Skip to yearly menu bar Skip to main content


Show Detail
 
Filter Rooms:  

SUN 6 DEC
noon
Expo Demonstration:
(ends 2:00 PM)
Expo Talk Panel:
(ends 1:00 PM)
Expo Demonstration:
(ends 2:00 PM)
Expo Talk Panel:
(ends 1:00 PM)
Expo Talk Panel:
(ends 1:00 PM)
Expo Demonstration:
(ends 2:00 PM)
Expo Demonstration:
(ends 2:00 PM)
Expo Demonstration:
(ends 2:00 PM)
4:30 p.m.
Break:
(ends 5:30 PM)

MON 7 DEC
8 a.m.
Affinity Event:
(ends 5:00 PM)
Affinity Event:
(ends 5:00 PM)
Affinity Event:
(ends 5:00 PM)
Break:
(ends 9:00 AM)
8:30 a.m.
Education Track:
(ends 4:30 PM)
noon
Break:
(ends 2:00 PM)
1 p.m.
Affinity Event:
(ends 5:00 PM)
3 p.m.
Break:
(ends 3:30 PM)
5 p.m.
Remarks:
(ends 5:30 PM)
5:30 p.m.
Reception:
(ends 7:00 PM)

TUE 8 DEC
8 a.m.
Affinity Event:
(ends 5:00 PM)
8:30 a.m.
Break:
(ends 9:00 AM)
9 a.m.
Sydney Invited Talk:
Tie-Yan Liu
(ends 10:00 AM)
10 a.m.
Break:
(ends 10:30 AM)
Posters 10:00-1:00
(ends 1:00 PM)
11 a.m.
s -
Cadence: Music-Responsive Stage Lighting in Concert Video Generation
____ Controls
COrigami: An AI Pipeline for Co-Designing Flat-Foldable Visually Recognisable Origami
Da Capo
Dancing Ink Spirits: Negotiating Agency in Generative Chinese Ink Animation
Draw This First
Frictional Intelligence
Getting Motif-ated: Controllable AI Compositions from Injected Motif Prompts
MINT: Musical Intent Representation in Human–AI Co-Creation
Music-Originated Zeitgeist for Artistic Representation and Translation (MOZART): Distributed Agency in Music-to-Physical-Painting
PaintCopilot: Modeling Painting as Autonomous Artistic Continuation
Restored Lines: A Model Finds the Poet’s Hardest Line Breaks and Declines to Write Them
Shaping AI’s Beliefs Before It Generates: Human Sense of Agency in Creative AI
Story Sprout: A Picture-Book Studio Where Children Direct the AI and Keep the Pen
TextMixer: Writing via Sampling and Remixing
The Body at the Edge of the Signal: AI, Glitch, and Painting After the Machine
The Generative No and Sourced Refusal in Human-AI Co-Creation
Transcendent Contact: Expanding Creative Agency Through Hallucination
Water Album: A Built Negotiation of Agency from Ink Gesture to Public Space
What Can AI Offer as a Design Probe for Creativity? Reflections from Co-Designing a Creative Writing Tool
Whose Hand is on the Vinyl? Transcribing a DJ's Scratch Gestures from Video into a Playable Instrument
Windchime: an Audiovisual Installation with Audio-Language Model implementations
Δw ∈ ℝⁿ
(ends 2:00 PM)
noon
Break:
(ends 2:00 PM)
1:30 p.m.
Test Of Time:
(ends 2:00 PM)
Affinity Poster Session:
(ends 4:30 PM)
Affinity Event:
(ends 4:30 PM)
2 p.m.
Sydney Invited Talk:
Barbara E Engelhardt
(ends 3:00 PM)
3 p.m.
Break:
(ends 3:30 PM)
3:30 p.m.
Orals 3:30-5:00
[3:30] LatentUM: Unleashing the Potential of Interleaved Cross-Modal Reasoning via a Latent-Space Unified Model
[3:45] Thinking with Images as Continuous Policy: Numerical Visual Chain-of-Thought
[4:00] They Can See It but not Say It: Iterative Self Knowledge Re-expression in Visual Reasoning Relative Pose Identification
[4:15] GeoSym127K: Scalable Symbolically-verifiable Synthesis for Multimodal Geometric Reasoning
[4:30] Clarification as Supervision: Reinforcement Learning for Vision-Language Interfaces
[4:45] Incentivizing Medical Vision Capabilities from Large-Scale Multimodal Pre-training
(ends 5:00 PM)
Orals 3:30-5:00
