Skip to yearly menu bar Skip to main content


Poster

What Makes a Good Path? Factoring Manifold Support and Path Geometry

Zhixuan Zhou ⋅ Tingting Dan ⋅ Guorong Wu
Dec 10, 2:00 AM - 5:00 AM Hall C1 #A319
The manifold hypothesis suggests that real-world data concentrates on low-dimensional structures, yet navigating meaningful trajectories on latent manifolds remains an open challenge. A common approach is to construct density-aware metrics, but such constructions bundle two distinct questions: (i) where valid data lies and (ii) how we choose to traverse on the manifold. Since different tasks may demand different traversal behaviors even on the same data manifold, specifying these two aspects independently offers additional modeling flexibility. We propose to factor the path objective into a kinetic term governed by a freely chosen geometric prior and a score-based potential, derived from the negative log-density of a pretrained diffusion model, that acts as a soft constraint for manifold adherence. The potential encourages dynamics to evolve along the data support, while the geometric prior remains free to encode task-specific notions of path optimality. To solve the resulting optimization problem, we introduce \textit{geodesic force matching} (GFM), a direct-collocation algorithm that discretizes the trajectory and optimizes all waypoints jointly to satisfy the Euler--Lagrange force balance in a least-squares sense. On synthetic manifolds and 3D shape interpolation, our method produces smooth, on-manifold paths and performs favorably against recent density-aware baselines, most notably in the low-noise regime where those baselines become numerically unstable.
Show more
View full details
Poster

Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion

Van Chien Nguyen ⋅ Chaitra Hegde ⋅ Van-Cuong Pham ⋅ Ryan Rossi ⋅ Franck Dernoncourt ⋅ Thien H Nguyen
Dec 10, 2:00 AM - 5:00 AM Hall C1 #A218
We introduce Orthrus, a simple and efficient dual-architecture framework that unifies the exact generation fidelity of autoregressive Large Language Models (LLMs) with the high-speed parallel token generation of diffusion models. The sequential nature of standard autoregressive decoding represents a fundamental bottleneck for high-throughput inference. While diffusion language models attempt to break this barrier via parallel generation, they suffer from significant performance degradation, high training costs, and a lack of rigorous convergence guarantees. Orthrus resolves this dichotomy natively. Designed to seamlessly integrate into existing Transformers, the framework augments a frozen LLM with a lightweight, trainable module to create a parallel diffusion view alongside the standard autoregressive view. In this unified system, both views attend to the exact same high-fidelity Key-Value (KV) cache; the autoregressive head executes context pre-filling to construct accurate KV representations, while the diffusion head executes parallel generation. By employing an exact consensus mechanism between the two views, Orthrus guarantees lossless inference, delivering up to a $7.8\times$ speedup with only an $O(1)$ memory cache overhead and minimal parameter additions.
Show more
View full details
Poster

nnTrace: Detecting and Localizing Silent Bugs in Distributed Training

Haitian Jiang ⋅ Shaowei Zhu ⋅ Zhen Zhang ⋅ Zhenyu Song ⋅ Xinwei Fu ⋅ Zhen Jia ⋅ Yida Wang ⋅ Jinyang Li
Dec 10, 2:00 AM - 5:00 AM Hall C1 #A828
Distributed training is essential for scaling LLM training across thousands of GPUs. However, as distributed training requires complex implementations, they are prone to silent bugs, which do not produce explicit error signals but lead to in correct training outcomes. Common debugging practices based on monitoring training loss or gradient norm curves are slow or unable to detect bugs and also do not help localize bugs. We design and implement nnTrace, the first systematic differential testing system for detecting and localizing silent bugs in distributed training. nnTrace aligns intermediate tensors from distributed training with those from a trusted reference implementation. To properly compare the floating-point values in the corresponding tensors, we propose a novel mathematical analysis that provides a guideline for setting tolerances, enabling nnTrace to distinguish bug-induced errors from numerical errors. Experimental results demonstrate that nnTrace effectively detects 11 existing bugs and 3 new bugs in the widely used Megatron-LM framework. nnTrace is effective in various training recipes, including low-precision recipes involving BF16 and FP8. Notably, Megatron-LM has already adopted the method proposed by nnTrace in its development workflow. Our code is available at https://anonymous.4open.science/r/NECK-3C61/.
Show more
View full details
Poster

UDT: Reconciling U-Nets and Diffusion Transformers with Data-Adaptive Token Reduction

Junno Yun ⋅ Yasar Utku Alcalar ⋅ Mehmet Akcakaya
Dec 10, 2:00 AM - 5:00 AM Hall C1 #A224
Diffusion Transformers (DiTs) have emerged as a core architecture in generative modeling due to their scalability and adaptability to multimodal tasks. DiTs comprise isotropic transformer blocks, and learn representations progressively across depth, where the denoising objective drives later layers to focus on fine-detail reconstruction. This results in degraded representation quality and an imbalanced encoder--decoder behavior. Prior approaches such as representation alignment (REPA) mitigate this by encouraging stronger early representations via training regularization. Alternatively, U-Net-style DiT architectures introduce explicit multi-scale encoder–decoder structures for improved convergence. But they build on standard U-Net wisdom via learnable operators for spatial downsampling, which are not well-suited to transformer architectures, introducing inefficiencies and compatibility issues with components such as cross-attention and representation regularization. In this work, we propose **UDT**, a U-Net diffusion transformer that combines the representation power of DiTs with the encoding–decoding benefits of U-Nets, through data-adaptive token merging for downsampling and upsampling, while preserving the DiT token dimension. Our baseline UDT architecture outperforms existing U-Net DiTs and achieves performance comparable to REPA across all model sizes. Furthermore, using architectural optimization and REPA, UDT outperforms SiT's 7.9 FID at 1400 epochs (w/o CFG) within 40 epochs ($\approx 40\times$ faster convergence) for XL model size. Finally, it achieves strong image generation results on ImageNet with 1.44 FID at $256 \times 256$ (with CFG) after only 200 epochs, providing a new backbone for DiTs with strong empirical benefits.
Show more
View full details
Poster

Tune-Up Open-Weight CLIP: Optimization Framework for Self-Supervised Fine-tuning of CLIP

Anant Mehta ⋅ Xiyuan Wei ⋅ Xingyu Chen ⋅ Tianbao Yang
Dec 10, 2:00 AM - 5:00 AM Hall C1 #A115
CLIP has become a cornerstone of multimodal representation learning, yet improving its performance typically requires a prohibitively costly process of training from scratch on billions of samples. We ask a different question: *Can we improve the performance of open-weight CLIP models across various downstream tasks using only existing self-supervised datasets?* Unlike supervised fine-tuning, which adapts a pretrained model to a single downstream task, our setting seeks to improve general performance across various tasks. However, as both our experiments and prior studies reveal, simply applying standard training protocols starting from an open-weight CLIP model often fails, leading to performance degradation. In this paper, we introduce **TuneCLIP**, a self-supervised fine-tuning framework that overcomes the performance degradation. TuneCLIP has two key components: (1) a warm-up stage of recovering optimization statistics to reduce cold-start bias, inspired by theoretical analysis, and (2) a fine-tuning stage of optimizing a new contrastive loss to mitigate the penalization on false negative pairs. Our extensive experiments show that TuneCLIP consistently improves performance across model architectures and scales. Notably, it elevates leading open-weight models like SigLIP (ViT-B/16), achieving gains of up to +2.5% on ImageNet and related out-of-distribution benchmarks, and +1.2% on the highly competitive DataComp benchmark, setting a new strong baseline for efficient post-pretraining adaptation.
Show more
View full details
Poster

Beyond Linear Activation Steering: Invertible Latent Transformations for Controlling LLM Behavior

Tuc Nguyen ⋅ Thai Le
Dec 10, 2:00 AM - 5:00 AM Hall C1 #A111
Activation steering provides a lightweight inference-time mechanism for controlling large language models (LLMs) by modifying their internal activation vectors toward desired behaviors. Most existing methods compute a fixed steering direction in the original activation space, typically from pairs of contrastive examples using mean differences, linear probes, or arbitrary separability criteria. While effective to a certain extent, these methods treat behavioral control as a global, linear, additive offset: the same direction is applied across inputs, and behaviors are linearly separable. This can be restrictive when behavioral features vary nonlinearly across the activation space or lie on curved and anisotropic manifolds, where the optimal intervention may be input-dependent. To address this limitation, we propose INNSteer, a nonlinear activation steering framework based on invertible latent transformations. Rather than searching for a better steering vector in the original representation space, INNSteer learns a lightweight invertible neural network $\phi$ that maps an LLM's activations into a latent space where behavioral classes are more amenable to linear control. At inference time, activations are mapped through $\phi$, steered in the latent space, and mapped back through the exact inverse transformation $\phi^{-1}$. This makes a simple latent-space translation become a nonlinear, input-dependent intervention in the original activation space. Across experiment settings on multiple LLM families, scales, behavioral traits, and safety benchmarks, INNSteer consistently improves model control over linear, transport-based, and nonlinear steering baselines while largely preserving generation fluency.
Show more
View full details
Poster

Sharpness of Minima in Deep Matrix Factorization

Anıl Kamber ⋅ Rahul Parhi
Dec 10, 8:30 AM - 11:30 AM Hall C1 #A310
Understanding the loss-landscape geometry near a minimum is key to explaining the implicit bias of gradient-based methods in non-convex optimization problems such as deep neural network training and deep matrix factorization. A central quantity to characterize this geometry is the maximum eigenvalue of the Hessian of the loss. Currently, its precise role has been obfuscated because no exact expressions for this sharpness measure were known in general settings. In this paper, we present the first exact expression for the maximum eigenvalue of the Hessian of the squared-error loss at *any* minimizer in deep matrix factorization/deep linear neural network training problems, resolving an open question posed by Mulayoff & Michaeli [2020]. This expression reveals a fundamental property of the loss landscape in deep matrix factorization: *Having a constant product of the spectral norms of the left and right intermediate factors across layers is a sufficient condition for flatness*. Most notably, in both depth-$2$ matrix and deep overparameterized scalar factorization, we show that this condition is both necessary and sufficient for flatness, which implies that *flat minima are spectral-norm balanced and not necessarily Frobenius-norm balanced*. To complement our theory, we provide an empirical verification of an escape phenomenon during gradient-based training near a minimizer of a deep matrix factorization problem which relies on our exact expression.
Show more
View full details
Poster

