ICCV 2025 accepted papers on Reinforcement learning
20 of the 2,701 papers accepted at ICCV 2025 (0.7%) are on Reinforcement learning, compared with 0.5% at ICCV 2023. They fall into 4 topics.
See ICCV 2025 in the interactive map
Submitting to ICCV? Checklist →
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 · 15 papers
- Human-Object Interaction from Human-Level Instructions (42 citations)
- CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Prediction (28 citations)
- DyWA: Dynamics-adaptive World Action Model for Generalizable Non-prehensile Manipulation (22 citations)
- Rethinking Bimanual Robotic Manipulation: Learning with Decoupled Interaction Framework (16 citations)
- DexH2R: A Benchmark for Dynamic Dexterous Grasping in Human-to-Robot Handover (13 citations)
- Medical World Model (10 citations)
- ModSkill: Physical Character Skill Modularization (7 citations)
- PROGRESSOR: A Perceptually Guided Reward Estimator with Self-Supervised Online Refinement (6 citations)
- Reinforcement Learning-Guided Data Selection via Redundancy Assessment (5 citations)
- Active Perception Meets Rule-Guided RL: A Two-Phase Approach for Precise Object Navigation in Complex Environments (3 citations)
- Disentangled World Models: Learning to Transfer Semantic Knowledge from Distracting Videos for Reinforcement Learning (3 citations)
- GeoExplorer: Active Geo-localization with Curiosity-Driven Exploration (2 citations)
and 3 more in the interactive map.
