Research map / Vision-language and multimodal / Robot action and navigation
VLA-R1: Enhancing Reasoning in Vision-Language-Action Models
Angen Ye, Zeyu Zhang, Boyuan Wang, Xiaofeng Wang, Dapeng Zhang, Zheng Zhu
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 |
|---|---|---|---|
| add chain-of-thought SFT (ablation) | VLA-R1 · In-domain affordance | IoU: 23.74 -> 28.37 | Improved |
| add chain-of-thought SFT (ablation) | VLA-R1 · In-domain trajectory | Avg distance: 128.38 -> 124.6 | Improved |
| add RLVR (GRPO) after CoT SFT (ablation) | VLA-R1 · In-domain affordance | IoU: 28.37 -> 36.51 | Improved |
| add RLVR (GRPO) after CoT SFT (ablation) | VLA-R1 · In-domain trajectory | Avg distance: 124.60 -> 91.74 | Improved |
| VLA-R1 versus ManipLVM-R1 baseline | VLA-R1-3B · In-domain affordance | IoU: 31.00 -> 36.51 (~17.78%) | Improved |
| VLA-R1 versus ManipLVM-R1 baseline | VLA-R1-3B · In-domain trajectory | Avg distance: 110.87 -> 91.74 (~17.25% reduction) | Improved |
| VLA-R1 versus ManipLVM-R1 baseline | VLA-R1-3B · Out-of-domain affordance | IoU: 28.00 -> 33.96 | Improved |
| VLA-R1 versus ManipLVM-R1 baseline | VLA-R1-3B · Out-of-domain trajectory | Avg distance: 131.99 -> 93.90 | Improved |
| VLA-R1 versus NORA in simulation | VLA-R1 · Simulation trajectory | success rate: 5% -> 70% | Improved |
| VLA-R1 versus NORA in simulation | VLA-R1 · Simulation affordance | success rate: 40% -> 55% | Improved |
| VLA-R1 versus NORA in real world | VLA-R1 · Real-world affordance | success rate: 35% -> 62.5% | Improved |
| VLA-R1 versus NORA in real world | VLA-R1 · Real-world trajectory | success rate: 47.5% -> 75% | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- RoboBrain-7B — RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete (CVPR 2025) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models (NeurIPS 2026 · similarity 0.94)
- NS-VLA: Towards Neuro-Symbolic Vision-Language-Action Models (NeurIPS 2026 · similarity 0.93)
- EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models (NeurIPS 2025 · similarity 0.93)
- VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching (NeurIPS 2025 · similarity 0.92)
- CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models (CVPR 2025 · similarity 0.92)
- VLA-REPLICA: A Low-Cost, Reproducible Benchmark for Real-World Evaluation of Vision-Language-Action Models (NeurIPS 2026 · similarity 0.92)
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.
