Optimization

Wasserstein Distance Constraint and Parameter Sparsification for Batched and Iterative Knowledge Editing AAAI 2025 Wasserstein Flow Matching: Generative Modeling Over Families of Distributions ICML 2025 Wasserstein Gradient Flow over Variational Parameter Space for Variational Inference AISTATS 2025 Wasserstein Policy Optimization ICML 2025 WaterPool: A Language Model Watermark Mitigating Trade-Offs among Imperceptibility, Efficacy and Robustness NAACL 2025 Wavelet Diffusion Neural Operator ICLR 2025 WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling ICLR 2025 Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned Model ICLR 2025 Weighted Embeddings for Low-Dimensional Graph Representation AAAI 2025 Weighted-Reward Preference Optimization for Implicit Model Fusion ICLR 2025 Weights-Rotated Preference Optimization for Large Language Models EMNLP 2025 What Are Step-Level Reward Models Rewarding? Counterintuitive Findings from MCTS-Boosted Mathematical Reasoning AAAI 2025 What to Distill? Fast Knowledge Distillation with Adaptive Sampling ICCV 2025 When Anchors Meet Cold Diffusion: A Multi-Stage Approach to Lane Detection ICCV 2025 When and why randomised exploration works (in linear bandits) ALT 2025 When Attention Sink Emerges in Language Models: An Empirical View ICLR 2025 When Confidence Fails: Revisiting Pseudo-Label Selection in Semi-supervised Semantic Segmentation ICCV 2025 When Every Token Counts: Optimal Segmentation for Low-Resource Language Models COLING 2025 When Evolution Strategy Meets Language Models Tuning COLING 2025 When Inverse Data Outperforms: Exploring the Pitfalls of Mixed Data in Multi-Stage Fine-Tuning EMNLP 2025 When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMs EMNLP 2025 When to Forget? Complexity Trade-offs in Machine Unlearning ICML 2025 When, Where and Why to Average Weights? ICML 2025 Where and How to Enhance: Discovering Bit-Width Contribution for Mixed Precision Quantization IJCAI 2025 Why Does the Effective Context Length of LLMs Fall Short? ICLR 2025