group relative policy optimization

Robust Tool Use via Fission-GRPO: Learning to Recover from Execution Errors ACL 2026 SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization CVPR 2026 Saliency-R1: Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment Reward CVPR 2026 Solve-Detect-Verify: Inference-Time Scaling with Flexible Generative Verifier ACL 2026 Step-GRPO: Enhancing Reasoning Quality and Efficiency via Structured PRM-Based Reinforcement Learning AAAI 2026 Stepwise Credit Assignment for GRPO on Flow-Matching Models CVPR 2026 Synthetic Curriculum Reinforces Compositional Text-to-Image Generation CVPR 2026 TableMix: Enhancing Multimodal Table Reasoning in MLLMs from a Data-Centric Perspective CVPR 2026 TA-GRPO-d: Trajectory-Aware GRPO for Optimizing Denoising Trajectories in Diffusion LLMs ACL 2026 Taming Extreme Tokens: Covariance-Aware GRPO with Gaussian-Kernel Advantage Reweighting ACL 2026 TAPO: Dynamic Teacher and Perturbed Answer Injection for Policy Optimization AAAI 2026 Team TüLK at SemEval-2026 Task 1: Humor Generation with Qwen and Group Relative Policy Optimization SemEval 2026 TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning CVPR 2026 TextShield-R1: Reinforced Reasoning for Tampered Text Detection AAAI 2026 Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning CVPR 2026 Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via sequence-level likelihood ACL 2026 Towards Faithful Industrial RAG: A Reinforced Co-adaptation Framework for Advertising QA ACL 2026 Training One Model to Master Cross-Level Agentic Actions via Reinforcement Learning CVPR 2026 TRivia: Self-supervised Fine-tuning of Vision-Language Models for Table Recognition CVPR 2026 TTRV: Test-Time Reinforcement Learning for Vision Language Models CVPR 2026 UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning AAAI 2026 UniMo: Unified Motion Generation and Understanding with Chain of Thought AAAI 2026 UNO! UNified Offline Training Paradigm for Learning Path Recommendation AAAI 2026 URPO: A Unified Reward & Policy Optimization Framework for Large Language Models AAAI 2026 VAR RL Done Right: Tackling Asynchronous Policy Conflicts in Visual Autoregressive Generation CVPR 2026