reinforcement learning

Datasets and Recipes for Video Temporal Grounding via Reinforcement Learning EMNLP 2025 DeAL: Decoding-time Alignment for Large Language Models ACL 2025 Debate4MATH: Multi-Agent Debate for Fine-Grained Reasoning in Math ACL 2025 DecEx-RAG: Boosting Agentic Retrieval-Augmented Generation with Decision and Execution Optimization via Process Supervision EMNLP 2025 DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning ICCV 2025 Deep Reinforcement Learning with Time-Scale Invariant Memory AAAI 2025 DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments EMNLP 2025 DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search ICLR 2025 Defending Against Sophisticated Poisoning Attacks with RL-based Aggregation in Federated Learning AAAI 2025 Demonstrating Berkeley Humanoid Lite: An Open-source, Accessible, and Customizable 3D-printed Humanoid Robot RSS 2025 Demonstrating GPU Parallelized Robot Simulation and Rendering for Generalizable Embodied AI with ManiSkill3 RSS 2025 Demonstration Selection for In-Context Learning via Reinforcement Learning ICML 2025 Demystifying Long Chain-of-Thought Reasoning ICML 2025 Demystifying Multilingual Reasoning in Process Reward Modeling EMNLP 2025 Dense Dynamics-Aware Reward Synthesis: Integrating Prior Experience with Demonstrations L4DC 2025 Deterministic Policy Gradient Primal-Dual Methods for Continuous-Space Constrained MDPs AAAI 2025 Dexplore: Scalable Neural Control for Dexterous Manipulation from Reference Scoped Exploration CoRL 2025 DexTrack: Towards Generalizable Neural Tracking Control for Dexterous Manipulation from Human References ICLR 2025 DiaLLMs: EHR-Enhanced Clinical Conversational System for Clinical Test Recommendation and Diagnosis Prediction ACL 2025 Dialogue Is Not Enough to Make a Communicative BabyLM (But Neither Is Developmentally Inspired Reinforcement Learning) EMNLP 2025 Dialogue Systems for Emotional Support via Value Reinforcement ACL 2025 Diffusion Policy Policy Optimization ICLR 2025 Digi-Q: Learning VLM Q-Value Functions for Training Device-Control Agents ICLR 2025 DiMa: Understanding the Hardness of Online Matching Problems via Diffusion Models ICML 2025 Direct Repair Optimization: Training Small Language Models For Educational Program Repair Improves Feedback ACL 2025