Enforcer: Feasibility Preserving Correction on Learned Dyanmics Manifolds

Markov Metrical Task Systems

MDMR-Bench: A Multi-Dimensional Benchmark for Multi-Reference Image Generation

Measure Less, Know More: Self-Supervised Test-Time Feature Acquisition

Measuring Cross-Modal Synergy: A Benchmark for VLM Explainability

Measuring Robustness and Efficiency in a Connectome-Constrained Fly Visual System Model on a Collision-Detection Task

Mechanistic Interpretability of EEG Foundation Models via Sparse Autoencoders

Memory flows: geometry and dynamics of sequential retrieval in input-driven Hopfield networks

MIND: Monge Inception Distance for Generative Models Evaluation

Mind the Heads: Topological Representation Alignment for Multimodal LLMs

MINEGRID: A Multi-Modal Benchmark for LLMs Evaluation on Dynamic Modeling of Power Systems

Mirror Descent Beyond Euclidean Stability: An Exponential Separation in Initialization Sensitivity

Mitigating Over-squashing without Rewiring: A Sheaf Effective Resistance Perspective

Monitoring Violations of Differential Privacy over Time

Multi-Armed Bandits With Best-Action Queries

MutQA: A Cross-Validated Q&A Dataset for Genetic Mutations

NAMVIS: Next-Scale Autoregressive Multi-View Image Synthesis

Necessary but Not Sufficient: Spectral Tests for Value-Linear Attention Surrogates

Network Learning with Semi-relaxed Gromov-Wasserstein

Neuro-Inspired Inverse Learning for Planning and Control

NeuroSynTheos: Learning to accelerate counterexample-guided reactive synthesis modulo theories

NIKA: Efficient Neural Video Representation via Structured Latent Diversity

NRF-GS: Neural Residual Fields for Expressive and Compact Gaussian Splatting

Omni-SpikeDet: A Spiking Open-World Detector with Dynamic Text–Image Alignment

One Scan is Enough: Demonstration-Free Adaptation for Language-Guided Navigation

Online Budget Allocation with Censored Semi-Bandit Feedback

On the Complexity of Preference-Based Bandits

On the Convergence of First-Order Methods in Signaling Games

On the Expressive Power and Limitations of Multi-Layer SSMs

OpenWhistle: A Large-Scale Longitudinal Dataset and Benchmark of Bottlenose Dolphin Vocalizations

ORBIT: A Framework for Multi-Agent Security Evaluations

Overthinking as a Symptom of Knowledge Conflict: Understanding and Detecting LLM's Hallucinations in Retrieval-Augmented Question Answering

PACZero: PAC-Private Fine-Tuning of Language Models via Sign Quantization

Participatory ML for Social Harm Should be Constructed, Validated and Reasoned Through First-Person Accounts

Payoff-Only Learning in Games via Best-Response Differential Inclusions

Perception Without Engagement: Dissecting the Causal Discovery Deficit in LMMs

Phaedra: Learning High-Fidelity Discrete Tokenization for the Physical Sciences

PieArena: Ranking and Profiling Language Agents in Realistic Negotiation Scenarios

POLAR-Bench: A Diagnostic Benchmark for Privacy-Utility Trade-offs in LLM Agents

Predicting directional flexibility in proteins

Predicting Only from Selected Evidence: A Tempered Product-of-Experts Bottleneck for Auditable EEG Diagnosis

Profit Maximization in Bilateral Trade against a Smooth Adversary

Propagate to Discover: Graph-Structured Propagation for Generalized Category Discovery

Proxy-Based Approximation of Shapley and Banzhaf Interactions

RankAlign: Unsupervised Vision-Language Representation Alignment via Rank Transformation

Regularized Large Neighborhood Search

Replicable Constrained Bandits

Rethinking Latency Denial-of-Service: Attack the LLM Serving Framework, Not the Model

Rethinking Neural Nonlinearity as Gating

Robust-by-Design Distributional Learning from Contaminated Samples

Rotations on Latent Hyperspheres: a Geometry-Aware Guiding Framework for Diffusion Models

Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift Correction

Scale-Sensitive Shattering: Learnability and Evaluability at Optimal Scale

Seahorse: A Unified Benchmarking Framework for Spatiotemporal Event Modeling

SecureClaw: Clawing Back Control of LLM Agents

Self-Evolving Agents Should Build Internal and External Models of the World

Simulation-aided Reinforcement Learning with Control Variates

Solaris: Building a Multiplayer Video World Model in Minecraft

Spherical Boltzmann machines: a solvable theory of learning and generation in energy-based models

spora: A Unified Multimodal Dataset for Spatial Proteomics

Stochastic Zeroth-Order Optimization Under Heavy-Tailed Noise

Tadpole: Autoencoders as Foundation Models for 3D PDEs with Online Learning

Target-Aligned Reinforcement Learning

TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks

The Agentic Oversight Tax: Human Supervision of AI Agents Has a Cost that Must be Accounted For

The balance between feature learning and collapse in generative dynamical systems

The limbic navigation system as a hierarchical RNN

The State-Prediction Separation Hypothesis

The sublevel Flood bifiltration: towards scalable 2-parameter persistent homology

Too Smart to Teach: The Articulability Ceiling in Language Models

Towards Fairness under Label Bias in Image Segmentation: Impact, Measurement and Mitigation

Towards Identifying Dominant Low-Rank Subspaces in Zeroth-Order Fine-Tuning

Towards instance-dependent regret optimality in Episodic MDPs with Posterior Sampling

Transformers Linearly Represent Highly Structured World Models

TurtLES: A Large-Scale Benchmark for Turbulent 3D Neural PDE Surrogates

Understanding axial attention in TSFMs through single location regression

VACE: Learning Geometrically Structured Representations for Time Series Anomaly Detection

Very Fast Bayesian Additive Regression Trees on GPU

Voronoi-Markov chain and spatial entropy for point pattern analysis

What are Key Factors for Updates in RL for LLM Reasoning?

When Actions Matter: Causal Affordances for Long-Horizon Credit Assignment in World Models

When Prompts Override Vision: Instruction-Induced Hallucinations in LVLMs

Where to Approximate in Neurosymbolic Inference?

Where to Look Matters: Rethinking Sub-Volume Sampling in 3D Medical Self-supervised Learning

Who caused $Y$? Local identifiability for learning causal parents

WORD: Diffusion-Based Posterior Inference for Online Goal Recognition

(ends 2:30 AM)

2:30 a.m.

Paris Oral Session 10 [2:30-4:00]

(ends 4:00 AM)