Theory

Speculative Decoding Speed-of-Light: Optimal Lower Bounds via Branching Random Walks EACL 2026 Split-Layer: Enhancing Implicit Neural Representation by Maximizing the Dimensionality of Feature Space AAAI 2026 Stable Mean Flow: Lyapunov-Inspired One-Step Flow Matching CVPR 2026 Structural Approach to Guiding a Present-Biased Agent AAAI 2026 Studying Classifier(-Free) Guidance from a Classifier-Centric Perspective AAAI 2026 Super Level Sets and Exponential Decay: A Synergistic Approach to Stable Neural Network Training (Abstract Reprint) AAAI 2026 SVD-NO: Learning PDE Solution Operators with SVD Integral Kernels AAAI 2026 SymPyBench: A Dynamic Benchmark for Scientific Reasoning with Executable Python Code EACL 2026 The Correspondence Between Bounded Graph Neural Networks and Fragments of First-Order Logic AAAI 2026 The matrix-vector complexity of Ax=b COLT 2026 The Planted Number Partitioning Problem ALT 2026 The Search for Stability: Learning Dynamics of Strategic Publishers with Initial Documents (Abstract Reprint) AAAI 2026 The Strong Lottery Ticket Hypothesis for Multi-Head Attention Mechanisms AAAI 2026 Tighter Truncated Rectangular Prism Approximation for RNN Robustness Verification AAAI 2026 Towards Acyclic Preference Evaluation of Language Models via Multiple Evaluators AAAI 2026 Towards Provably Unlearnable Examples via Bayes Error Optimization AAAI 2026 TRACE: A Framework for Analyzing and Enhancing Stepwise Reasoning in Vision-Language Models EACL 2026 Tracking the Limits of Knowledge Propagation: How LLMs Fail at Multi-Step Reasoning with Conflicting Knowledge EACL 2026 Tractable Weighted First-Order Model Counting with Bounded Treewidth Binary Evidence AAAI 2026 Transferable Hypergraph Attack via Injecting Nodes into Pivotal Hyperedges AAAI 2026 Transformers in Pseudo-Random Number Generation: A Dual Perspective on Theory and Practice AAAI 2026 TTA-Bench: A Comprehensive Benchmark for Evaluating Text-to-Audio Models AAAI 2026 Two Constraint Compilation Methods for Lifted Planning AAAI 2026 Universality of high-dimensional scaling limits of stochastic gradient descent (extended abstract) COLT 2026 Unpacking the Implicit Norm Dynamics of Sharpness-Aware Minimization in Tensorized Models AAAI 2026