Theory

ULTRABENCH: Benchmarking LLMs under Extreme Fine-grained Text Generation EMNLP 2025 Uncertainty-Aware Contrastive Decoding ACL 2025 Understanding Factual Recall in Transformers via Associative Memories ICLR 2025 Understanding Matrix Function Normalizations in Covariance Pooling through the Lens of Riemannian Geometry ICLR 2025 Understanding Mode Connectivity via Parameter Space Symmetry ICML 2025 Understanding Multi-layered Transmission Matrices CVPR 2025 Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems EMNLP 2025 Understanding the Stability-based Generalization of Personalized Federated Learning ICLR 2025 Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld’s Episode Theory EMNLP 2025 Understanding Virtual Nodes: Oversquashing and Node Heterogeneity ICLR 2025 U-Nets as Belief Propagation: Efficient Classification, Denoising, and Diffusion in Generative Hierarchical Models ICLR 2025 Unified Convergence Analysis for Score-Based Diffusion Models with Deterministic Samplers ICLR 2025 Unique Hard Attention: A Tale of Two Sides ACL 2025 Universal Sharpness Dynamics in Neural Network Training: Fixed Point Analysis, Edge of Stability, and Route to Chaos ICLR 2025 Unraveling the Smoothness Properties of Diffusion Models: A Gaussian Mixture Perspective ICCV 2025 Unstable Grounds for Beautiful Trees? Testing the Robustness of Concept Translations in the Compilation of Multilingual Wordlists ACL 2025 URO-Bench: Towards Comprehensive Evaluation for End-to-End Spoken Dialogue Models EMNLP 2025 U-shaped and Inverted-U Scaling behind Emergent Abilities of Large Language Models ICLR 2025 Utility-Directed Conformal Prediction: A Decision-Aware Framework for Actionable Uncertainty Quantification ICLR 2025 UTMath: A Benchmark for Math Evaluation with Unit Test EMNLP 2025 VCSearch: Bridging the Gap Between Well-Defined and Ill-Defined Problems in Mathematical Reasoning EMNLP 2025 VerifiAgent: a Unified Verification Agent in Language Model Reasoning EMNLP 2025 VI^3NR: Variance Informed Initialization for Implicit Neural Representations CVPR 2025 VideoPhy: Evaluating Physical Commonsense for Video Generation ICLR 2025 VoiceBBQ: Investigating Effect of Content and Acoustics in Social Bias of Spoken Language Model EMNLP 2025