Testable Learning of General Halfspaces under Massart Noise

Ilias Diakonikolas ⋅ Giannis Iakovidis ⋅ Daniel Kane ⋅ Sihan Liu
Dec 10, 8:30 AM - 11:30 AM Hall C1 #A424
We study the algorithmic task of testably learning general Massart halfspaces under the Gaussian distribution. In the testable learning setting, the aim is the design of a tester-learner pair satisfying the following properties: (1) if the tester accepts, the learner outputs a hypothesis and a certificate that it achieves near-optimal error, and (2) it is highly unlikely that the tester rejects if the data satisfies the underlying assumptions. Our main result is the first testable learning algorithm for general halfspaces with Massart noise and Gaussian marginals. The complexity of our algorithm is $d^{\mathrm{polylog}(\min\{1/\gamma, 1/\epsilon \})}$, where $\epsilon$ is the excess error and $\gamma$ is the bias of the target halfspace, which qualitatively matches the known quasi-polynomial Statistical Query lower bound for the non-testable setting. The analysis of our algorithm hinges on a novel sandwiching polynomial approximation to the sign function with multiplicative error that may be of broader interest.
Show more
View full details
Poster

OmniGF: A Dual-Branch Vision-Language Framework for Unified Gaze Following

Qiaomu Miao ⋅ Haoyu Wu ⋅ Jingyi Xu ⋅ Minh Hoai ⋅ Dimitris Samaras
Dec 10, 8:30 AM - 11:30 AM Hall C1 #A628
Understanding human gaze behavior is essential for complex scene comprehension and human-computer interaction. Traditional gaze following models are typically restricted to pure spatial localization, lacking the high-level capacity to reason about semantic targets or complex social contexts. Furthermore, these models often process individuals sequentially, requiring redundant computations over the same scene image for multi-person inference. While recent Vision-Language Models (VLMs) offer the exceptional semantic reasoning needed to address gaze-related semantic tasks, their reliance on discrete text generation inherently limits precision in continuous spatial tasks like gaze localization. To bridge this gap, we propose OmniGF, a unified vision-language framework that adapts foundational VLMs for highly scalable multi-person gaze reasoning. The model adopts a dual-branch decoding strategy: a structured language branch generates discrete reasoning states, while a continuous spatial branch directly taps into the VLM's dense hidden states. Supervising these extracted representations with high-resolution gaze target heatmaps effectively overcomes the spatial bottleneck of text-only coordinate generation. Furthermore, to explicitly ground the model in multi-person scenes, we augment the input with head embeddings encoded from cropped head images, providing fine-grained appearance and orientation cues for all individuals simultaneously. By modeling all individuals and leveraging the strong semantic capability of VLMs, OmniGF seamlessly integrates precise spatial gaze target estimation, semantic gaze prediction, and complex social gaze reasoning. Extensive experiments demonstrate that our framework establishes new state-of-the-art performance across multiple standard benchmarks.
Show more
View full details
Poster

Two Speeds of Learning: A Representation-Readout Decomposition of Grokking and Double Descent

Chi-Ning Chou ⋅ Oscar Uzdelewicz ⋅ Neng-Chun Chiu ⋅ Yao-Yuan Yang ⋅ SueYeon Chung
Dec 10, 8:30 AM - 11:30 AM Hall C1 #A913
Training loss and accuracy are the standard signals used to monitor generalization during deep neural network training. Two well-documented phenomena complicate this picture: in grokking, train loss falls rapidly while test performance improves abruptly only after a long delay; in epoch-wise double descent, train loss decreases monotonically while test loss or error rises and falls. Existing accounts are often task-specific, and a task-agnostic analysis framework for diagnosing and explaining these phenomena across realistic tasks and architectures is missing. We address this challenge by analyzing two competing processes that underlie learning dynamics: representation learning in the encoder and readout calibration in the final classifier. Using tools from representational geometry, neural tangent kernels, and linear probing, we show that both processes are active throughout training, with the fluctuations of their relative speed giving rise to seemingly anomalous generalization dynamics. Applying the representation-readout decomposition to grokking across a wide range of tasks and architectures, we find that the readout is train-biased before grokking onset, and representation learning is gradual but not absent—contrary to the lazy-to-rich account. The framework further provides diagnostic signatures distinguishing spurious from genuine generalization: in a previously reported MNIST grokking example and an epoch-wise double descent example, apparent delayed or non-monotone generalization is shown to arise from representation degradation and readout misalignment induced by non-standard training recipes. Together, these results establish the representation-readout decomposition as a top-down framework for understanding learning dynamics and revealing underlying algorithms for interpretability research.
Show more
View full details
Poster

G-Zero: Self-Play for Open-Ended Generation from Zero Data

Chengsong Huang ⋅ Haolin Liu ⋅ Tong Zheng ⋅ Runpeng(Leo) Dai ⋅ Langlin Huang ⋅ JINYUAN LI ⋅ Zongxia Li ⋅ Zhepei Wei ⋅ Yu Meng ⋅ Jiaxin Huang
Dec 10, 8:30 AM - 11:30 AM Hall C1 #A810
Self-evolving LLMs excel in verifiable domains but struggle in open-ended tasks, where reliance on proxy LLM judges introduces capability bottlenecks and reward hacking. To overcome this, we introduce G-Zero, a verifier-free, co-evolutionary framework for autonomous self-improvement. Our core innovation is \textbf{Hint-$\delta$}, an intrinsic reward that quantifies the predictive shift between a Generator model's unassisted response and its response conditioned on a self-generated hint. Using this signal, a Proposer model is trained via GRPO to continuously target the Generator's blind spots by synthesizing challenging queries and informative hints. The Generator is concurrently optimized via DPO to internalize these hint-guided improvements. Theoretically, we prove a best-iterate suboptimality guarantee for an idealized standard-DPO version of G-Zero, provided that the Proposer induces sufficient exploration coverage and the data filteration keeps pseudo-label score noise low.. By deriving supervision entirely from internal distributional dynamics, G-Zero bypasses the capability ceilings of external judges, providing a scalable, robust pathway for continuous LLM self-evolution across unverifiable domains.
Show more
View full details
Poster

Agent-ToM: Learning to Monitor Autonomous LLM Agents via Theory-of-Mind Reasoning

Nesreen Ahmed ⋅ Nima Nafisi
Dec 10, 8:30 AM - 11:30 AM Hall C1 #A1005
Monitoring autonomous large language model (LLM) agents for covert malicious behavior (e.g., covertly pursuing a hidden malicious objective) is challenging due to delayed, context-dependent, and long-horizon attack patterns. In adversarial settings such as sabotage, agents may pursue hidden objectives while maintaining superficially benign behavior, making detection difficult even with full trajectory access. Prior monitoring approaches primarily improve monitor scaffolding or ensemble aggregation, but treat each trajectory independently and do not improve from prior monitoring experience. Moreover, standard reasoning methods explain observed behavior but do not explicitly reason about agent beliefs, intentions, and goal alignment required to distinguish benign task execution from covert deviation. We propose Agent-ToM, a learning-to-monitor framework grounded in Theory-of-Mind (ToM) reasoning for security analysis of autonomous agents. Agent-ToM performs structured full-trajectory analysis by inferring beliefs, step-level intent hypotheses with calibrated confidence, expected actions, and deviations from task-consistent behavioral baselines. At inference time, it employs a Reason--Verify--Refine pipeline to construct and validate monitoring decisions. At training time, Agent-ToM learns from prior monitoring episodes by distilling critique signals into a persistent semantic guardrail memory that accumulates monitoring strategies, enabling reusable belief- and intent-conditioned constraints to be applied across episodes. We evaluate Agent-ToM on adversarial agent monitoring benchmarks (SHADE-Arena and CUA-SHADE-Arena). Agent-ToM achieves strong precision--recall balance and outperforms state-of-the-art monitoring baselines, including ensemble methods, while using a single coherent reasoning pipeline. These results demonstrate that \emph{learning at the monitoring layer}, combined with structured ToM reasoning and verification, provides an effective and deployable foundation for securing autonomous LLM agents.
Show more
View full details
Poster

StomataBench: Measuring Taxonomic Generalization in Stomatal Detection

Sainath Reddy Gummi ⋅ Hankui K Zhang ⋅ Chulwoo Pack ⋅ Shyam Solanki ⋅ Young Chang
Dec 10, 8:30 AM - 11:30 AM Hall C1 #A802
Accelerating stomata measurement is essential for developing drought-resilient plants. However, most automated stomata detectors are tested under narrow imaging and species conditions. Their behavior under broader ecological distribution shift remains unclear. We introduce StomataBench, a benchmark for stomatal object detection across species, acquisition protocols, and biological density regimes. The benchmark uses a curated multispecies training set of 3,154 images with 134,802 annotated stomata from 21 woody species. It is evaluated on four test datasets totaling 19,657 images, covering diverse woody taxa and heterogeneous public crop sources. Unlike standard detection benchmarks that report only AP, StomataBench evaluates measurement reliability. We measure COCO AP, F1, score-threshold sensitivity, image-level count error, and stomatal density agreement. We benchmark sixteen detectors spanning two-stage, one-stage, transformer, open-vocabulary, and promptable foundation models. The results show that model rankings change with the biological objective. GDINO-SB provides the strongest average AP generalization, while SAM3-OD gives reliable operating point for count and density estimation. Conventional detectors remain competitive on near-domain woody plants, but foundation models are robust under harder ecological shifts. Failure analysis shows that far-OOD detection is often limited by missing stomata. These results identify cross-lineage proposal generation as a key unsolved problem for reliable stomatal phenotyping under ecological distribution shift.
Show more
View full details
Poster

The Score Kalman Filter

Kaito Iwasaki ⋅ Anthony Bloch ⋅ Taeyoung Lee ⋅ Maani Ghaffari
Dec 10, 8:30 AM - 11:30 AM Hall C1 #A207
A central obstacle in nonlinear Bayesian filtering is representing the belief distribution. Moment-based filters address this by propagating polynomial moments and reconstructing a density from them. Recent work completes the predict-update loop via the maximum-entropy (MaxEnt) principle, but each step requires the partition function and its gradient, both $n$-dimensional integrals whose cost scales exponentially, restricting the demonstrated MaxEnt moment filtering to $n \le 4$. We avoid the partition function entirely by combining score matching with Stein's identity. In our setting, score matching reduces the density fit to a single linear solve whose coefficients are assembled directly from the propagated moments. The same parameters then drive Stein's identity to close the moment hierarchy during prediction and to recover posterior moments after each Bayesian update, keeping the full predict-update loop free of partition function evaluation. The resulting $\textbf{Score Kalman Filter}$ (SKF) reduces to the classical information-form Kalman filter as a special case and performs every step through linear algebra. On nonlinear coupled-oscillator networks, the SKF runs through $n=20$ and reports lower RMSE than the EKF, UKF, EnKF, and particle-filter baselines on the tested synthetic benchmarks.
Show more
View full details
Poster

GeoWind2Plan: Mission-Time 3D Urban Wind Prediction for Energy-Efficient UAV Planning

