Optimization

Breaking Token Into Concepts: Exploring Extreme Compression in Token Representation Via Compositional Shared Semantics EMNLP 2025 Bregman Conditional Random Fields: Sequence Labeling with Parallelizable Inference Algorithms ACL 2025 Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization ICLR 2025 Bridging Jensen Gap for Max-Min Group Fairness Optimization in Recommendation ICLR 2025 Bridging Model Predictive Control and Deep Learning for Scalable Reachability Analysis RSS 2025 Bridging Robustness and Generalization Against Word Substitution Attacks in NLP via the Growth Bound Matrix Approach ACL 2025 Bridging the Capability Gap: Joint Alignment Tuning for Harmonizing LLM-based Multi-Agent Systems EMNLP 2025 Bridging the Gap between Gaussian Diffusion Models and Universal Quantization for Image Compression CVPR 2025 Bridging the Language Gaps in Large Language Models with Inference-Time Cross-Lingual Intervention ACL 2025 Broadening Target Distributions for Accelerated Diffusion Models via a Novel Analysis Approach ICLR 2025 Budgeted Online Continual Learning by Adaptive Layer Freezing and Frequency-based Sampling ICLR 2025 Building Math Agents with Multi-Turn Iterative Preference Learning ICLR 2025 Building Rome with Convex Optimization RSS 2025 Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient ACL 2025 Byte Latent Transformer: Patches Scale Better Than Tokens ACL 2025 Byzantine-Resilient Federated Alternating Gradient Descent and Minimization for Partly-Decoupled Low Rank Matrix Learning ICML 2025 CacheQuant: Comprehensively Accelerated Diffusion Models CVPR 2025 CaDA: Cross-Problem Routing Solver with Constraint-Aware Dual-Attention ICML 2025 CAKE: Cascading and Adaptive KV Cache Eviction with Layer Preferences ICLR 2025 CalibraEval: Calibrating Prediction Distribution to Mitigate Selection Bias in LLMs-as-Judges ACL 2025 Calibrated Disambiguation for Partial Multi-label Learning AAAI 2025 Calibrated Language Models and How to Find Them with Label Smoothing ICML 2025 Calibrated Multi-Preference Optimization for Aligning Diffusion Models CVPR 2025 Calibrating LLM Confidence by Probing Perturbed Representation Stability EMNLP 2025 Calibrating LLMs for Text-to-SQL Parsing by Leveraging Sub-clause Frequencies EMNLP 2025