ECCV 2026 accepted papers on Reinforcement learning
37 of the 2,834 papers accepted at ECCV 2026 (1.3%) are on Reinforcement learning, compared with 0.6% at ECCV 2024. They fall into 4 topics.
See ECCV 2026 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Visual and representation RL · 22 papers
- World Models for Learning Dexterous Hand-Object Interactions from Human Videos (48 citations)
- Persistent Robot World Models: Stabilizing Multi-Step Rollouts via Reinforcement Learning (13 citations)
- HiPolicy: Hierarchical Multi-Frequency Action Chunking for Policy Learning (10 citations)
- TIR-Agent: Training an Explorative and Efficient Agent for Image Restoration (7 citations)
- ConTrack: Constrained Hand Motion Tracking with Adaptive Trade-off Control (5 citations)
- UniBYD: A Unified Framework for Learning Robotic Manipulation Across Embodiments Beyond Imitation of Human Demonstrations (4 citations)
- What Matters in RL-Based Methods for Object-Goal Navigation? An Empirical Study and A Unified Framework (4 citations)
- CellFluxRL: Biologically-Constrained Virtual Cell Modeling via Reinforcement Learning (2 citations)
- Tac2Real: Reliable and GPU Visuotactile Simulation for Online Reinforcement Learning and Zero-shot Real-World Deployment (2 citations)
- ReconDreamer-RL: Enhancing Reinforcement Learning via Diffusion-based Reconstruction (1 citation)
- Boba: Batched Simulation for Physics-Based Gaussian Digital Twins
- Grasp-Oriented Non-Prehensile Manipulation via Learning a Graspability Field
and 10 more in the interactive map.
RL from feedback · 11 papers
- Distribution Matching Distillation Meets Reinforcement Learning (50 citations)
- Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models (9 citations)
- ReGRPO: Reflection-Augmented Policy Optimization for Tool-Using Agents (2 citations)
- Joint Alignment and Distillation for Video Generation via Sample-Guided Distribution Matching (1 citation)
- Policy-Based Tuning of Autoregressive Image Models with Instance- and Distribution-Level Rewards (1 citation)
- FlowLess: Controlling Abstract Image Generation
- GR-GRPO: Graph-Diffused Credit for Autoregressive Image RL Alignment
- On-Policy Diffusion Reinforcement Learning Meets Off-Policy Quality Anchoring
- REVA-PO: Stabilizing Reinforcement Learning for Chest X-ray Report Generation
- SupGRPO: Enhancing GRPO with Matching-based Online SFT for Text Spotting
- When Rubrics Fail: Error Enumeration as Reward for Reference-Free RL Post-Training