[3:30] LoRAcles: Self-Supervised Weight-Space Interpretability at Scale
[3:45] IDEA: Unwrapping Visual Black-box Models by Interaction Decomposition
[4:00] Decomposing Earth Embeddings with Sparse Autoencoders
[4:15] Learning Reveals Invisible Structure in Low-Rank RNNs
[4:30] Geometry-Aware Similarity Metrics for Neural Representations on Riemannian and Statistical Manifolds
[4:45] FLIP: Fast and Accurate Global Lipschitz Estimation for Large Feedforward Networks
(ends 5:00 PM)
Orals 3:30-4:45
[3:30] Proactive Instance Navigation with Comparative Judgment for Ambiguous User Queries
[3:45] PhaseLoRA: Control-Regime-Conditioned Low-Rank Adaptation for Continuous-Action Vision-Language-Action Policies
[4:00] Resilience Matters for Embodied Agents System: New Metrics, Systematic Evaluation, and Optimization
[4:15] HeMeR: Heterogeneous Memory Reconciliation for Embodied Agents via Structured KV Reuse
[4:30] HABIT: Human-Aware Behavior and Interaction Training Dataset for Robot Manipulation
(ends 5:00 PM)
Orals 3:30-5:00
[3:30] BrainWorld: A Structural-Prior-Conditioned Generative Model for Whole-Brain 4D fMRI Dynamics
[3:45] A multi-scale information geometry reveals the structure of mutual information in neural populations
[4:00] Neural population tuning statistics as priors for multitask generalization
[4:15] Learning Sparse Semantic-Cortical Atoms for Multisubject Naturalistic fMRI Encoding
[4:30] MindAlign: Bridging EEG, Vision, and Language for Zero-Shot Visual Decoding
[4:45] Evaluating Neural Data Tokenizers: A Framework for Assessing Learned Representations of Spiking Activity
(ends 5:00 PM)
Orals 3:30-4:45
[3:30] CIG: Exploration via Conditional Information Gain
[3:45] Can In-Context Learning Support Intrinsic Curiosity?
[4:00] Emergence of Physical Intelligence via Controllable Information Production
[4:15] Coordination Connectivity: Shared Initialization Shapes the Joint-Policy Landscape in MARL
[4:30] SMART: Scalable Multi-Agent Role-conditioned Teaming via LLM-free Tree Search
(ends 5:00 PM)
4:30 p.m.
s -
Bodies in Dialogue: Exploring Perceived Agency through Embodied AI in Human-Robot Theatre
Effort
glitch-ing bodies
Human Operator
Impossible Rooms
Inner Witness: A Closed-Loop Neuroadaptive Audiovisual Installation
In the Mix: AI Support for Live DJ Track Selection
KAAYA: The Body Draws What the Eye Never Sees
Light Language Objects: Ambiguity and Otherness in Embodied AI
Lose Yourself: Controlling the Model
LumiComposer: Negotiating Creative Control Between Illumination, Mapping, and Generative Music Models
Magic Quill: A Real-time Score Engraving System for Live MIDI Performances
Passing: An Endless Journey through Reconstructed Spacetime with AI-Generated Sound
Preference Without Assertion: Locating Aesthetic Agency in a Gaze-Driven Design System
Presence Is Not Placement: Auditing What Vibrato Metrics Measure
Pullim: Untangling the Knots within
Rope Flow Music: An Embodied Instrument that Sonifies a Movement Practice
Smell with Genji: Rediscovering Sensory Experience with an AI Co-Smelling Partner
Stellar Pathfinding
Structural and Representational Agency in LLM-Driven Timbre Generation and Interpolation
When Brain Signals Steer Generative AI: Agency Beyond Causal Influence
Wishstone: Negotiating Voice Agency Through a Tangible Generative Keepsake
(ends 7:30 PM)
5 p.m.
Break:
(ends 6:00 PM)
Posters 5:00-8:00
(ends 8:00 PM)

