Optimization

DON’T STOP ME NOW: EMBEDDING BASED SCHEDULING FOR LLMS ICLR 2025 DORM: Preference Data Weights Optimization for Reward Modeling in LLM Alignment EMNLP 2025 Do Stochastic, Feel Noiseless: Stable Stochastic Optimization via a Double Momentum Mechanism ICLR 2025 DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search ICLR 2025 Doubly-Bounded Queue for Constrained Online Learning: Keeping Pace with Dynamics of Both Loss and Constraint AAAI 2025 DP-FROST: Differentially Private Fine-tuning of Pre-trained Models with Freezing Model Parameters COLING 2025 DPGA-TextSyn: Differentially Private Genetic Algorithm for Synthetic Text Generation ACL 2025 DPO Kernels: A Semantically-Aware, Kernel-Enhanced, and Divergence-Rich Paradigm for Direct Preference Optimization ACL 2025 DPO Meets PPO: Reinforced Token Optimization for RLHF ICML 2025 Draft Model Knows When to Stop: Self-Verification Speculative Decoding for Long-Form Generation EMNLP 2025 D-RAG: Differentiable Retrieval-Augmented Generation for Knowledge Graph Question Answering EMNLP 2025 DragLoRA: Online Optimization of LoRA Adapters for Drag-based Image Editing in Diffusion Model ICML 2025 Drama: Mamba-Enabled Model-Based Reinforcement Learning Is Sample and Parameter Efficient ICLR 2025 DRBO: Mitigating the Bottleneck Effect via Dynamic Reward Balancing in Multi-reward LLM Optimization EMNLP 2025 DrDiff: Dynamic Routing Diffusion with Hierarchical Attention for Breaking the Efficiency-Quality Trade-off EMNLP 2025 DreamDPO: Aligning Text-to-3D Generation with Human Preferences via Direct Preference Optimization ICML 2025 DRM Revisited: A Complete Error Analysis JMLR 2025 DRoP: Distributionally Robust Data Pruning ICLR 2025 Drop Dropout on Single Epoch Language Model Pretraining ACL 2025 Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMs EMNLP 2025 Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization ICLR 2025 DROWN: Towards Tighter LiRPA-based Robustness Certification COLING 2025 DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization ACL 2025 DSBRouter: End-to-end Global Routing via Diffusion Schrödinger Bridge ICML 2025 DS-LLM: Leveraging Dynamical Systems to Enhance Both Training and Inference of Large Language Models ICLR 2025