Research map / Vision-language and multimodal / Robot action and navigation
VLBiMan: Vision-Language Anchored One-Shot Demonstration Enables Generalizable Bimanual Robotic Manipulation
Huayi Zhou, Kui Jia
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 Florence-2 + SAM2 instead of SAM+DINOv2 for perception (ablation) | VLBiMan · Six basic tasks, novel instances, with interference | average success rate (%): 35.8% -> 59.2% | Improved |
| use the proposed initial grasp alignment instead of AnyGrasp (ablation) | VLBiMan · Six basic tasks, novel instances, with interference | average success rate (%): 31.7% -> 59.2% | Improved |
| add progressive IK refinement (ablation) | VLBiMan · Six basic tasks, novel instances, with interference | average success rate (%): 29.2% -> 59.2% | Improved |
| add dynamic collision compensation (ablation) | VLBiMan · Six basic tasks, novel instances, with interference | average success rate (%): 34.2% -> 59.2% | Improved |
| inject oracle initial grasp label into ReKep (ReKep+) | ReKep · Six basic tasks, same objects, no interference | average success rate (%): 43.3% -> 63.3% | Improved |
| add external dynamic interference during execution | VLBiMan · Six basic tasks, novel instances | average success rate (%): 78.0% -> 59.3% | Hurt |
| replace same objects with novel category-level instances | VLBiMan · Six basic tasks, no interference | average success rate (%): 85.3% -> 78.0% | Hurt |
| move from basic tasks to long-horizon tasks | VLBiMan · same objects, no interference | average success rate (%): 85.3% -> 52.0% | Hurt |
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.
- MAGIC — MAGIC: Multimodal relAtional Graph adversarIal inferenCe for Diverse and Unpaired Text-Based Image Captioning (AAAI 2022) · better on 3 of 3 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
- Programmatically Grounded, Compositionally Generalizable Robotic Manipulation (ICLR 2023 · similarity 0.91)
- TwinVLA: Data-Efficient Bimanual Manipulation with Twin Single-Arm Vision-Language-Action Models (ICLR 2026 · similarity 0.91)
- Exploring the Limits of Vision-Language-Action Manipulation in Cross-task Generalization (NeurIPS 2025 · similarity 0.90)
- VLMimic: Vision Language Models are Visual Imitation Learner for Fine-grained Actions (NeurIPS 2024 · similarity 0.90)
- Object-Centric Prompt-Driven Vision-Language-Action Model for Robotic Manipulation (CVPR 2025 · similarity 0.89)
- PriorVLA: Prior-Preserving Adaptation for Vision-Language-Action Models (NeurIPS 2026 · similarity 0.89)
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.
