Reinforcement Learning

Learning to Reason with Curriculum I: Provable Benefits of Autocurriculum COLT 2026 Learning to Refuse: Refusal-Aware Reinforcement Fine-Tuning for Hard-Irrelevant Queries in Video Temporal Grounding CVPR 2026 Learning What Helps: Task-Aligned Context Selection for Vision Tasks CVPR 2026 MASC: Metal-Aware Sampling and Correction via Reinforcement Learning for Accelerated MRI MIDL 2026 MaskAdapt: Learning Flexible Motion Adaptation via Mask-Invariant Prior for Physics-Based Characters CVPR 2026 Masked Auto-Regressive Variational Acceleration: Fast Inference Makes Practical Reinforcement Learning CVPR 2026 MaskFocus: Focusing Policy Optimization on Critical Steps for Masked Image Generation CVPR 2026 MedLoc-R1: Performance-Aware Curriculum Reward Scheduling for GRPO-Based Medical Visual Grounding CVPR 2026 Mesh-Pro: Asynchronous Advantage-guided Ranking Preference Optimization for Artist-style Quadrilateral Mesh Generation CVPR 2026 Mimic Human Cognition, Master Multi-Image Reasoning: A Meta-Action Framework for Enhanced Visual Understanding CVPR 2026 MindDriver: Introducing Progressive Multimodal Reasoning for Autonomous Driving CVPR 2026 Mitigating Selection Bias in Large Language Models via Permutation-Aware GRPO ACL 2026 MoCha: End-to-End Video Character Replacement without Structural Guidance CVPR 2026 Monet: Reasoning in Latent Visual Space Beyond Image and Language CVPR 2026 MT3: A Synergistic Multi-Task RL Framework for Specializing MLLMs in Text Image Machine Translation ACL 2026 Multi-Task Reinforcement Learning for Enhanced Multimodal LLM-as-a-Judge ACL 2026 MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding ACL 2026 MuSe: Multi-Stage Graph Reasoning via Vision-Language Models ACL 2026 NeoAMT: Neologism-Aware Agentic Machine Translation with Reinforcement Learning ACL 2026 NS-Diff: Fluid Navier-Stokes Guided Video Diffusion via Reinforcement Learning CVPR 2026 OmniOData: Unleashing Small Language Models for OData Query Generation with Synthetic Data and Reinforcement Learning ACL 2026 Optimizing Length Compression in Large Reasoning Models ACL 2026 OraPO: Oracle-educated Reinforcement Learning for Data-efficient and Factual Radiology Report Generation CVPR 2026 OS-Oracle: A Comprehensive Framework for Cross-Platform GUI Critic Models CVPR 2026 ParaUni: Enhance Generation in Unified Multimodal Model with Reinforcement-driven Hierarchical Parallel Information Interaction CVPR 2026