Shaoxiang Qin ⋅ Xiongye Xiao ⋅ Yucheng Zhao ⋅ Fuyuan Lyu ⋅ Di Zhou ⋅ Jiachen Yao ⋅ Steve Liu ⋅ Animashree Anandkumar ⋅ Liangzhu Leon Wang
Dec 10, 8:30 AM - 11:30 AM Hall C1 #A827
In urban low-altitude flight, buildings reshape ambient wind into spatially varying 3D flow, making unmanned aerial vehicle (UAV) energy depend on local wind exposure as well as path length. However, building-resolved wind information is rarely available when a mission must be planned. Computational fluid dynamics (CFD) can produce high-fidelity urban flow fields, but each simulation is tied to a fixed inflow boundary condition and can take hours to days, which is incompatible with urban UAV missions that typically last minutes to tens of minutes. We present GeoWind2Plan, a geometry-to-wind-to-planning framework for mission-time 3D urban wind prediction and energy-efficient UAV planning. Given only a background wind vector, 3D building geometry, and a start-goal pair, GeoWind2Plan transforms the building geometry into a reference-wind frame, predicts mission-relevant 3D wind patches with a localized geometry-conditioned neural operator, stitches them into a queryable local wind field, and optimizes a feasible 3D path and speed profile using a physically grounded UAV energy model. Rather than pursuing CFD-perfect reconstruction, GeoWind2Plan targets decision-useful wind prediction: trajectories are planned with predicted wind and evaluated under high-fidelity CFD wind. Across held-out urban domains, wind speeds, and mission wind-angle regimes, GeoWind2Plan performs corridor-localized wind inference in about 3 seconds, compared with roughly 8 hours for CFD. Under CFD evaluation, trajectories planned with GeoWind2Plan reduce energy by 6.9%, 12.7%, and 4.5% in tailwind, headwind, and crosswind missions relative to wind-agnostic planning, recovering 87.9%, 85.7%, and 75.0% of CFD-reference savings. These results show that fast, corridor-localized 3D urban wind prediction can make wind-aware UAV energy planning practical at mission time.
Show more
View full details
Poster

Online Allocation with Differential Privacy

Jianyi Yang ⋅ Xingyu Zhou ⋅ Mostafa Mushsharat ⋅ Shaolei Ren
Dec 10, 8:30 AM - 11:30 AM Hall C1 #A300
We study private online allocation problems, where allocation decisions must satisfy differential privacy (DP) to protect sensitive user information while optimizing performance under constrained resources. We first formalize differential privacy notions suited to different privacy requirements in online allocation and establish the fundamental performance limits of any algorithm under these definitions. Based on these insights, we propose PPOA, a privacy-preserving meta algorithm for online allocation, and establish sufficient conditions under which PPOA preserves Joint DP (JDP) or Local DP (LDP) while achieving asymptotically near-optimal performance. Building on these conditions, PPOA can be instantiated into a variety of concrete algorithms. In particular, we present the specific designs, which include PPOA-DMD that preserves JDP and LDP and PPOA-FTRL that preserves JDP. We analyze their performance under both adversarial and stochastic settings and characterize the fundamental trade-offs between DP and allocation performance. Finally, we demonstrate the superior performance of the proposed algorithms via numerical experiments on AI model routing in battery-powered edge systems.
Show more
View full details
Poster

The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment

Rishab Balasubramanian ⋅ Pin-Jie Lin ⋅ Rituraj Sharma ⋅ Mohit Bansal ⋅ Tu Vu
Dec 10, 8:30 AM - 11:30 AM Hall C1 #A110
We investigate whether post-trained capabilities can be transferred across model scales without retraining, and propose the Master Key Hypothesis, which states that model capabilities correspond to directions in a low-dimensional latent subspace that induce specific behaviors and are transferable across models through linear alignment. Based on the hypothesis, we introduce UNLOCK, a training-free and label-free framework that extracts a capability direction by contrasting activations between capability-present and capability-absent Source variants, aligns it with a Target model through a low-rank linear transformation, and applies it at inference time to elicit the behavior. Experiments on reasoning behaviors, including Chain-of-Thought (CoT) and mathematical reasoning, demonstrate substantial improvements across model scales without training. For example, transferring CoT reasoning from Qwen1.5-14B to Qwen1.5-7B yields an accuracy gain of 12.1% on MATH, and transferring a mathematical reasoning direction from Qwen3-4B-Base to Qwen3-14B-Base improves AGIEval Math accuracy from 61.1% to 71.3%, surpassing the 67.8% achieved by the 14B post-trained model. Our analysis shows that the success of transfer depends on the capabilities learned during pre-training, and that our intervention amplifies latent capabilities by sharpening the output distribution toward successful reasoning trajectories.
Show more
View full details
Poster

Stop Using Plausibility as the Criterion for Explainable AI

Weina Jin ⋅ Xiaoxiao Li ⋅ Ghassan Hamarneh
Dec 10, 8:30 AM - 11:30 AM Hall C1 #A908
Explainable artificial intelligence (XAI) is motivated by the problem of making AI predictions understandable, transparent, and responsible, as AI becomes increasingly impactful in society and high-stakes domains. The evaluation and optimization criteria of XAI are gatekeepers for XAI algorithms to achieve their expected goals and should withstand rigorous inspection. To improve the scientific rigor of XAI, we conduct the first comprehensive and critical examination of a common XAI criterion: plausibility. Plausibility assesses how convincing the AI explanation is to humans, and is usually quantified by metrics of feature localization or feature correlation. Our examination shows that plausibility is invalid to measure explainability, and human explanations are not the ground truth for XAI, because doing so ignores the necessary assumptions underpinning an explanation. One fundamental assumption is that AI explanation is supposed to behave adversarially, analogous to auditors' or doctors' roles of identifying potential problems. Evaluating or optimizing XAI to generate more plausible explanations is analogous to incentivizing (i.e., bribing) auditors/doctors to generate more positive reports, which is different from encouraging AI models to learn more plausible features (analogous to encouraging companies/patients to improve their conduct/health). Our examination further reveals the consequences of using plausibility as the XAI criterion, including increasing misleading explanations that manipulate users, deteriorating users' trust in the AI system, undermining human autonomy, being unable to achieve complementary human-AI task performance, and abandoning other possible approaches of enhancing understandability. Due to the invalidity of measurements and the unethical issues, this position paper argues that the AI community should stop using plausibility as the criterion to evaluate and optimize XAI algorithms. We also delineate new research approaches to improve XAI in trustworthiness, understandability, and utility to users including complementary human-AI task performance.
Show more
View full details
Poster

A Bitter Lesson for Data Filtering

Christopher Mohri ⋅ John Duchi ⋅ Tatsunori Hashimoto
Dec 10, 8:30 AM - 11:30 AM Hall C1 #A122
We investigate data filtering for large model pretraining via new scaling studies that target the high compute, data-scarce regime. In spite of an apparently common belief that filtering data to include only high-quality information is essential, our experiments suggest that with enough compute, the best data filter is no data filter. We find that sufficiently trained large parameter models not only tolerate low-quality and distractor data, but in fact, including nominally 'poor' data improves model performance.
Show more
View full details
Poster

Position: Reconciling Open Access with Owner Control in AI Model Distribution Deserves More Research Effort

Zerui Cheng ⋅ Edoardo Contente ⋅ Benjamin Finch ⋅ Oleg Golev ⋅ Jonathan Hayase ⋅ Andrew Miller ⋅ Niusha Moshrefi ⋅ Anshul Nasery ⋅ Sewoong Oh ⋅ Himanshu Tyagi ⋅ Pramod Viswanath
Dec 10, 8:30 AM - 11:30 AM Hall C1 #A907
The rapid rise of AI has seen the coexistence of open-weight models and closed-source, API-based deployment, each with its own strengths and limitations. A growing share of deployment scenarios needs both local, customizable execution and owner-side accountability, yet neither extreme serves them well. Such scenarios include on-prem enterprise use with sensitive data, edge and offline robotics, and local fine-tuning or retrieval-augmented generation. This position paper argues that the middle regime between closed APIs and open-weight release deserves a principled deployment-level primitive of its own, and proposes OML—Open, Monetizable, Loyal—as a starting point for that primitive. An OML-formatted artifact aims to be simultaneously Open (open-weight and locally executable), Monetizable (usage is accountable to the owner), and Loyal (owner-declared use constraints are enforceable). Throughout, "open" refers to open-weight, locally executable artifacts rather than to fully open-source release, and "loyal" refers to owner-declared use constraints rather than to remote control over a running model. We articulate the desirable properties and threat model for OML, survey theoretical and practical constructions across software, hardware, and cryptographic primitives, and outline an end-to-end deployment protocol together with market-based and policy alternatives. We then describe OML 1.0, a low-overhead instantiation based on AI-native fingerprinting, and characterize the regime in which it provides meaningful guarantees. We close with a research agenda calling on the ML, cryptography, systems, and mechanism-design communities to refine the primitives needed to make OML deployable at scale.
Show more
View full details
Poster

Community-Centered AI is Feasible and Beneficial for Impacted Communities

Tzu-Sheng Kuo ⋅ Quan Ze Chen ⋅ Amy Zhang ⋅ Kenneth Holstein ⋅ Haiyi Zhu
Dec 10, 8:30 AM - 11:30 AM Hall C1 #A904
AI systems are increasingly used in community contexts, yet they often fail to align with the communities they impact. To address this misalignment, we advocate for community-centered AI---an AI development paradigm that shifts away from pursuing general-purpose AI and instead focuses on co-developing tailored AI systems with the specific communities they impact. This position paper argues that community-centered AI is both feasible and beneficial for impacted communities. To support this argument, we first outline the potential benefits of community-centered AI, including greater alignment, enhanced legitimacy, capacity building, and normative justification. Next, we highlight emerging efforts in community-centered AI across the AI development process, demonstrating its feasibility in delivering these benefits. Finally, we propose a framework to guide future work in this area, characterizing community-centered AI efforts along three dimensions: participation mode, decision-making process, and development layer. Overall, this paper calls for increased research on community-centered AI.
Show more
View full details
Poster

Sort, Partition, Randomize: Optimal Binary Hypothesis Testing under Local Differential Privacy

Elena Ghazi ⋅ Jawad Nasser ⋅ Flavio Calmon ⋅ Ibrahim Issa
Dec 10, 8:30 AM - 11:30 AM Hall C1 #A902
We study optimal design of $\varepsilon$-locally differentially private mechanisms for binary hypothesis testing. Each observation is drawn from one of two known distributions $P_0,P_1$ on a finite alphabet of size $k$, privatized by a mechanism $Q$, and then used to infer which distribution generated the data. We measure testing utility using an $f$-divergence—including total variation, KL, and hockey-stick divergences—between the two induced output distributions. Previous work established structural properties of optimal mechanisms, but only yielded exponential-time algorithms. We prove a sharp structure: for every $\varepsilon$ and every $f$-divergence objective, after sorting the alphabet by likelihood ratio, there exists an optimal mechanism that partitions the sorted alphabet into contiguous blocks and applies randomized response to the block label. We call this class Sort–Partition–Randomize (SPR). This characterization yields an exact dynamic program that computes an optimal mechanism in $O(k^3)$ time, and more generally in $O(\ell k^2)$ time with an $\ell$-output budget. Our results make it possible to efficiently compute and characterize the exact optimum across the full privacy range, beyond asymptotic privacy regimes.
Show more
View full details
Poster

