Optimization

Understanding Nonlinear Implicit Bias via Region Counts in Input Space ICML 2025 Understanding Reference Policies in Direct Preference Optimization NAACL 2025 Understanding Silent Data Corruption in LLM Training ACL 2025 Understanding the Learning Dynamics of LoRA: A Gradient Flow Perspective on Low-Rank Adaptation in Matrix Factorization AISTATS 2025 UNIALIGN: Scaling Multimodal Alignment within One Unified Model CVPR 2025 UniAP: Unifying Inter- and Intra-Layer Automatic Parallelism by Mixed Integer Quadratic Programming CVPR 2025 UniBuc-AE at SemEval-2025 Task 7: Training Text Embedding Models for Multilingual and Crosslingual Fact-Checked Claim Retrieval SemEval 2025 UniCBE: An Uniformity-driven Comparing Based Evaluation Framework with Unified Multi-Objective Optimization ICLR 2025 UniCO: On Unified Combinatorial Optimization via Problem Reduction to Matrix-Encoded General TSP ICLR 2025 Unified Discrete Diffusion for Categorical Data JMLR 2025 Uniform Mean Estimation for Heavy-Tailed Distributions via Median-of-Means ICML 2025 Unifying Streaming and Non-streaming Zipformer-based ASR ACL 2025 Unifying Uniform and Binary-coding Quantization for Accurate Compression of Large Language Models ACL 2025 UniICL: An Efficient ICL Framework Unifying Compression, Selection, and Generation ACL 2025 Unilaw-R1: A Large Language Model for Legal Reasoning with Reinforcement Learning and Iterative Inference EMNLP 2025 Unisolver: PDE-Conditional Transformers Towards Universal Neural PDE Solvers ICML 2025 Unity in Diversity: Video Editing via Gradient-Latent Purification CVPR 2025 Universal generalization guarantees for Wasserstein distributionally robust models ICLR 2025 Universal Neural Optimal Transport ICML 2025 Universal Online Convex Optimization Meets Second-order Bounds JMLR 2025 Universal Post-Processing Networks for Joint Optimization of Modules in Task-Oriented Dialogue Systems AAAI 2025 Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate NAACL 2025 Unlearning-based Neural Interpretations ICLR 2025 Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model Optimizers AAAI 2025 Unlocking Decoding-time Controllability: Gradient-Free Multi-Objective Alignment with Contrastive Prompts NAACL 2025