WED 9 DEC
8:30 a.m.
Break:
(ends 9:00 AM)
9 a.m.
Sydney Invited Talk:
Satinder Singh
(ends 10:00 AM)
10 a.m.
Break:
(ends 10:30 AM)
Posters 10:00-1:00
(ends 1:00 PM)
11 a.m.
s -
AgencyBudget: Controlling Unsolicited Change in Iterative Human–AI Co-Creation
AI's Silent Omissions: Redistributing Bodily Agency
ANCORA
Creative Compression in LLM-Based Dramatic Character Interpretation
Don Qui-CoPilot: An Experiment in the Surrender and Reclamation of Self in the Age of Agentic AI
Everyone's a Director: A Trip to the Moon, recreated by 4.8 Million Votes
Exploring Textual Guidance for Video-to-Music Generation Models
From Artists to Artisans: Preserving Agency Against Cognitive Fordism
Give Me a Hand
How Much of This Is Mine? Shapley Credit for the Aesthetic Reranker
How to Get an Audience to Laugh at a Live Generative Story: Crowd-Sourced Humor and Shared Agency
Incentives Shape How Humans Co-Create with Generative AI
Love Mission 404: Manufacturing Spontaneity in a Generative Dating Show
Machine Eye
PainterBench: Evaluating Painterly Controllability in Generation and Verification
Performative Taste: When Creative Control Changes with Horizon
Spectral Evidence
Synthetic Capital: Symbolic Hierarchy in Fashion Photography and the Outsider Status of Generative Imagery
The Avatar in Chief
The National Average
The Sound of Reasoning
Towards Measuring Creative Agency through Observable Signals in Human–AI Graphic Design
When Rejected Properties Return: Measuring Veto Persistence in Conversational Image Editing
WHISPERS: An Interactive AI Thriller Series
Whose Hand Do You Prefer? The Steerability of Machine Aesthetic Judgment
(ends 2:00 PM)
noon
Break:
(ends 2:00 PM)
2 p.m.
Sydney Invited Talk:
Cheng Soon Ong
(ends 3:00 PM)
3 p.m.
Break:
(ends 3:30 PM)
3:30 p.m.
Orals 3:30-4:45
[3:30] Bridging Compute- and Data-Optimal Pretraining
[3:45] Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
[4:00] Quantized Reasoning Models Think They Need to Think Longer, but They Do Not
[4:15] Pruning and Distilling Mixture-of-Experts into Dense Language Models
[4:30] LittleLearner: Language Models Under Pedagogically-Controlled Knowledge Exposure
(ends 5:00 PM)
Orals 3:30-4:45
[3:30] SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild
[3:45] Beyond Family Labels: A Taxonomic Ornstein-Uhlenbeck Prior for Avian 3D Shape Recovery
[4:00] BEAST3D: animal behavioral analysis and neural encoding from multi-view video via Gaussian splatting
[4:15] Déjà View: Looping Transformers for Multi-View 3D Reconstruction
[4:30] Behavioral Geometric Supervision Aligns Video Foundation Models with Human Social Perception
(ends 5:00 PM)
Orals 3:30-4:45
[3:30] Agent Security is a Systems Problem
[3:45] CLIOPATRA: Extracting Private Information from LLM Insights
[4:00] Felid: A Flexible and Efficient Design for Transformer Fine-Tuning over Encrypted Data
[4:15] Catch-Only-One: Non-Transferable Examples for Model-Specific Authorization
[4:30] Can We Model the Artifacts Explicitly? Disentangle Artifacts via Pairwise Edit Relations for Image Manipulation Localization