UniReFP: Robust Unified Fingerprinting for Vision Models against Cross-Task Repurposing Attacks

Ziye Geng ⋅ Guang Yang ⋅ Yihang Chen ⋅ Lingfeng Yao ⋅ Xing Shi ⋅ Miao Pan ⋅ Xin Fu ⋅ Changqing Luo
Dec 10, 8:30 AM - 11:30 AM Hall C1 #A1008
We identify, for the first time, a new model modification attack—the cross-task model repurposing attack—that can render fingerprints generated by existing model fingerprinting approaches inapplicable. To address this challenge, we propose UniReFP—a novel unified model fingerprinting framework applicable to diverse vision models across different tasks—that utilizes ownership evidence in a shared class-level semantic space rather than original task-specific output space, enabling effective ownership verification when a protected model is repurposed across tasks with heterogeneous output formats. Specifically, UniReFP constructs a surrogate classifier by repurposing the protected model, enabling fingerprints to be generated independently of the original task-dependent output space of the protected model. Moreover, it optimizes grouped fingerprints to encode ownership evidence: fingerprints within the same group are encouraged to induce consistent semantic responses and intermediate representations on the surrogate classifier, while producing dispersed responses on independently trained reference classifiers. During verification, UniReFP uses a task-aware semantic projection mechanism to map heterogeneous suspect-model outputs into unified semantic-presence vectors, and determines ownership by measuring inner-group consistency. Extensive experimental results validate the effectiveness of UniReFP, consistently showing superior performance under cross-task repurposing attacks, commonly studied model modification attacks, and even their combinations.
Show more
View full details
Poster

DeltaPrompts: Escaping the Zero-Delta Trap in Multimodal Distillation

Jaehun Jung ⋅ Hyunwoo Kim ⋅ Brandon Cui ⋅ Ximing Lu ⋅ David Acuna ⋅ Prithviraj Ammanabrolu ⋅ Yejin Choi
Dec 11, 2:00 AM - 5:00 AM Hall C1 #A1124
Distillation enables compact Vision-Language Models (VLMs) to obtain strong reasoning capabilities, yet the prompts driving this process are typically chosen via simple heuristics or aggregated from off-the-shelf datasets. We reveal a critical inefficiency in this approach: up to 69\% of the prompts in standard chart / document reasoning datasets are effectively $\textit{zero-delta}$, meaning the teacher and student already induce the exact same answer distribution. Training on these prompts provides minimal learning signal, causing student improvement to rapidly saturate regardless of data scale. To escape the zero-delta trap, we return to first principles: distillation fundamentally minimizes distributional divergence, and thus a prompt is valuable only if it exposes a functional capability gap between the teacher and student. We quantify this gap through $\textit{answer divergence}$ ($\Delta$), demonstrating that non-zero divergence is critical for effective scaling. Building on this insight, we propose a staged synthesis pipeline that repurposes existing datasets as seeds, actively targeting student failure modes to produce better prompts. The result is $\textbf{DeltaPrompts}$, a diverse dataset of 200k synthetic, high-divergence reasoning problems. We evaluate $\text{DeltaPrompts}$ across three distinct settings: on-policy distillation with the target teacher-student pair, transfer to a novel model family without regenerating the data, and off-policy fine-tuning of a non-reasoning model. Across all scenarios, $\text{DeltaPrompts}$ drives substantial gains, yielding up to 15\% relative improvement even on top of a highly-optimized reasoning model ($\textit{e.g.,}$ Qwen3-VL-8B-Thinking)---averaged over 10 benchmarks spanning chart, document and perception-centric reasoning.
Show more
View full details
Poster

Dynamic Tokenization via Reinforcement Patching: End-to-end Training and Zero-shot Transfer

Yulun Wu ⋅ Sravan Kumar Ankireddy ⋅ Samuel Sharpe ⋅ Nikita Seleznev ⋅ Dehao Yuan ⋅ Hyeji Kim ⋅ Nam Nguyen
Dec 11, 2:00 AM - 5:00 AM Hall C1 #A105
Efficiently aggregating spatial or temporal horizons to acquire compact representations has become a unifying principle in modern deep learning models, yet learning data-adaptive representations for long-horizon sequence data, especially continuous sequences like time series, remains an open challenge. While fixed-size patching has improved scalability and performance, discovering variable-sized, data-driven patches end-to-end often forces models to rely on soft discretization, specific backbones, or heuristic rules. In this work, we propose Reinforcement Patching (ReinPatch), a novel framework that jointly optimizes a sequence patching policy and its downstream sequence backbone model with reinforcement learning. By formulating patch boundary placement as a discrete decision process optimized via Group Relative Policy Gradient (GRPG), ReinPatch bypasses the need for continuous relaxations and performs dynamic patching policy optimization in a natural manner. Moreover, our method allows strict enforcement of a desired compression rate, freeing the downstream backbone to scale efficiently, and natively supports multi-level hierarchical modeling. We evaluate ReinPatch on time-series forecasting datasets, where it demonstrates compelling performance compared to state-of-the-art data-driven patching strategies. Furthermore, our detached design allows the patching module to be extracted as a standalone foundation patcher, providing the community with visual and empirical insights into the segmentation behaviors preferred by a purely performance-driven neural patching strategy.
Show more
View full details
Poster

Neural Dual Bounds: Valid-by-Construction JGLP Warm-Starts for MAP and Constrained MAP

Akshay Vyas ⋅ Shivvrat Arya ⋅ Brij Malhotra ⋅ Tahrima Rahman ⋅ Vibhav Gogate ⋅ Nicholas Ruozzi
Dec 11, 2:00 AM - 5:00 AM Hall C1 #A209
We present Neural Dual Bounds, a calibration-free framework that produces deterministic upper bounds for MAP inference in probabilistic graphical models using a single neural-network forward pass. The framework trains a network to output the edge messages of a mini-bucket style upper bound on a given join-graph decomposition in a self-supervised manner by directly minimizing the a smooth dual objective. The output of this network can be used at test time to warm-start a standard JGLP optimizer. Across diverse benchmarks, this warm start yields dual gaps that are orders of magnitude tighter than those from zero initialization, with the largest gains in the early-iteration regime. We also apply our framework for the constrained MAP (CMPE) task, and we show that neural warm starts with test-time adaptation consistently achieve the tightest dual gaps across all iteration budgets against an adaptive baseline.
Show more
View full details
Poster

Towards a Universal Causal Reasoner

Qirun Dai ⋅ Xiao Liu ⋅ Jiawei Zhang ⋅ Dylan Zhang ⋅ Hao Peng ⋅ Chenhao Tan
Dec 11, 2:00 AM - 5:00 AM Hall C1 #A118
Despite the importance of causal reasoning, training LLMs to perform causal reasoning remains underexplored. Existing data efforts mostly focus on benchmarking LLMs on specific aspects of causality, rendering them less suitable for training generalizable causal reasoners. To address this, we propose UniCo, a data generation framework that both (1) addresses 18 causal query types across Pearl's Causal Ladder and (2) translates symbolic samples into code and narrative domains to simulate real-world use cases where causal terms are not explicitly specified. To ensure data quality, UniCo grounds answers with exact causal inference and filter cases with reasoning shortcuts. Upon supervised-finetuning with 66.6K UniCo-generated instances, Qwen3-4B, Qwen3-8B and Olmo-3-7B-Instruct achieve an average of 22.9% improvements across all 18 in-distribution query types, and 8.1% over state-of-the-art causal data generation frameworks on 7 established causal benchmarks outside the training distribution. Furthermore, in real-world medical understanding, legal decision, and tabular reasoning, UniCo-trained models consistently display more faithful reasoning traces, outperforming the base models by an average of 20.2% in faithfulness metrics. These suggest that causality-centered training not only strengthens causal reasoning, but also equips LLMs with a causal mindset in general reasoning tasks.
Show more
View full details
Poster

(Strongly) Replicable Distribution Testers imply High Probability Distribution Testers

Ilias Diakonikolas ⋅ Jingyi Gao ⋅ Daniel Kane ⋅ Sihan Liu ⋅ Christopher Ye
Dec 11, 2:00 AM - 5:00 AM Hall C1 #A527
We study connections between the sample cost of replicability, which requires an algorithm to produce consistent outputs in different runs, and the sample complexity in the high success probability regime for distribution testing algorithms. Specifically, we consider a stronger notion of replicability, which we term as strong replicability, and show that any $\rho$-strongly-replicable testing algorithm can be converted in a blackbox manner to a tester with at most $\exp(-\tilde{\Omega}(\rho^{-2}))$ failure probability under the same sample budget. Our conversion is optimal for many natural testers. As applications of our conversion theorem, we obtain tight sample lower bounds for strongly replicable testers for coin bias and closeness testing.
Show more
View full details
Poster

World Tracing: Pixel-Aligned Geometry Beyond the Visible

Hao Zhang ⋅ Mohamed El Banani ⋅ Jen-Hao Cheng ⋅ Paul Zhang ⋅ Yi Hua ⋅ Ben Mildenhall ⋅ Christoph Lassner ⋅ Narendra Ahuja ⋅ Gengshan Yang
Dec 11, 2:00 AM - 5:00 AM Hall C1 #A629
Single-image 3D methods often trade off pixel alignment and completeness: monocular reconstructors stay registered to visible pixels but stop at the first surface, while image-to-3D generators complete shapes in a canonical frame that is no longer aligned to the input. We introduce methodlong (method), a pixel-aligned multilayer geometry representation that keeps generated 3D in the input camera frame while completing geometry beyond the visible surface. For each input ray, method predicts an ordered stack of camera-space 3D points, where the first entry explains the observed surface and subsequent entries complete occluded surfaces along the same pixel ray. methodnet, a flow-matching diffusion transformer with a frozen 2D foundation encoder, learns this representation from depth-filled dense targets, removing the need for a separate per-layer visibility-mask head. The same objective covers static objects, static scenes, and dynamic clips, with temporal attention added for video. Because the output preserves the input camera frame, intrinsics, and pixel correspondences, it provides a direct 2D-to-3D interface for downstream systems, including text-driven 3D scene editing, geometry-conditioned novel-camera video generation, and training-free integration with existing textured-mesh generators. Across object, scene, and dynamic benchmarks, method improves visible-surface accuracy and complete-geometry quality over strong reconstruction and generation baselines.
Show more
View full details
Poster

