Optimization

DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs EMNLP 2025 DTA: Dual Temporal-Channel-Wise Attention for Spiking Neural Networks WACV 2025 DTW-Align: Bridging the Modality Gap in End-to-End Speech Translation with Dynamic Time Warping Alignment EMNLP 2025 DTZO: Distributed Trilevel Zeroth Order Learning with Provable Non-Asymptotic Convergence ICML 2025 Dual-Balancing for Physics-Informed Neural Networks IJCAI 2025 Dual Feature Reduction for the Sparse-group Lasso and its Adaptive Variant ICML 2025 DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads ICLR 2025 Dynamic Algorithm Termination for Branch-and-Bound-based Neural Network Verification AAAI 2025 Dynamic and Generalizable Process Reward Modeling ACL 2025 Dynamic angular synchronization under smoothness constraints JMLR 2025 Dynamic Back-Substitution in Bound-Propagation-Based Neural Network Verification AAAI 2025 Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts NAACL 2025 Dynamic Fisher-weighted Model Merging via Bayesian Optimization NAACL 2025 Dynamic Group Normalization: Spatio-Temporal Adaptation to Evolving Data Statistics CVPR 2025 Dynamic Jointly Batch Selection for Data Efficient Machine Translation Fine-Tuning EMNLP 2025 Dynamic Loss-Based Sample Reweighting for Improved Large Language Model Pretraining ICLR 2025 Dynamic Low-Rank Sparse Adaptation for Large Language Models ICLR 2025 Dynamic Negative Guidance of Diffusion Models ICLR 2025 Dynamic Parallel Tree Search for Efficient LLM Reasoning ACL 2025 Dynamic Retriever for In-Context Knowledge Editing via Policy Optimization EMNLP 2025 Dynamic Scaling of Unit Tests for Code Reward Modeling ACL 2025 Dynamic Sparse Training versus Dense Training: The Unexpected Winner in Image Corruption Robustness ICLR 2025 Dynamic-Width Speculative Beam Decoding for LLM Inference AAAI 2025 Dyn-D^2P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee IJCAI 2025 EARL-BO: Reinforcement Learning for Multi-Step Lookahead, High-Dimensional Bayesian Optimization ICML 2025