(ends 5:00 PM)
Orals 3:30-4:45
[3:30] C3P: Contrastive promoter-protein pretraining yields representations capturing bacterial gene regulation
[3:45] TALK: One-Shot Batch Design for Protein Variant Effect Prediction
[4:00] Compact SO(3) Equivariant Atomistic Foundation Models via Structural Pruning
[4:15] CausalBind: Causal Modeling and Learning for Protein-Molecule Virtual Screening
[4:30] Emergent Biological Capabilities in a Foundation Model for Molecular Interactions
(ends 5:00 PM)
Orals 3:30-4:45
[3:30] We Should Distinguish Unlearning From Untraining
[3:45] AdaSRU: Adaptive Source-Free Recommendation Unlearning via Gradient-Constrained Optimization
[4:00] CURE: Counterfactual Unsafe-token Re-masking for Diffusion Large Language Model Test-time Alignment
[4:15] The Attacker in the Mirror: Breaking Self-Consistency in Safety via Anchored Bipolicy Self-Play
[4:30] Learning to Audit ML Models with Theory of Mind
(ends 5:00 PM)
Orals 3:30-5:00
[3:30] Do We Need Asynchronous SGD? On the Near-Optimality of Synchronous Methods
[3:45] Reference-Guided Training: Adaptive Gradient Scaling via Per-Sample Loss Comparisons
[4:00] Follow the Regularized Leader Does Not Converge in Constrained Optimization
[4:15] From Average Sensitivity to Small-Loss Regret Bounds under Random-Order Model
[4:30] Testable and Actionable Calibration for Full Swap Regret
[4:45] Prediction Under Imperfect Compression: A Theory of Approximate MDL
(ends 5:00 PM)
4:30 p.m.
s -
Activation Steering the Nan-Shan in Typhoon
Agent Inheritance Protocol: Speculating on Feralized Agents After Principals Die
AI Mom™
Algorithmic Flesh
Ars Incompleta: A Novel That No One Will Ever Finish Reading
Attention Garden
Automation of Creative Design Representation: A First Step Towards a Co-Pilot for Generative Design
Biocompiler: Compiling Spatial Network Optimization Problems into Living Solvers with Digital Fabrication System
Born, not Made
Cache Machine
Entangled Matter: AI, Humans and Golems
Ethos Lithos
FANVERSE: Exploring and Extending Branching Story Universes Across Canon and Fan Fiction
FlockWorld: Toward Population-Scale Multi-Agent Video World Models through Artificial Life Simulation
From Memory: Mechanistic Interpretability and Emotion as Artistic Mediums
Horror Vacui
In a Grove, Again: Optimizing over Feasible Event Histories for Incentive-Driven Testimony
Memory Machines #3: an oceanic pas de deux
Neo Ferro-Mýrmēx Economy
nom nom: Metabolic Worldbuilding through Neural Cellular Automata
Playing the Plot: Optimizing Narrative Structure with Strategic World Models
Symbiotic Traces: An Ecological Record of Language Model Training
The Dead Ear: A Language Model’s Inherited Accent Is an Archive, Not an Author
The Plot Refuses the Author: Diegetic Contestability for Character-Driven AI Co-Writing
What Value Forgets: Neural Search Within a Combinatorial-Game Value
(ends 7:30 PM)
5 p.m.
Break:
(ends 6:00 PM)
Posters 5:00-8:00
(ends 8:00 PM)