Budgeting Discretion: Theory and Evidence on Street-Level Decision-Making

Gaurab Pokharel ⋅ Sanmay Das ⋅ Patrick J Fowler
Dec 11, 2:00 AM - 5:00 AM Hall C1 #A1006
Street-level bureaucrats, such as caseworkers, triage nurses, and school administration, operate under a fundamental tension. The official policy on who to prioritize for services may conflict with bureaucrats estimation of who would benefit most from those services. The social theory of street-level bureaucracy argues that frontline agents use discretionary authority to bridge this gap, overriding policy recommendations when professional judgment identifies cases where doing so would meaningfully improve outcomes. As algorithmic recommendations become embedded in allocation settings, understanding the structure of this discretionary behavior is fundamental to designing tools that account for, rather than suppress, this value of professional judgment. We formalize discretion as a finite-horizon dynamic allocation problem. An agent implements a default policy but holds a limited budget of K overrides across T periods. Each period, the agent observes whether deviating from the default would yield a welfare gain and must decide whether to spend a scarce override now or conserve it for future opportunities. We show that the optimal policy is a state-dependent threshold rule and prove a behavioral invariance: for location-scale families of improvement distributions, the rate at which an optimal agent exercises discretion is independent of the amount of welfare gains and depends only on the distribution's shape. Fat-tailed gains induce patience (conserving overrides for rare, high-stakes cases); thin-tailed gains induce routine, front-loaded spending. We also compare the conceptual implications of our model with operational data from a homelessness service system. Override rates shift with short-run capacity openings in scarce housing, rising when recent exits free slots, and falling when interventions are congested. This could be the result of a perceived increase in the discretionary budget. Further, the temporal pattern of spending is front-loaded: override rates peak on Mondays and early in the fiscal year, consistent with the routine, early-spending behavior our model predicts under thin-tailed improvement distributions. These findings identify a systematic structure in both human and theoretically optimal decision-making, with direct implications for the design of human-AI allocation systems that are both more efficient and equitable.
Show more
View full details
Poster

Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction

Zhuofeng Li ⋅ Haoxiang Zhang ⋅ Cong Wei ⋅ Pan Lu ⋅ Ping Nie ⋅ Yuyang Bai ⋅ Shangbin Feng ⋅ Hangxiao Zhu ⋅ Ming Zhong ⋅ Yuyu Zhang ⋅ Jianwen Xie ⋅ Yejin Choi ⋅ James Zou ⋅ Jiawei Han ⋅ Wenhu Chen ⋅ Jimmy Lin ⋅ Dongfu Jiang ⋅ Yu Zhang
Dec 11, 2:00 AM - 5:00 AM Hall C1 #A1025
Modern retrieval-augmented systems typically access a corpus through a fixed similarity interface (either sparse or dense) that returns only the top-$k$ most similar documents for a query. While efficient, this design becomes a bottleneck for agentic search: exact lexical matching, conjunctions of weak clues, local context verification, and multi-step hypothesis refinement are difficult to realize with a conventional off-the-shelf retriever, and evidence filtered out early cannot be recovered downstream. This problem becomes particularly acute when agents must iteratively discover intermediate entities, combine partial evidence, and revise their search strategy. To address this problem, we study direct corpus interaction (DCI), a simple alternative in which an agent searches the raw corpus directly using general-purpose terminal tools (e.g., grep, file reads, shell commands, and lightweight scripts), without relying on embedding models, vector indexes, or retrieval APIs. This approach requires no offline indexing and adapts naturally to evolving local corpora. Across benchmarks for information retrieval (i.e., BRIGHT and BEIR) and end-to-end agentic search (i.e., BrowseComp-Plus), this simple setup substantially outperforms strong sparse, dense, and reranking baselines. It also attains strong accuracy on multi-hop question answering without relying on any conventional semantic retriever. Our results suggest that as language agents grow more capable, retrieval quality depends not only on reasoning ability, but also on how richly the corpus interface supports interaction. DCI therefore points to a broader interface design space for agentic search. Our code is available at https://anonymous.4open.science/r/dci-agent/.
Show more
View full details
Poster

UltraDiff:Transferring High-Fidelity Priors to Compressed Latent Spaces for High-resolution Image Generation

Jingjing Ren ⋅ Haitian Zheng ⋅ Haoyu Chen ⋅ Connelly Barnes ⋅ Zhifei Zhang ⋅ Yuqian Zhou ⋅ Zhe Lin ⋅ Lei Zhu
Dec 11, 2:00 AM - 5:00 AM Hall C1 #A618
High-resolution synthesis with Latent Diffusion Models (LDMs) faces a fundamental trade-off between computational cost and generative fidelity. This trade-off is largely governed by the latent compression factor $f$ (e.g. f8: $f{=}8$ and f32: $f{=}32$). While aggressive compression (f32) significantly improves efficiency, it suffers from severe information loss and ambiguity compared to standard f8 models. We propose UltraDiff, a framework that reformulates this challenge as joint-latent diffusion learning followed by marginal score distillation. We introduce MixTeacher, a dual-branch DiT that models the joint f8-f32 distribution, utilizing shared attention to resolve the ambiguity of the compressed space with high-fidelity f8 priors. Crucially, we propose vector field distillation in the native f32 space. Theoretically, this compels the student to learn the conditional expectation of the teacher's trajectory, effectively filtering out compression artifacts. UltraDiff matches f8 quality across 1K-4K resolutions while preserving f32 efficiency. Notably, it generates 2K images in 6.2 seconds on a single A100 GPU—over $40\times$ faster than f8 baselines.
Show more
View full details
Poster

SceneBind: Binding What and Where Across Vision, Audio, and Language

Mingfei Chen ⋅ Zijun Cui ⋅ Ruoke Zhang ⋅ Hyeonggon Ryu ⋅ Eli Shlizerman
Dec 11, 2:00 AM - 5:00 AM Hall C1 #A726
We present SceneBind an omni-modal representation of realistic scenes with joint semantic and 3D spatial understanding across vision, audio, and language. Existing omni-modal encoders excel at instance-level semantics (i.e., what is present), but often lack explicit spatial structure (i.e., where it is). SceneBind addresses this gap by representing each scene as a semantic-spatial entity, combining a global semantic embedding with object-centric semantic-spatial slots. This representation explicitly captures object-level semantics, spatial attributes, and uncertainty. We further propose SceneBind Matching, a semantic–spatial matching scheme that integrates global scene similarity with object alignment, supporting cross-modal scene retrieval and object grounding. To train and evaluate SceneBind, we curate a novel real-world binaural audio-visual dataset with structured semantic and spatial annotations, and propose a training protocol for aligning semantic and spatial signals across modalities. SceneBind is compatible with large-scale pretrained semantic encoders, adds lightweight spatial modeling with only a few additional tokens. It achieves state-of-the-art scene and spatial retrieval while enabling strong zero-shot transfer to downstream tasks such as audio-visual localization.
Show more
View full details
Poster

Theoretical Limits of Language Model Alignment

Lucas Monteiro Paes ⋅ Natalie Mackraz ⋅ Barry-John Theobald ⋅ Federico Danieli
Dec 11, 8:30 AM - 11:30 AM Hall C1 #A1003
Language model (LM) alignment improves model outputs to reflect human preferences while preserving the capabilities of the base model. The most common alignment approaches are (i) reinforcement learning, which maximizes the expected reward under a KL-divergence constraint, and (ii) best-of-$N$ alignment, which selects the highest-reward output among $N$ independent samples. Despite their widespread use, the fundamental limits of reward improvement under a KL budget remain poorly understood. We characterize the information-theoretic limits of KL-regularized alignment by deriving the maximum achievable expected reward gain for a fixed KL-divergence budget. Our first result provides a closed-form expression for the optimal reward improvement, governed by a Jeffreys divergence term rather than the $\sqrt{\texttt{KL}}$ used in prior analyses. We further reformulate this expression as a covariance under the base model, yielding a practical estimator that predicts achievable alignment gains from base model samples alone. We extend our analysis to the proxy reward setting, showing that the gap between ideal and proxy alignment (reward hacking) grows with the KL penalty factor and magnitude of reward error. We then prove that reward ensembling mitigates reward hacking, providing a theoretical justification for this technique used in practice. Empirically, we compute the KL–reward Pareto frontier for two alignment tasks for LMs, safety and summarization, and show that best-of-$N$ closely approaches the theoretical limit, while PPO and GRPO remain substantially suboptimal. Our theoretical results shed light on several empirically observed phenomena in the alignment literature and suggest that algorithmic improvements are needed to achieve optimal alignment without high inference costs.
Show more
View full details
Poster

Do Thinking Tokens Help with Safety?

Narutatsu Ri ⋅ Abhishek Panigrahi ⋅ Sanjeev Arora
Dec 11, 8:30 AM - 11:30 AM Hall C1 #A1006
Today's reasoning models use thinking tokens to attain stronger performance on benchmarks than their instruction-tuned counterparts. It is also generally believed that this more "deliberative" mode should improve alignment and safety, by providing the model a safe space to consider whether its planned answer to the request violates its safety principles. We present evidence that this intuition is not always correct. Across frontier open-weight reasoning models spanning GPT-OSS, Phi, OLMo, and Qwen model families, we find that the model's decision is already strongly encoded at the beginning of thinking, with a probe on the first token's hidden representation predicting refusal/compliance with $\ge0.85$ AUROC and $\sim90$\% balanced accuracy. We also find little evidence that current models can use their thinking trace to deliberate about safety, as additional thinking after the first 20\% of the trace rarely moves the final decision. While sentence-level inspection of thinking traces may show signs of oscillation between refusal- and compliance-leaning rationales, we find that in $\geq 85$\% of thinking traces, such oscillations exert limited to no influence on the final response. We also examine the effect of existing inference-time and training-based safety interventions and find that they largely alter thinking behavior by shifting models toward more refusal-leaning reasoning while substantially reducing helpfulness on benign prompts. Our results suggest that safety behavior in current reasoning models is much less deliberative than commonly assumed, highlighting the need for training methods that more effectively utilize thinking traces for safety-critical decision making.
Show more
View full details
Poster

Optimal Recalibration of an Online Predictor

Lunjia Hu ⋅ Kevin Tian ⋅ Chutong Yang
Dec 11, 8:30 AM - 11:30 AM Hall C1 #A429
We study the problem of recalibrating an online predictor [KE17, OKS24]: given an arbitrary ``hint'' sequence of forecasts, the learner must output new predictions that are calibrated while incurring small excess error relative to the original forecasts, under a proper loss. We give an online algorithm that achieves $(\varepsilon, \varepsilon^2)$-recalibration for Lipschitz proper losses in $T \approx \varepsilon^{-3}$ rounds, using an imbalanced extension of the recent simultaneous Blackwell approachability reduction framework of [HTY26]. We also show this tradeoff is optimal by proving a matching lower bound for recalibrating against the squared loss. As an application, we show how our recalibration algorithm can be combined with the online refinement method of [FH23] to obtain simultaneous $\varepsilon$-calibration and $\varepsilon^2$-calibeating for smooth proper losses at the same asymptotic rate, improving upon prior works that achieved these properties separately or with a worse $\varepsilon$ dependence. We also discuss extensions to settings with multiple hint sequences.
Show more
View full details
Poster

Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability

Qingyue Zhao ⋅ Kaixuan Ji ⋅ Heyang Zhao ⋅ Quanquan Gu
Dec 11, 8:30 AM - 11:30 AM Hall C1 #A526
*Kullback-Leibler* (KL) regularization is ubiquitous in reinforcement learning (RL) algorithms in the form of *reverse* or *forward* KL. Recent studies have demonstrated $\epsilon^{-1}$-type fast rates for RL under reverse KL regularization, in contrast to the standard $\epsilon^{-2}$-type sample complexity. However, for forward-KL-regularized objectives, existing statistical analyses are either not applicable or resulting in $\tilde{O}(\epsilon^{-2})$ slow rates. We take the first step towards addressing this problem via a streamlined analysis of forward-KL-regularized offline contextual bandits. We give the first $\tilde{O}(\epsilon^{-1})$ upper bounds in tabular and general function approximation settings, both under notions of *single-policy concentrability*. In particular, our convex-analytical pipeline unifies these settings by exploiting the pessimism principle in a novel way and completely bypasses the proof routines in previous works based on the mean-value theorem, which might be of independent interest. Moreover, we provide rate-optimal lower bounds, manifesting the tightness of our upper bounds in terms of statistical rates. Our lower bounds also demonstrate that the forward-KL-regularized sample complexity recovers the unregularized slow rate in the low-regularization regime, similarly to the reverse-KL regularization.
Show more
View full details
Poster

Improved Leverage Score Sampling for Constrained Active Linear Regression

Aarshvi Gajjar ⋅ Syamantak Kumar ⋅ Aditya Makkar ⋅ Christopher Musco ⋅ Joey Zhou
Dec 11, 8:30 AM - 11:30 AM Hall C1 #A518
In this paper we study active learning for constrained linear regression. Given a design matrix $A \in \mathbb{R}^{n \times d}$, a constraint set $\mathcal C \subseteq \mathbb{R}^d$, and query access to a response vector $b \in \mathbb{R}^n$, we seek to output an approximate solution to the problem $\min_{x\in \mathcal{C}} \lVert Ax - b\rVert_2^2$ using as few queries to $b$ as possible. This problem arises in many scientific and engineering applications, and _randomized leverage score sampling_ provides a powerful method to solve it. However, existing leverage score methods either ignore the constraint or encode it only through ridge regularization, thereby suffering poor query complexity for anisotropic constraint sets. We propose _ellipsoid-regularized leverage scores_, where we first approximate the constraint set by an outer ellipsoid and then use its shape matrix to bias sampling toward directions that matter under the constraint geometry. We prove that the resulting query complexity is governed by a natural ``anisotropic effective dimension`` of the problem, $d_{\text{eff}}(\mathcal{C}) \leq d$. In particular, we show that $\tilde O(d_{\text{eff}}(\mathcal{C})/\varepsilon^2)$ label queries suffice to return a feasible point whose objective value is at most $(1+\varepsilon)$ times the optimum. This bound is typically much smaller than what would be obtained using standard leverage scores. Furthermore, for convex constraints, we show how to improve the dependence on $\varepsilon$ from $1/\varepsilon^2$ to $1/\varepsilon$. We complement these upper bounds with two lower bounds: first, a lower bound showing that the $1/\varepsilon^2$ dependence is unavoidable without convexity assumptions on $\mathcal C$, and second, a lower bound showing that the effective-dimension dependence is unavoidable for ellipsoidal constraints. We also provide experiments supporting our theoretical results.
Show more
View full details
Poster

Optimal Rates for Pure $\varepsilon$-Differentially Private Stochastic Convex Optimization with Heavy Tails

Andrew Lowy
Dec 11, 8:30 AM - 11:30 AM Hall C1 #A1114
We study stochastic convex optimization (SCO) with heavy-tailed gradients under pure $\varepsilon$-differential privacy (DP). Instead of assuming a bound on the worst-case Lipschitz parameter of the loss, we assume only a bounded $k$-th moment. This assumption allows for unbounded, heavy-tailed stochastic gradient distributions, and can yield sharper excess risk bounds. Prior work characterized the minimax optimal rate for $\rho$-zero-concentrated DP SCO up to logarithmic factors in this setting, but the pure $\varepsilon$-DP case has remained open. We characterize the minimax optimal excess-risk rate for pure $\varepsilon$-DP heavy-tailed SCO up to logarithmic factors. Our algorithm achieves this rate in polynomial time with high probability. Moreover, it runs in deterministic polynomial time when the worst-case Lipschitz parameter is polynomially bounded. For important structured problem classes --- including hinge/ReLU-type and absolute-value losses on Euclidean balls, ellipsoids, and polytopes --- we achieve deterministic polynomial time even when the worst-case Lipschitz parameter is infinite. Our approach is based on a novel framework for privately optimizing Lipschitz extensions of the empirical loss. We complement our upper bound with a nearly matching high-probability lower bound.
Show more
View full details
Poster

Mecha-nudges for Machines

Giulio Frey ⋅ Kawin Ethayarajh
Dec 11, 8:30 AM - 11:30 AM Hall C1 #A912
AI agents are becoming active decision-makers on the Internet. As they make decisions in the same environments as humans, the environments themselves can change to influence them. We call this $\textit{mecha-nudging}$: changes to how choices are presented that systematically influence AI agents without materially degrading the decision environment for humans. To measure this phenomenon, we combine two frameworks---$\textit{Bayesian persuasion}$ from economics and $\mathcal{V}$-$\textit{usable information}$ from computer science---to get a common unit (bits) for quantifying how environments change across a wide range of interventions, contexts, and models. We apply this framework to over six million Etsy listings and find that, after ChatGPT’s release, listings contain significantly more machine-usable information for predicting agent curation decisions, increasing by 0.143 bits out of a maximum possible increase of 0.355. This shift is robust across prompts, token choices, labeling models, and fine-tuning architectures; absent in a regulated-text placebo; and far larger than the effect of generic LLM rewriting. In contrast, a human study finds little to no change in human-usable information. Our results provide the first large-scale evidence that systematic mecha-nudging is already occurring in the wild.
Show more
View full details
Poster

ECHO: Terminal Agents Learn World Models for Free

Vaishnavi Shrivastava ⋅ Ahmed Awadallah ⋅ Dimitris Papailiopoulos
Dec 11, 8:30 AM - 11:30 AM Hall C1 #A1029
CLI agents are the closest thing language models have to an embodied setting: the model emits commands, the terminal executes them, and the returned stream---stdout, errors, file contents---records the consequences of its actions. We argue that this stream is a supervision signal, but standard agent RL largely discards it: GRPO-style training updates action tokens while ignoring environment responses, even though rollouts already contain them. We introduce ECHO (Environment Cross-entropy Hybrid Objective), an auxiliary loss that trains the policy to predict observation tokens alongside the policy gradient. ECHO reuses the same forward pass, requires no additional rollouts, and turns terminal feedback into a dense signal that remains informative even on failed trajectories. This objective shapes the policy toward a world model of terminal dynamics, plausibly improving its priors over which actions are likely to succeed. On TerminalBench 2, ECHO nearly doubles pass@1: Qwen3-8B improves from 2.70% to 5.17%, and Qwen3-14B from 5.17% to 10.79%. From base Qwen3-8B, ECHO+GRPO matches expert-SFT-then-GRPO on held-out terminal tasks without the expert demonstrations required for SFT, and closes roughly half this gap on TerminalBench 2. Without verifier rewards, ECHO can lead to self-improvement through exploration alone, suggesting environment observations are not merely context for actions but supervision for the policy itself.
Show more
View full details
Poster

The Invisible Hand of Physics: When Video Diffusion Models Know More Than They Show

Parsa Esmati ⋅ Somjit Nath ⋅ Katja Hofmann ⋅ Derek Nowrouzezahrai ⋅ Samira Ebrahimi Kahou ⋅ Majid Mirmehdi
Dec 11, 8:30 AM - 11:30 AM Hall C1 #A101
Modern video diffusion models generate increasingly realistic and temporally coherent videos, motivating their use as candidate world simulators. Yet it remains unclear whether these models internally encode physical structure, or merely reproduce motion patterns seen during training. We study this question by probing video diffusion models along latent trajectories corresponding to real videos with known physical plausibility. To obtain such trajectories, we approximately invert the deterministic sampling process by integrating the learned velocity field backward from a clean video latent to noise, giving access to the model’s intermediate states and attention maps. Using these recovered trajectories, we show that physical plausibility is linearly decodable from diffusion transformer states across IntPhys and InfLevel, reaching around 81\% average accuracy and outperforming dedicated representation-learning baselines such as V-JEPA and VideoMAE. Surprisingly, this signal is absent from the VAE latent input and emerges inside the denoising transformer itself, despite the model not being trained with a self-supervised predictive objective. These findings suggest that physically meaningful representations can arise as a byproduct of generative denoising.
Show more
View full details
Poster

The Value of Being Wrong: Self-Mined Visual In-Context Learning from Errors

Shu Zhao ⋅ TAN YU
Dec 11, 8:30 AM - 11:30 AM Hall C1 #A720
Visual in-context learning (ICL) enables vision-language models (VLMs) to adapt at test time via demonstration examples, but its effectiveness depends critically on the examples selected. Recent counterfactual selection methods improve ICL by constructing demonstrations that expose how individual attribute changes affect the answer. However, they require multi-stage pipelines involving attribute extraction, caption engineering, and composed image matching. We propose a simpler alternative grounded in a key observation: a model's own prediction errors are natural counterfactual demonstrations that directly encode its failure modes. Our method, SMILE (Self-Mined Visual In-Context Learning from Errors), builds a model-specific pool of hard negatives offline by recording the target VLM's own mistakes. At test time, the prediction serves as a direction signal that surfaces, in the semantic embedding space, the past mistakes most likely to recur for the current query. This prediction-conditioned identification provides a unified mechanism for both closed-set classification and open-ended visual question answering without task-specific design. Across four benchmarks and four VLMs, SMILE delivers an average task-score gain of +2.72 points over the SOTA baseline at 5× lower latency. Source code is provided in the supplementary material.
Show more
View full details
Poster

CoMMa: Contribution-Aware Medical Multi-Agents for Decentralized Oncology Decision Support

Yichen WU ⋅ Yujin Oh ⋅ Sangjoon Park ⋅ Kailong Fan ⋅ Yuhan Liu ⋅ Zhiyi Shi ⋅ Sekeun Kim ⋅ Dania Daye ⋅ Hana Farzaneh ⋅ Wei Liu ⋅ Xiang Li ⋅ Raul N Uppot ⋅ Quanzheng Li
Dec 11, 8:30 AM - 11:30 AM Hall C1 #A1124
Recent multi-agent frameworks have shown promise for oncology decision support, yet most assume centralized data access and rely on prompt-based assignment, limiting their applicability in privacy-sensitive clinical settings. We propose Contribution-Aware Medical Multi-Agents (CoMMa), a decentralized LLM-agent framework where specialists operate on partitioned clinical data streams. Unlike prior approaches that share inputs across agents, CoMMa enforces data decentralization to include stronger role specialization and further enhances this via agent-specific finetuning. To enable reliable and interpretable coordination, we introduce a contribution-aware aggregation mechanism that replaces stochastic, narrative-based reasoning with deterministic embedding projections to approximate each agent's marginal utility. This yields explicit credit assignment over agents, providing a stable and interpretable decision pathway aligned with clinical requirements. We evaluate CoMMa on multiple oncology benchmarks, including real-world multidisciplinary tumor board datasets from large academic hospitals in North America and East Asia, as well as public datasets, demonstrating strong performance and generalization across heterogeneous clinical settings.
Show more
View full details
Poster

