Optimization

Reward-Augmented Data Enhances Direct Preference Alignment of LLMs ICML 2025 Reward Fine-Tuning Two-Step Diffusion Models via Learning Differentiable Latent-Space Surrogate Reward CVPR 2025 Reward-Guided Iterative Refinement in Diffusion Models at Test-Time with Applications to Protein and DNA Design ICML 2025 Reward-Guided Tree Search for Inference Time Alignment of Large Language Models NAACL 2025 Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning ICLR 2025 Rewarding the Unlikely: Lifting GRPO Beyond Distribution Sharpening EMNLP 2025 Reward-Shifted Speculative Sampling Is An Efficient Test-Time Weak-to-Strong Aligner EMNLP 2025 Riemannian Bilevel Optimization JMLR 2025 Riemannian Diffusion Adaptation for Distributed Optimization on Manifolds ICML 2025 Riemannian Geometric-based Meta Learning AAAI 2025 Riemannian Optimization for LoRA on the Stiefel Manifold EMNLP 2025 Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift ICML 2025 Right Time to Learn: Promoting Generalization via Bio-inspired Spacing Effect in Knowledge Distillation ICML 2025 Ringmaster ASGD: The First Asynchronous SGD with Optimal Time Complexity ICML 2025 RiOT: Efficient Prompt Refinement with Residual Optimization Tree ACL 2025 Risk-averse Total-reward MDPs with ERM and EVaR AAAI 2025 Risk-Sensitive Diffusion: Robustly Optimizing Diffusion Models with Noisy Samples ICLR 2025 RIVAL: Reinforcement Learning with Iterative and Adversarial Optimization for Machine Translation EMNLP 2025 RLHF Algorithms Ranked: An Extensive Evaluation Across Diverse Tasks, Rewards, and Hyperparameters EMNLP 2025 RLKGF: Reinforcement Learning from Knowledge Graph Feedback Without Human Annotations ACL 2025 RLPF: Reinforcement Learning from Prediction Feedback for User Summarization with LLMs AAAI 2025 RMoA: Optimizing Mixture-of-Agents through Diversity Maximization and Residual Compensation ACL 2025 Robot Learning with Super-Linear Scaling RSS 2025 Robust Algorithms for Recovering Planted r-Colorable Graphs COLT 2025 Robust Feature Learning for Multi-Index Models in High Dimensions ICLR 2025