Research map / Reinforcement learning / Visual and representation RL
Semore: VLM-guided Enhanced Semantic Motion Representations for Visual Reinforcement Learning
Wentao Wang, Chunyang Liu, Kehua Sheng, Bo Zhang, Yan Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace Simoun with Semore | Semore · CARLA JW | episode reward: 168 -> 201 | Improved |
| replace Simoun with Semore | Semore · CARLA HW | episode reward: 268 -> 316 | Improved |
| use Semore instead of Simoun on steering | Semore · CARLA JW | average steer (%): 13.69 -> 13.91 | Hurt |
| add motion stream decoupled from semantic stream (ablation) | Semore · CARLA HW | distance (m): 146 -> 203 | Improved |
| add VLM semantic supervision (ablation) | Semore · CARLA HW | distance (m): 203 -> 238 | Improved |
| add VLM semantic supervision (ablation) | Semore · CARLA JW | crash intensity: 2582 -> 2471 | Improved |
| add motion supervision and interaction (ablation) | Semore · CARLA JW | distance (m): 174 -> 233 | Improved |
| add motion supervision and interaction (ablation) | Semore · CARLA HB | crash intensity: 2549 -> 2418 | Improved |
Closest papers by meaning
- VLMs-Guided Representation Distillation for Efficient Vision-Based Reinforcement Learning (CVPR 2025 · similarity 0.90)
- COVR: Collaborative Optimization of VLMs and RL Agent for Visual-Based Control (AAAI 2026 · similarity 0.89)
- What Can RL Bring to VLA Generalization? An Empirical Study (NeurIPS 2025 · similarity 0.88)
- From Representational Complementarity to Dual Systems: Synergizing VLM and Vision-Only Backbones for End-to-End Driving (NeurIPS 2026 · similarity 0.88)
- GFlowVLM: Enhancing Multi-step Reasoning in Vision-Language Models with Generative Flow Networks (CVPR 2025 · similarity 0.87)
- PeRL: Permutation-Enhanced Reinforcement Learning for Interleaved Vision-Language Reasoning (NeurIPS 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
