Optimization

Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent ICML 2025 Model Performance-Guided Evaluation Data Selection for Effective Prompt Optimization ACL 2025 Model predictive control is almost optimal for restless bandits COLT 2025 Models of Heavy-Tailed Mechanistic Universality ICML 2025 Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence ICML 2025 ModernBERT or DeBERTaV3? Examining Architecture and Data Influence on Transformer Encoder Models Performance IJCNLP 2025 MoDification: Mixture of Depths Made Easy NAACL 2025 Modified K-means Algorithm with Local Optimality Guarantees ICML 2025 MoFE: Mixture of Frozen Experts Architecture NAACL 2025 MoKA:Parameter Efficiency Fine-Tuning via Mixture of Kronecker Product Adaption COLING 2025 MoLEx: Mixture of Layer Experts for Fine-tuning with Sparse Upcycling ICLR 2025 Momentum-Driven Adaptivity: Towards Tuning-Free Asynchronous Federated Learning ICML 2025 MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking ICML 2025 MONAS-ESNN: Multi-Objective Neural Architecture Search for Efficient Spiking Neural Networks WACV 2025 Monte Carlo Tree Diffusion for System 2 Planning ICML 2025 MOPO: Multi-Objective Prompt Optimization for Affective Text Generation COLING 2025 More Data or Better Data? A Critical Analysis of Data Selection and Synthesis for Mathematical Reasoning EMNLP 2025 More is not always better? Enhancing Many-Shot In-Context Learning with Differentiated and Reweighting Objectives ACL 2025 More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression EMNLP 2025 Morph: A Motion-free Physics Optimization Framework for Human Motion Generation ICCV 2025 MOS-Attack: A Scalable Multi-objective Adversarial Attack Framework CVPR 2025 MPBench: A Comprehensive Multimodal Reasoning Benchmark for Process Errors Identification ACL 2025 MPO: An Efficient Post-Processing Framework for Mixing Diverse Preference Alignment ICML 2025 MPO: Boosting LLM Agents with Meta Plan Optimization EMNLP 2025 MPPO: Multi Pair-wise Preference Optimization for LLMs with Arbitrary Negative Samples COLING 2025