Regret–Oracle Complexity Tradeoffs in Agnostic Online Learning

Idan Attias ⋅ Steve Hanneke ⋅ Arvind Ramaswami
Dec 11, 8:30 AM - 11:30 AM Hall C1 #A525
Agnostic online learning is classically solved via a reduction to the realizable setting, utilizing Littlestone's Standard Optimal Algorithm (SOA) as a base learner. However, the SOA is computationally intractable to execute even for a single round. To overcome this barrier, recent work in oracle-efficient online learning replaces the SOA with a realizable base learner that accesses the concept class exclusively through an offline empirical risk minimization (ERM) oracle. While such agnostic learners achieve near-optimal expected regret, they suffer from a doubly-exponential oracle complexity of $\mathcal{O}\big(T^{2^{\mathcal{O}(d_\mathrm{LD})}}\big)$, where $d_\mathrm{LD}$ is the Littlestone dimension and $T$ is the number of rounds. In this work, we significantly improve this oracle complexity while relying on an even weaker primitive: a weak-consistency oracle, which merely decides whether a given labeled dataset is realizable. At the core of our approach is an adaptive and dynamic agnostic-to-realizable reduction that actively prunes non-realizable label sequences on the fly. By using the VC dimension ($d_\mathrm{VC}$) to bound the number of dynamically maintained active paths, our algorithm reduces the total query complexity down to $\mathcal{O}(T^{d_\mathrm{VC}+1})$ while perfectly preserving near-optimal expected regret. Crucially, this dynamic pruning also yields a memory reduction over the standard reduction. Furthermore, we formally quantify the regret--oracle complexity tradeoff, providing upper bounds that smoothly interpolate between restricted query budgets and attainable expected regret. We complement these with lower bounds proving that any learner restricted to $Q = o(\sqrt{T})$ queries must suffer an expected regret of $\Omega(T/Q)$.
Show more
View full details
Poster

MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction

Jianing Zhang ⋅ Chenhao Zheng ⋅ Yajun Yang ⋅ Rustin Soraki ⋅ Winson Han ⋅ Chun-Liang Li ⋅ Jason Ren ⋅ Max Argus ⋅ Jieyu Zhang ⋅ Ranjay Krishna
Dec 12, 2:00 AM - 5:00 AM Hall C1 #A626
Motion forecasting is central to visual intelligence: agents must anticipate how objects will move in order to plan actions, reason about physical interactions, and synthesize realistic futures. We argue that 3D points in world coordinates provide a general representation that is class-agnostic, view-stable, compact, and directly useful for downstream tasks. We formalize the task of goal-conditioned 3D point motion forecasting: given a short visual history, a set of 3D query points on an object of interest, and a language description of the intended goal, the model predicts the future 3D trajectory of each point. We introduce a full stack to study this task at scale: (1) MolmoMotion-1M is a large corpus of action-described, object-grounded 3D point trajectory dataset annotated from 1.16M unconstrained videos; (2) PointMotionBench is a human-verified benchmark spanning 111 object categories and 61 motion types; and (3) MolmoMotion is a general motion forecasting model that supports both autoregressive coordinate prediction and flow-matching-based trajectory generation. MolmoMotion is able to accurately predicts diverse motion patterns with different language instructions, and significantly outperforms all existing motion prediction baselines on PointMotionBench. Finally, we show that the learned 3D motion prior transfers well to downstream applications: it improves training efficiency and generalization for robot manipulation, and its predicted trajectories provide effective motion guidance for generative models to synthesize videos with more realistic object motion.
Show more
View full details
Poster

Proper Agnostic Learning of Functions of Halfspaces

Sergei Tikhonov ⋅ Arsen Vasilyan
Dec 12, 2:00 AM - 5:00 AM Hall C1 #A421
We study the problem of computationally efficient **proper agnostic learning** of high-dimensional concept classes under the Gaussian distribution. In this setting, given i.i.d.\ labeled samples from an unknown distribution over $\mathbb{R}^d \times \{\pm 1\}$ whose marginal on $\mathbb{R}^d$ is Gaussian, the goal is to output a hypothesis from a target class $\mathcal{F}$ whose 0-1 loss is within $\varepsilon$ of that of the best classifier in $\mathcal{F}$. We give the first efficient proper agnostic learning algorithm for arbitrary Boolean functions of $K$ halfspaces under Gaussian marginals. Our algorithm runs in time $d^{O(K^2 \log(1/\varepsilon)/\varepsilon^2)} + (K/\varepsilon)^{O(K^3/\varepsilon^{2.5})}$. Prior to our work, the only known algorithm for $K \geq 2$ was brute-force search, with runtime exponential in $d$. Moreover, the dependence of our runtime on the dimension $d$ matches that of the best known \emph{improper} learning algorithm, namely $d^{\widetilde{O}(K^2/\varepsilon^2)}$. For the special case of a single halfspace ($K=1$), the best previous runtime was $d^{O(1/\varepsilon^4)} + (1/\varepsilon)^{O(1/\varepsilon^6)}$.\ Our algorithm improves this to $d^{O(1/\varepsilon^2)} + (1/\varepsilon)^{O(1/\varepsilon^{2.5})}$. Once again, the dependence on $d$ matches that of the best known improper algorithm, namely $d^{O(1/\varepsilon^2)}$. Furthermore, the dependence of our runtime on the dimension $d$ is essentially optimal in the statistical query model.
Show more
View full details
Poster

Targeted Review for AI-Assisted Biodiversity Surveys: Active Continuous-Score Occupancy Modeling

Timm Haucke ⋅ Lauren Harrell ⋅ Justin Kay ⋅ Mary K Clapp ⋅ Sara Beery
Dec 12, 2:00 AM - 5:00 AM Hall C1 #A921
We increasingly use machine learning to label scientific datasets. The models we develop and deploy are improving all the time, but they are not and will likely never be perfect. Mistakes matter, as errors can propagate into our scientific understanding, particularly when systematically biased. Very reasonably, scientists thus review substantial proportions of ML-generated labels to verify or correct mistakes in pursuit of ensuring their scientific findings are not biased by ML. In this work, we focus on helping scientists optimally allocate this reviewing effort relative to their scientific goals. We focus on a specific class of scientists (ecologists) and a specific, widespread, and impactful modeling target (occupancy modeling, which estimates where species are likely to occur, conditioned on environmental factors). We introduce ACORN (Active Continuous-Score Occupancy Modeling), a method that incorporates ML predictions into occupancy models and strategically selects samples for expert review that are maximally informative for downstream ecological analysis. Across camera-trap and bioacoustic datasets, our method recovers ecological conclusions close to those obtained from fully human-labeled data, while requiring substantially fewer expert reviews than non-targeted review policies. Our results suggest that ML-assisted scientific workflows should optimize expert effort for downstream inference, rather than for classifier accuracy alone, especially when human review budget is limited.
Show more
View full details
Poster

MoSE3: Learning World-Space SE(3) at Every Pixel

Jiahuan(Joanna) Cheng ⋅ Zhiyi Li ⋅ Tian Xia ⋅ Ruojin Cai ⋅ Yilun Du ⋅ Qianqian Wang
Dec 12, 2:00 AM - 5:00 AM Hall C1 #A615
Dense 2D/3D point tracking has been the dominant paradigm for modeling motion in dynamic scenes, but a point track is just a 3-DoF translation curve per pixel: it captures where pixels go, not the rotation of the underlying part, nor which pixels move together as one body. We propose MoSE3, the first feed-forward model that predicts dense SE(3) motion from monocular RGB video, producing full 6-DoF rigid transforms at every pixel in world space. Per-pixel SE(3) motion offers a richer view of how a scene moves: rotation, translation, and grouping all at once. Directly predicting SE(3) is challenging: rotations lie on a curved manifold that is ill-suited to Euclidean regression, and annotations for SE(3) are particularly difficult to acquire. To address these challenges, MoSE3 predicts per-pixel SE(3) through two jointly learned intermediates, 3D point tracks and rigidity embeddings, and recovers SE(3) by differentiably fitting transforms within each soft rigid cluster, enabling end-to-end prediction and supervision. To close the data gap, we introduce Art-Kubric, a large-scale synthetic dataset with dense SE(3) and rigidity labels for articulated scenes with rich physical interactions. MoSE3 achieves state-of-the-art SE(3) estimation at pixel, part, and object levels on both rigid and articulated benchmarks, and state-of-the-art 3D point tracking on three datasets, while showing strong generalization to real-world videos despite being trained solely on synthetic motion data.
Show more
View full details
Poster

EVALUATION CARDS: An Interpretive Layer for AI Evaluation Reporting

Avijit Ghosh ⋅ Anka Reuel-Lamparth ⋅ Wm. Matthew Kennedy ⋅ Jenny Chim ⋅ Yilin Huang ⋅ Srishti Yadav ⋅ Anastassia Kornilova ⋅ Damian Stachura ⋅ Kevin Klyman ⋅ Jennifer Mickel ⋅ Felix Friedrich ⋅ Max Lamparth ⋅ Jan Batzner ⋅ Anoop Mishra ⋅ Jeba Sania ⋅ Eliya Habba ⋅ Nathan Heath ⋅ Shalaleh Rismani ⋅ Usman Gohar ⋅ Andrea Loehr ⋅ David Manheim ⋅ Ruchira Dhar ⋅ Sree Harsha Nelaturu ⋅ Aarush Sinha ⋅ Leshem Choshen ⋅ Yixiong Hao ⋅ Yanan Long ⋅ Andrew Tran ⋅ Drishti Sharma ⋅ Ishan Khire ⋅ Amit Saha ⋅ Subramanyam Sahoo ⋅ Michael Hardy ⋅ Michael A. Riegler ⋅ Kabir Manghnani ⋅ Michelle Lin ⋅ Nancy Jiang ⋅ Asaf Yehudai ⋅ Nuno Moniz ⋅ Yacine Jernite ⋅ Zeerak Talat ⋅ Stella Biderman ⋅ Mubashara Akhtar ⋅ Jessica Ji ⋅ Aris Hofmann ⋅ Mykel J Kochenderfer ⋅ Sanmi Koyejo ⋅ Irene Solaiman
Dec 12, 2:00 AM - 5:00 AM Hall C1 #A914
AI evaluation results are produced at scale but reported inconsistently across leaderboards, model cards, benchmark papers, and company blogs. This fragmentation is borne at the level of interpretation: readers cannot reliably compare results across sources, identify what is missing from a given report, or trace an aggregate claim to the evidence behind it. Recent efforts address isolated components of this problem but leave three gaps unresolved: They cover only narrow slices of the evaluation lifecycle and do not compose into a single interpretable record. They specify static representations that do not differentiate between the questions technical and policy readers bring to the same evidence. And they remain proposals on paper, without the extraction infrastructure required for adoption at scale. We present EVALUATION CARDS, an operational reporting layer that composes benchmark metadata, evaluation run data, and model metadata into a unified record. We (1) derive a reporting schema from a structured literature review of 52 papers and 10 stakeholder interviews, (2) implement four interpretive signals (reproducibility, documentation completeness, provenance and risk, and score comparability), rendered through reader modes calibrated to research and policy audiences, and (3) provide a deployed monitoring tool that applies EVALUATION CARDS across 5,498 models, 635 benchmarks, and 101,843 results, surfacing systematic gaps in current reporting practice.
Show more
View full details
Poster

