Reinforcement Learning

Designing Instance-Level Sampling Schedules via REINFORCE with James-Stein Shrinkage CVPR 2026 DEVA: Fine-tuning Multimodal Large Language Models for Visual Perception Tasks CVPR 2026 Discriminative Perception via Anchored Description for Reasoning Segmentation CVPR 2026 Disentangling Reasoning Logic to Resolve Explicit Knowledge Conflicts ACL 2026 Do Less, Achieve More: Do We Need Every-Step Optimization for RL Fine-tuning of Diffusion Models? CVPR 2026 DRM: Diffusion-based Reward Model With Step-wise Guidance CVPR 2026 d-TreeRPO: Towards More Reliable Policy Optimization for Diffusion Language Models ACL 2026 Dual-Agent Reinforcement Learning for Adaptive and Cost-Aware Visual-Inertial Odometry CVPR 2026 Edges Compete for Trust: Group Relative Edge Optimization for Building Reconstruction from Point Clouds CVPR 2026 Efficiently Learning To Reason or Not to Reason: Root-token Policy Optimization for Adaptive Thinking ACL 2026 Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching CVPR 2026 Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization ACL 2026 Enhancing Reinforcement Learning for Radiology Report Generation with Evidence-aware Rewards and Self-correcting Preference Learning ACL 2026 Enhancing Spatial Understanding in Image Generation via Reward Modeling CVPR 2026 ETR: Entropy Trend Reward for Efficient Chain-of-Thought Reasoning ACL 2026 Evo-Attacker: Memory-Augmented Reinforcement Learning for Long-Horizon Tool Attacks on LLM-MAS ACL 2026 EvoID: Reinforced Evolution for Identity-Preserving Video Generation CVPR 2026 Evolutionary Guided Decoding: Iterative Value Refinement for LLMs ACL 2026 EvoRoute: Experience-Driven Self-Routing LLM Agent Systems ACL 2026 Expand and Prune: Maximizing Trajectory Diversity for Effective GRPO in Generative Models CVPR 2026 Fine-Grained GRPO for Precise Preference Alignment in Flow Models CVPR 2026 Flash-DMD: Towards High-Fidelity Few-Step Image Generation with Efficient Distillation and Joint Reinforcement Learning CVPR 2026 Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs ACL 2026 From "Aha Moments" to Controllable Thinking: Toward Meta-Cognitive Reasoning in LRMs via Decoupled Reasoning and Control ACL 2026 From Competition to Synergy: Unlocking Reinforcement Learning for Subject-Driven Image Generation ACL 2026