THU 10 DEC
8 a.m.
(ends 5:00 PM)
8:30 a.m.
Break:
(ends 9:00 AM)
9 a.m.
Sydney Invited Talk:
Shannon Vallor
(ends 10:00 AM)
10 a.m.
Break:
(ends 10:30 AM)
Posters 10:00-1:00
(ends 1:00 PM)
noon
Break:
(ends 2:00 PM)
1:30 p.m.
Award:
(ends 2:00 PM)
2 p.m.
Sydney Invited Talk:
José Hernández-Orallo
(ends 3:00 PM)
3 p.m.
Break:
(ends 3:30 PM)
3:30 p.m.
Orals 3:30-4:45
[3:30] Self-Programmed Execution for Language-Model Agents
[3:45] ExComm: Exploration-Stage Communication for Error-Resilient Agentic Test-Time Scaling
[4:00] Inductive Deductive Synthesis: Enabling AI to Generate Formally Verified Systems
[4:15] APS: Bias-Controlled Adaptive Prototype Simulation for Population-Scale LLM Agents
[4:30] Can LLM Agents Respond to Disasters? Benchmarking Heterogeneous Geospatial Reasoning in Emergency Operations
(ends 5:00 PM)
Orals 3:30-4:45
[3:30] Strong Stochastic Flow Maps
[3:45] Colored Noise Diffusion Sampling
[4:00] ParetoSlider: Diffusion Models Post-Training for Continuous Reward Control
[4:15] Shaping Useful Noise: Energy Distributions Predict Visual Pretraining Quality
[4:30] EntiRE: Invariant Learning for Robust Concept Erasure in Text-to-Image Generative Models
(ends 5:00 PM)
Orals 3:30-5:00
[3:30] Benchmark Health Index: A Systematic Framework for Benchmarking the Benchmarks of LLMs
[3:45] Leaderboard Hacking: Preference-Based Model Evaluations are Vulnerable to Manipulation
[4:00] GenAI Evaluation Results are Largely Artifacts of Evaluation Design Choices: Evidence from Audit Studies of Resume Screening
[4:15] Computer Use at the Edge of the Statistical Precipice
[4:30] Offloading Score: Measuring AI Reliance through Counterfactual Workflows
[4:45] ALTER: An Allen's Algebra-Based Evaluation Framework for Temporal Reasoning of LLMs
(ends 5:00 PM)
Orals 3:30-5:00
[3:30] TiRex-2: Generalizing TiRex to Multivariate Data and Streaming
[3:45] Fractional State Space Transition for Long Sequence Modeling
[4:00] Spectral Energy Allocation Enables Source-Free Domain Adaptation in Time Series Forecasting
[4:15] Filtered Conformal Ellipsoids for Graph-Native Time Series
[4:30] DIAGNO: Diagonal Spherical Neural Operators for Heterogeneous Earth Dynamics Modeling
[4:45] Mechanism-Aware Ensemble Conditioning for Data-Limited Emulation of Extreme Events
(ends 5:00 PM)
Orals 3:30-5:00
[3:30] The Aleatoric-Epistemic Dichotomy of Uncertainty is Meaningful and Indispensable for Machine Learning
[3:45] probly: Uncertainty-Aware Machine Learning
[4:00] Mitigating Confidence Miscalibration in Open-World Semi-Supervised Learning
[4:15] Impossibility of Distribution-Free Predictive Inference for Individual Treatment Effects
[4:30] Exact Gaussian Moment Matching for Residual Networks: a Second-Order Method
[4:45] Surprises in Proper Positive-Only Learning
(ends 5:00 PM)
Orals 3:30-4:45
[3:30] Graph Cascades: Contagion-Based Mesoscopic Rewiring for Structure-Aware Graph Machine Learning
[3:45] Releasing Anchors from Cross-View Correspondence: Probabilistic Multi-View Anchor Graph Clustering
[4:00] UECO: A Unified Encoder with Structure-Aware Attention Mixture via Iterative Edge Evolving for Neural Combinatorial Optimization
[4:15] MaxSketch: Robust Distinct Counting in Streams via Random Projections
[4:30] Free Decompression with Algebraic Spectral Curves
(ends 5:00 PM)
5 p.m.
Town Hall:
(ends 6:00 PM)
Break:
(ends 6:00 PM)
Posters 5:00-8:00
(ends 8:00 PM)

FRI 11 DEC
8 a.m.
Competition:
(ends 10:15 AM)
Workshop:
(ends 5:00 PM)
9 a.m.
Break:
(ends 9:30 AM)
noon
Break:
(ends 1:00 PM)
3 p.m.
Break:
(ends 3:30 PM)
3:30 p.m.
Competition:
(ends 5:45 PM)
5:30 p.m.
Reception:
(ends 7:30 PM)

SAT 12 DEC
8 a.m.
Workshop:
(ends 5:00 PM)
Workshop:
(ends 5:00 PM)
Workshop:
(ends 5:00 PM)
9 a.m.
Break:
(ends 9:30 AM)
10:30 a.m.
Competition:
(ends 12:45 PM)
noon
Break:
(ends 1:00 PM)
3 p.m.
Break:
(ends 3:30 PM)
3:30 p.m.