Research map / Vision-language and multimodal / Robot action and navigation
UniHM: Unified Dexterous Hand Manipulation with Vision Language Model
Zhenhao Zhang, Jiaxin Liu, Ye Shi, Jingya 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 MotionGPT3 with UniHM | MotionGPT3 · DexYCB seen | MPJPE: 74.80 -> 61.40 | Improved |
| Replace MotionGPT3 with UniHM | MotionGPT3 · OakInk unseen | FID: 272.69 -> 253.41 | Improved |
| Use RGB-D input instead of RGB only (ablation) | UniHM · DexYCB seen | MPJPE: 85.47 -> 61.40 | Improved |
| Add progressive masked training (ablation) | UniHM · DexYCB seen | MPJPE: 73.41 -> 61.40 | Improved |
| Add physics-guided refinement (ablation) | UniHM · DexYCB seen | MPJPE: 65.78 -> 61.40 | Improved |
| Add physics-guided refinement (ablation) | UniHM · DexYCB unseen | FID: 45.06 -> 41.03 | Improved |
| Add progressive masked training (ablation) | UniHM · DexYCB seen | Diversity: 73.09 -> 39.62 (GT 125.53) | Mixed |
| Use UniHM instead of MotionGPT3+Dex-Retargeting | MotionGPT3 · real-world Pick&Place (seen) | success rate: 15% -> 50% | Improved |
| Use UniHM instead of MotionGPT3+Dex-Retargeting | MotionGPT3 · real-world Pull&Push (unseen) | success rate: 15% -> 55% | 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.
- MotionGPT3 — MotionGPT: Human Motion as a Foreign Language (NeurIPS 2023) · better on 8 of 8 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
- Scaffolding Dexterous Manipulation with Vision-Language Models (NeurIPS 2025 · similarity 0.91)
- ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning (CVPR 2025 · similarity 0.89)
- Grasp as You Say: Language-guided Dexterous Grasp Generation (NeurIPS 2024 · similarity 0.89)
- UniGraspTransformer: Simplified Policy Distillation for Scalable Dexterous Robotic Grasping (CVPR 2025 · similarity 0.89)
- FlowHOI: Flow-based Semantics-Grounded Generation of Hand-Object Interactions for Dexterous Robot Manipulation (NeurIPS 2026 · similarity 0.89)
- HandEdit: A Unified Benchmark for Egocentric Human-to-Robot Dexterous Hand Image Editing (NeurIPS 2026 · similarity 0.88)
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.
