3

Stationary Robust Mean-Field Games under Model Mismatches

1

Room 1: Wednesday Posters 1-26

135

Policy-Based Trajectory Clustering in Offline Reinforcement Learning

2

182

Bandit Learning for Online Scheduling with Immediate Decision

3

297

CAIC: Congestion-Aware Intent Communication for Multi-Agent Reinforcement Learning

4

298

Policy Optimization for Adversarial Linear Mixture MDPs with Unknown Transitions and Bandit Feedback

5

368

HHC: Hierarchical Hypergraph Communication for Multi-Agent Systems

6

447

Robust Transfer Learning With Side Information

7

487

Multi-Agent RL with Invisible Collaborators: Marginal Advantage Estimation for Indirect Cooperation

8

681

Robust Constrained Markov Games: Multi-Agent Decision-Making under Model Uncertainty and Constraints

9

688

Gaussian Approximation and Multiplier Bootstrap for Federated Linear Stochastic Approximation

10

722

Stochastic Dominance Driven First-Order Policy Optimization for Multi-Objective Reinforcement Learning

11

751

SteinGate: Tail-Sensitive Safe Reinforcement Learning via Stein Discrepancy

12

770

Provably Efficient Reinforcement Learning in Continuous-Time Episodic MDPs with Poisson Decision Epochs

13

925

The Price of Knowledge: Optimal Algorithms for Costly Bandits

14

945

Provably Efficient Personalized Multi-Objective Bandits with Proactive Conversational Queries

15

1003

Revisiting TD Target Aggregation under Uncertainty in Q-Learning

16

1032

Analytic Planning under Uncertainty with Moment Closure

17

125

Federated Combinatorial Causal Bandits with Heterogeneous Causal Influences

18

183

Instrumental and Proximal Causal Inference with Gaussian Processes

19

301

On the Granularity of Causal Effect Identifiability

20

748

Interpretable Causal Discovery via Causal-Effect Constraints

21

775

Information-Theoretic Lower Bounds for Causal Inference under Credal Uncertainty

22

787

Matched-Pair Experimental Design with Active Learning

23

810

Structure Learning for Unfaithful Distributions: The Minimal Dependence Faithfulness

24

868

Improving RCT-Based Treatment Effect Estimation Under Covariate Mismatch via Calibrated Alignment

25

163

The Convergence Behavior of Adam under Heavy-Tailed Noise

26

90

Conformal Prediction Sets for Instance Segmentation

27

Room 2: Wednesday Posters 27-56

264

Identifying Labeling Mechanism in Positive–Unlabeled Learning under Unknown Class Prior

28

350

Inference for quantile-parametrized families via CDF confidence bands

29

363

Bandwidth Selection in Kernel Density Estimation for Model Calibration

30

389

Metacognitive Arbitration as Uncertainty Compression in Multi-Agent Language Models

31

390

Conditional neural control variates for variance reduction in Bayesian inverse problems

32

408

Linear Regression with Heteroskedastic Errors

33

463

Conformal Risk Sharing: Certified Cost Allocation with Participation Guarantees

34

482

Fairness Uncertainty Quantification: A Constrained Stochastic Optimization Perspective

35

563

Exact Uncertainty Propagation via Gaussian Process Neurons

36

584

Improving online FDR procedures via online analogs of e-closure and compound e-values

37

617

IDCR: Information-Directed Conformal Retrieval

38

650

PCU: Perturbation-Calibrated Uncertainty for Unsupervised Anomaly Detection

39

738

When Does Model Multiplicity Affect Prediction Intervals? A Sharp Phase Transition

40

808

Valid and Efficient Uncertainty Quantification for Federated Joint Shift

42

931

ALIGN: Adversarial Learning for Generalizable Speech Neuroprosthesis

43

990

PRISM: Calibrated Bayesian Fusion and Auditable Attribution for Reliable LLM Event Prediction from Text

44

1039

Score-Based Diffusion Priors for Adaptive Conformal Inference under Distribution Shift

45

1045

Robustness Quantification for Discriminative Models: a New Robustness Metric and its Application to Dynamic Classifier Selection

46

1087

Efficient Federated Conformal Prediction with Group-Conditional Guarantee

47

1128

Calibration-Aware Online Adaptation under Label Shift

48

475

Finite-Sample Regret Analysis of Nash Q-Learning with Random-Feature Approximation

49

867

Tight rates of approximation of mixed Nash equilibria by entropy regularization in continuous games

50

994

Expert Advice with Costly Observations

51

334

Online Learning for Project Selection in Hedonic Project Games

52

228

When Can We Learn from Noisy Logical Data? Parameterized Complexity of Approximate Concept Fitting in Description Logics

53

491

Online Fair Allocation with Demand-Side Time-Dependent Weight

54

185

Unified Confidence Adjustment for Robust Cross-Modal Retrieval under Test-Time Distribution Shifts

55

900

Partial Causal Structure Learning for Valid Selective Conformal Inference under Interventions

56

12

Higher-Order Hit-&-Run Samplers for Linearly Constrained Densities

1

Room 3: Thurs

day Posters 1-27

17

Implicit Variational Rejection Sampling

2

95

Probabilistic Verification of Neural Networks via Efficient Probabilistic Hull Generation

