Reinforcement Learning

Rethinking the Role of Entropy in Optimizing Tool-Use Behaviors for Large Language Model Agents ACL 2026 REVISOR: Beyond Textual Reflection, Towards Multimodal Introspective Reasoning in Long-Form Video Understanding CVPR 2026 Right at My Level: A Unified Multilingual Framework for Proficiency-Aware Text Simplification ACL 2026 RollPacker: Taming Long-Tail Rollouts for RL Post-Training with Tail Batching NSDI 2026 SAMIX: Reinforcing SAM2 with Semantic Adapter and Reference Selecting Policy for Mix-Supervised Segmentation CVPR 2026 SAMTok: Representing Any Mask with Two Words CVPR 2026 SeCuRepair: Semantics-Aligned, Curriculum-Driven, and Reasoning-Enhanced Vulnerability Repair Framework ACL 2026 See Further, Think Deeper: Advancing VLM's Reasoning Ability with Low-level Visual Cues and Reflection CVPR 2026 Seeing is Improving: Visual Feedback for Iterative Text Layout Refinement CVPR 2026 Solve-Detect-Verify: Inference-Time Scaling with Flexible Generative Verifier ACL 2026 SpatialReward: Verifiable Spatial Reward Modeling for Fine-Grained Spatial Consistency in Text-to-Image Generation CVPR 2026 Specificity-aware reinforcement learning for fine-grained open-world classification CVPR 2026 Stable and Efficient Single-Rollout RL for Multimodal Reasoning CVPR 2026 Stepwise Credit Assignment for GRPO on Flow-Matching Models CVPR 2026 TA-GRPO-d: Trajectory-Aware GRPO for Optimizing Denoising Trajectories in Diffusion LLMs ACL 2026 Team TüLK at SemEval-2026 Task 1: Humor Generation with Qwen and Group Relative Policy Optimization SemEval 2026 TexOCR: Advancing Document OCR Models for Compilable Page-to-LaTeX Reconstruction ACL 2026 TextPecker: Rewarding Structural Anomaly Quantification for Enhancing Visual Text Rendering CVPR 2026 The olmOCR Project: Building Fully Open OCR using VLMs ACL 2026 ThinkGen: Generalized Thinking for Visual Generation CVPR 2026 Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual Generation CVPR 2026 Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning CVPR 2026 TInR: Exploring Tool-Internalized Reasoning in Large Language Models ACL 2026 ToolOmni: Enabling Open-World Tool Use via Agentic learning with Proactive Retrieval and Grounded Execution ACL 2026 Trajectory Tactics: When Transformers Learn Exploration to Generate Online Signature WACV 2026