Learning to Price with Persuasion

Maria-Florina Balcan ⋅ Tejas Pagare ⋅ Karan Singh
Dec 12, 2:00 AM - 5:00 AM Hall C1 #A405
Motivated by modern marketplaces, where the platform or the seller routinely gathers detailed user profiles, we study a novel learning theoretic model that simultaneously involves information and mechanism design. Specifically, we consider the economic setting recently introduced by Bergemann et al, where in addition to the menu of quality-price pairs, the seller offers information on the value of the match between product quality and buyer's taste via a signaling scheme. We relax the assumption that the seller knows the buyers' belief about the distribution of tastes and study the sample requirements of designing a revenue maximizing scheme. We consider both the batch setting where we have access to data from a set of i.i.d. buyers and an online demand query model where we observe the buyers behaviors to seller's schemes. Despite the apparent non-convexity of the problem, we also give the first FPTAS to compute a scheme that maximizes the revenue within an arbitrarily small additive loss, which was unknown even in the previous result of Bergemann et al. Overall, this brings a new learning perspective in asymmetric economic settings where buyers and sellers know different types of information.
Show more
View full details
Poster

Polynomial-Time Robust Multiclass Linear Classification under Gaussian Marginals

Ilias Diakonikolas ⋅ Giannis Iakovidis ⋅ Mingchen Ma
Dec 12, 2:00 AM - 5:00 AM Hall C1 #A417
We study the task of agnostic learning of multiclass linear classifiers under the Gaussian distribution. Given labeled examples $(x, y)$ from a distribution over $\mathbb{R}^d \times [k]$, with Gaussian $x$-marginal, the goal is to output a hypothesis whose error is comparable to that of the best $k$-class linear classifier. While the binary case $k=2$ has a well-developed algorithmic theory, much less is known for $k \ge 3$. Even for $k=3$, prior robust algorithms incur exponential dependence on the inverse of the desired accuracy in both complexity and representation size. In this work, we develop new structural results for multiclass linear classifiers and use them to design fully polynomial-time robust learners with dimension-independent error guarantees. Our first result shows that the standard multiclass perceptron algorithm requires super-polynomially many samples and updates, even with clean labels and Gaussian marginals, revealing a basic obstruction absent in the binary case. Our main positive result is a pairwise improper-learning framework which yields an efficient learner with error $\widetilde O(k^{3/2}\sqrt{\mathrm{opt}})+\epsilon$ for general $k$. Additionally, we develop a sharper localization-based framework which leads to error $O(\mathrm{opt})+\epsilon$ for $k=3$, and error $\mathrm{poly}(k)\mathrm{opt}+\epsilon$ for geometrically regular $k$-class linear classifiers.
Show more
View full details
Poster

Flow Matching Reinforcement Learning via SDE Inference

Maojiang Su ⋅ Tsung-En Lin ⋅ Jerry Yao-Chieh Hu ⋅ Guo Ye ⋅ Haoran Lu ⋅ Shang Wu ⋅ Zhaoran Wang ⋅ Han Liu
Dec 12, 2:00 AM - 5:00 AM Hall C1 #A517
We develop a unified framework for flow-based reinforcement learning (RL) grounded in diffusion–flow duality and establish its theoretical foundations. The frameworks enables RL for deterministic flow matching inference by introducing diffusion stochastic inference dynamics that supports exploration while admitting deterministic deployment. We show that our frameworks subsumes several existing flow-based RL methods as special cases and inspire effective now methods. Then we provide theoretical foundations for the frameworks by establishing the correctness and performance transfer guarantee. Specifically, we prove that the policies optimized under stochastic dynamics close to deterministic dynamics at deployment when the pretrained model is well-trained. Moreover, we show that the policy improvement achieved under training-time SDE inference transfers to deployment-time ODE inference. Finally, we conduct experiments to validate our theoretical results.
Show more
View full details
Poster

VLSplat: Vision-Language Guided Object-Centric 3D Gaussian Splatting via Scene Graph

Yuntae Jeon ⋅ Younho Jeon ⋅ Sujin Jin ⋅ Sungho Jo ⋅ Seunghee Park
Dec 12, 8:30 AM - 11:30 AM Hall C1 #A601
Learning semantic representations for 3D Gaussian Splatting has recently emerged as a promising direction for 3D scene understanding. However, existing 2D-to-3D semantic lifting approaches rely primarily on 2D segmentation supervision and lack object-level priors, causing the learned representation to be driven by local mask evidence rather than holistic object structure. In this paper, we present VLSplat, a vision-language guided approach for object-centric semantic lifting in 3D Gaussian Splatting. Our method augments mask-based lifting with object-level semantic priors derived from vision-language models and refines Gaussian representations using an object-group scene graph. The refinement is performed through two language-guided modules: intra-group refinement suppresses semantic noise within object groups, while inter-group acquisition expands object support regions by incorporating structurally relevant candidates from neighboring groups. Extensive experiments on indoor scene datasets demonstrate that VLSplat improves semantic consistency and structural completeness. Our code and models are available at https://vlsplat.github.io/
Show more
View full details
Poster

Arena-T2I Hard: Benchmarking and Improving Faithfulness with Dependency-Aware Checklist Rewards

Yuanhao Ban ⋅ Tong Xie ⋅ Sohyun An ⋅ Yunqi Hong ⋅ Evan Frick ⋅ I-Hung Hsu ⋅ Wei-Lin Chiang ⋅ Ion Stoica ⋅ Cho-Jui Hsieh
Dec 12, 8:30 AM - 11:30 AM Hall C1 #A908
**Faithfulness**—how precisely a generated image aligns with its prompt—is increasingly central to the real-world utility of text-to-image (T2I) models. Existing faithfulness benchmarks, however, rely on simple atomic instructions, where top-tier systems already achieve near-perfect scores. As T2I models enter creative workflows, users increasingly issue multi-faceted requests involving intricate spatial relationships, stylistic constraints, and complex text rendering. In this setting, a single binary VLM-judge score no longer reveals **which** specific constraints the model fails to satisfy. We introduce **Arena-T2I Hard**, a 310-prompt stress benchmark drawn from real arena T2I logs, with approximately 30 decomposed yes/no constraints per prompt spanning six categories, including text rendering. The strongest closed-source system we evaluate reaches **0.855**, with a **33 pp** performance gap across 11 systems, demonstrating substantial discriminative power. Moreover, high public-arena rankings fail to predict faithfulness, confirming that holistic Bradley–Terry (BT) preference scores prioritize aesthetics over fine-grained prompt adherence. We propose a **dependency-aware checklist reward** that decomposes each prompt into a DAG of yes/no questions and zeroes descendants of failed parents, turning faithfulness into a per-constraint training signal. Combined with a BT aesthetic reward via **group-decoupled normalization (GDPO)**, which standardizes each reward within its rollout group so neither collapses, our recipe attains a strictly better faithfulness–aesthetics trade-off on **SD3.5-Medium** and **FLUX.1-dev** under MMRB2 pairwise comparisons than every single-reward, naive weighted-sum, or 4-reward BT-ensemble baseline. We release **Arena-T2I Hard** as a public stress benchmark.
Show more
View full details
Poster

Corrected Integrated Laplace Approximation for Bayesian Inference in Latent Gaussian Models

Jinlin Lai ⋅ Charles Margossian ⋅ Daniel Sheldon
Dec 12, 8:30 AM - 11:30 AM Hall C1 #A206
Latent Gaussian models (LGMs) are a popular class of Bayesian hierarchical models that include Gaussian processes, as well as certain spatial models and mixed-effect models. Efficient Bayesian inference of LGMs often requires marginalizing out the latent variables. For LGMs with a non-Gaussian likelihood, exact marginalization is not possible and a popular approach is to do approximate marginalization with an integrated Laplace approximation (ILA). Using ILA produces an approximate posterior which, in some settings, can differ significantly from the correct posterior, which impacts downstream applications. We propose an importance sampling scheme to correct the error introduced by ILA. By increasing the number of samples in importance sampling, the posterior with ILA converges to the correct posterior. This idea is realized with various techniques, including pseudo-marginalization, quasi-Monte Carlo and randomized quasi-Monte Carlo. We implement our methods in an automatic differentiation framework to support gradient-based algorithms when doing inference on the hyperparameters. For the latter, we specifically consider the use of Hamiltonian Monte Carlo. We demonstrate the benefits of reduced error in various applied models.
Show more
View full details
Poster

Whole-Body Compliant Control via Learned Force-Regulation Modules

Diego Aldarondo ⋅ Aadhithya Iyer ⋅ Daniel Giebisch ⋅ Nina Mortensen ⋅ Sridhar Pandian Arunachalam ⋅ Robert Cochran ⋅ Josh Merel
Dec 12, 8:30 AM - 11:30 AM Hall C1 #A709
To operate safely and effectively around people, humanoid robots must control the forces they exchange with the world. Whereas classical impedance and admittance methods shape contact forces precisely, modern reinforcement-learning controllers typically forgo such regulation in favor of robustness and faithful command tracking. Incorporating impedance-style compliance into a performant humanoid whole-body controller remains an open problem. We present a framework for learned whole-body force regulation that approximates the behavior of impedance controllers using only a PD position-target interface and position encoders. The framework includes three mechanisms for force regulation: passive joint-angle compliance via noisy action perturbations, joint-angle force regulation via perturbation--action blending around a commanded pose, and task-space force regulation via reward-shaped tracking of both a virtual forcefield attractor and a commanded pose. All three share a residual actor--critic recipe, an internal model of proprioception and perturbations, and a policy-blending procedure that combines multiple experts. A 6-DOF body command, optional upper-body pose, and controllable compliance expose the controllers as reusable low-level modules that enable compliant interaction and object manipulation across standing, crouching, and walking. We demonstrate whole-body teleoperation in simulation and on Sprout, a 27-DOF bipedal humanoid.
Show more
View full details