Theory

Principled Analysis of Deep Reinforcement Learning Evaluation and Design Paradigms AAAI 2026 Probabilistic Safety Verification of Neural Policies via Predicate Abstraction AAAI 2026 Probabilistic Verification of Neural Networks via Efficient Probabilistic Hull Generation UAI 2026 Promises Made, Promises Kept: Safe Pareto Improvements via Ex Post Verifiable Commitments AAAI 2026 Proof Systems for Tensor-based Model Counting AAAI 2026 Proof Systems That Tightly Characterise Model Counting Algorithms AAAI 2026 Provably Data-Driven Projection Method for Quadratic Programming AAAI 2026 Quantifying and Improving Adaptivity in Conformal Prediction Through Input Transformations AAAI 2026 Quantifying the Limits of Segmentation Foundation Models: Modeling Challenges in Segmenting Tree-Like and Low-Contrast Objects WACV 2026 Randomization for Faster Exact Optimization of Discounted Markov Decision Processes COLT 2026 Repetition Makes Perfect: Recurrent Graph Neural Networks Match Message Passing Limit AAAI 2026 Rethinking AI: From Functions to Functors AAAI 2026 Rethinking Hallucinations: Correctness, Consistency, and Prompt Multiplicity EACL 2026 Rethinking Saliency Maps: A Cognitive Human Aligned Taxonomy and Evaluation Framework for Explanations AAAI 2026 Revisiting Differentiable Structure Learning: Inconsistency of L1 Penalty and Beyond AAAI 2026 Rigorous Asymptotics for First-Order Algorithms Through the Dynamical Cavity Method COLT 2026 Sample Complexity Bounds for Linear Constrained MDPs with a Generative Model ALT 2026 Sampling-Free Uncertainty Quantification via Hidden State Dynamics in Language Models AAAI 2026 Sandwiching Polynomials for Geometric Concepts with Low Intrinsic Dimension COLT 2026 Scientifically-Interpretable Reasoning Network (ScIReN): Discovering Hidden Relationships in the Carbon Cycle and Beyond AAAI 2026 SIDE: Surrogate Conditional Data Extraction from Diffusion Models AAAI 2026 Small Models Exhibit Limited Answer Consistency in Repetition Trials of the Multiple-Choice MMLU-Redux and MedQA Benchmarks AAAI 2026 SMiLE: Provably Enforcing Global Relational Properties in Neural Networks AAAI 2026 Spatio-Temporal Hierarchical Causal Models AAAI 2026 Spectral Basis Learning for Expressive Graph Neural Networks in Link Prediction AAAI 2026