3

144

Exploiting Concavity Information in Contextual Bandit Optimization

4

204

Kronecker-Structured Nonparametric Spatiotemporal Point Processes

5

245

Particle Dynamics for Latent-Variable Energy-Based Models

6

354

Poisson–Gamma Modeling of Inter-Relational Dependencies in Dynamic Knowledge Graphs

7

365

From Bayes' Rule to Bayes Rules: Information Processing, Bayes' Theorem, and Imprecise Probabilities

8

451

Implicit Learning for Reasoning in First-Order Probabilistic Logic

9

495

Approximation Rates for Schrödinger Bridge Potentials via Fixed-Point ERM

10

821

VaSST: Variational Inference for Symbolic Regression using Soft Symbolic Trees

11

829

Learning to Infer Fast by Attending to Sparse Temporal Observations

12

885

MMG: Mutual Information Estimation via the MMSE Gap in Diffusion

13

916

Bayesian Experimental Design via Score Matching

14

947

General Bayesian Policy Learning

15

1095

Finding the Signal in the Spam: Jointly Learning Rewards and Worker Reliability from Pairwise Comparisons

16

150

Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion Models

17

427

EpiRDN: A Learnable Anisotropic Reaction-Diffusion Network for Epidemic Time Series Prediction

18

645

Provable Subspace Identification of Nonlinear Multi-view CCA

19

710

AudiFair: Privacy-Preserving Framework for Auditing Fairness

20

936

Classical and Quantum Speedups for Non-Convex Optimization via Energy Conserving Descent

21

1077

First-Order Softmax Weighted Switching Gradient Method for Distributed Stochastic Minimax Optimization with Stochastic Constraints

22

77

Efficient Q-Learning and Actor–Critic Methods for Robust Average-Reward Reinforcement Learning.

23

239

On the Sublinear Regret of Continuous K-Max Bandits

24

758

Global Convergence of Average Reward Constrained MDPs with Neural Critic and General Policy Parameterization

25

920

Explore, Refine, then Commit: Nearly Optimal Multi-Group Mean Estimation with Active Learning

26

1017

When and How Often is Weighted Majority Vote Optimal Under Log Loss?

27

20

Graph Contrastive Learning with Low-Rank Regularization and Low-Rank Attention for Noisy Node Classification

28

Room 4: Thurs

day Posters 28-59

62

Score-Regularized Joint Sampling with Importance Weights for Flow Matching

29

187

Remedying Coarsening-Based GNN Training under Heterophily via Adaptive Complementary Enhancement

30

275

Grokked Models are Better Unlearners

31

278

On the Effect of Sampling Diversity in Scaling LLM Inference

32

352

Evaluating the Role of Great Pre-trained Diffusion Models in Few-shot Phase: Warm-up and Acceleration

33

361

From Moves to Paths: A Hierarchical Framework for Trajectory Representation Learning

34

410

A Sequence-Graph Fusion Framework via BiMamba and Fourier-KAN for Interpretable Drug-Target Affinity Prediction

35

456

Not All Queries Need Deep Thought: CoFiCot for Adaptive Coarse-to-fine Stateful Refinement

36

497

Gradient-Guided Reward Optimization for Inference-time Alignment

37

552

ReVAD: From Imitation to Reasoning in Vectorized Autonomous Driving via Latent Space Search

38

660

Controlling Path Dependence in Gradient Ascent Unlearning through Forget-Set Ordering

39

687

Communication-Efficient Distributed Training for Collaborative Flat Optima Recovery in Deep Learning

40

724

Learning Informative Attention Weights for Person Re-Identification

41

739

ARGUS: Argumentation-Based Minimal-Change Repair for Verifiable LLM Self-Explanations

42

773

Mitigating Spurious Correlations with Memorization-Guided Dataset De-Biasing

43

774

Model Agnostic Graph Prompt Learning for Crystal Property Prediction

44

815

From Global to Factor-Wise Expert Composition in Discrete Diffusion Models

45

819

Capacity and Redundancy Trade-offs in Multi-Task Learning

46

845

Adaptive Fourier Decomposition-guided Neural Operator Design for Inverse PDE Problems

47

1119

Collapse-Aware Regularization for Reliable Reasoning Under Distribution Shift

48

1131

EagleConv: Bio-inspired Dual-Foveated Convolution for Robust Small Object Detection

49

32

SeSE: Black-Box Uncertainty Quantification for Large Language Models Based on Structural Information Theory

50

1038

Transformer Based Bayesian Network Structure Learning from an Information Theory Perspective

51

490

EVIA: Entropic Variational Inference Auto-encoding

52

458

Neural Routed Boosting: Robust Learning against Heteroscedastic Noise

53

309

Concept Sketching for Description Logics

54

492

Group-Fair Allocations of Contiguous Blocks of Indivisible Items

55

1083

LENS: Latent Precision Inference in Multi-LLM Routing

56

946

Workload-Preserving Differentially Private Synthetic Data for Causal Inference via Maximum-Entropy Calibration

57

930

Kernel Integrated (R^2): A Measure of Dependence

58

790

Certified Interventional Fidelity: Anytime-Valid, Adaptive Evaluation of Causal Claims in Mechanistic Interpretability

59