Research map / Vision-language and multimodal / Robot action and navigation
QUAR-VLA: Vision-Language-Action Model for Quadruped Robots
Pengxiang Ding, Han Zhao, Wenjie Zhang, Wenxuan Song, Min Zhang, Siteng Huang, Ningxi Yang, Donglin 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 |
|---|---|---|---|
| use a VLA with a pretrained multimodal LLM instead of a visual encoder plus policy head | QUART vs VC-1/CLIP · QUARD Crawl | success rate: 0 -> 0.32 | Improved |
| add more simulated data to co-training with 3K real samples (ablation) | QUART · Real-world Go to | success (trials): 3/20 -> 13/20 | Improved |
| replace MLP policy head with decoder-only transformer on a VLM baseline (ablation) | Aligned VLM+P · QUARD seen tasks | success rate: Go to 0.43 -> 0.15; Crawl 0 -> 0 | No clear effect |
| swap Fuyu-8B backbone for LLaVa-7B (ablation) | QUART · QUARD seen tasks | success rate: Go to 0.60 -> 0.52; Unload 0.12 -> 0.16 | Mixed |
| multi-task training instead of single-task training (ablation) | QUART · QUARD seen tasks | success rate: Go avoid 0.19 -> 0.53; Crawl 0.25 -> 0.32 | Improved |
| multi-task instead of single-task training for baseline on Distinguish (ablation) | VC-1 · QUARD Distinguish | success rate: 0.70 -> 0.46 | Hurt |
| use pretrained MLLM for unseen verbal instructions | QUART · QUARD unseen verbal | success rate: VC-1 0.19 -> 0.33; R3M 0 -> 0.33 | Improved |
| use unaligned vision encoder (R3M) without language alignment | R3M baseline · QUARD seen tasks | success rate: Go to 0.58 on distinguish, 0 elsewhere | Hurt |
| switch navigation planner from D* to A* for data collection | QUARD simulation data · data quality | path quality | Improved |
Closest papers by meaning
- CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models (CVPR 2025 · similarity 0.89)
- XR-1: Towards Versatile Vision-Language-Action Models via Learning Unified Vision-Motion Representations (ICML 2026 · similarity 0.89)
- ChatVLA-2: Vision-Language-Action Model with Open-World Reasoning (NeurIPS 2025 · similarity 0.89)
- FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies (NeurIPS 2026 · similarity 0.88)
- ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models (NeurIPS 2026 · similarity 0.88)
- Beyond Data Scaling: Representation-Centric Pre-training for Vision-Language-Action Models (NeurIPS 2026 · 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.
