Research map / Image generation / Autoregressive and latent generation
MaskDexGrasp: Generative Masked Modeling for Part-Aware Dexterous Grasp Synthesis
Binghui Zuo, Lin Zhou, Haoxuan Xu, Jianan Yan, Zhipeng Yu, Zekai Liu, Yangang 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 part-aware tokenizer instead of vanilla VQ-VAE (ablation) | MaskDexGrasp · TDG Subset 2 | Success rate (%): 50.63 -> 75.16 | Improved |
| use part-aware tokenizer instead of vanilla VQ-VAE (ablation) | MaskDexGrasp · TDG Subset 1 | Success rate (%): 32.55 -> 44.68 | Improved |
| enlarge codebook from 128x256 to 256x512 (ablation) | MaskDexGrasp · TDG Subset 2 | Success rate (%): 61.64 -> 75.16 | Improved |
| enlarge codebook from 256x512 to 512x1024 (ablation) | MaskDexGrasp · TDG Subset 2 | Success rate (%): 75.16 -> 72.57 | No clear effect |
| increase inference iterations beyond default (ablation) | MaskDexGrasp · TDG Subset 2 | Success rate (%): 74.47 -> 74.66 -> 75.16 | No clear effect |
| replace diffusion baselines with masked-token sampling | MaskDexGrasp · TDG | Inference time (s): 4.417 -> 0.033 | Improved |
| replace DexGraspAnything with MaskDexGrasp | DexGraspAnything · TDG Subset 2 | Success rate (%): 58.90 -> 75.16 | Improved |
| replace DexGraspAnything with MaskDexGrasp | DexGraspAnything · TDG Subset 1 | Success rate (%): 46.54 -> 44.68 | Hurt |
| replace DexGraspAnything with MaskDexGrasp | DexGraspAnything · TDG Subset 2 | Hstd: 0.253 -> 0.406 | Hurt |
Closest papers by meaning
- UniGraspTransformer: Simplified Policy Distillation for Scalable Dexterous Robotic Grasping (CVPR 2025 · similarity 0.88)
- Grasp as You Say: Language-guided Dexterous Grasp Generation (NeurIPS 2024 · similarity 0.87)
- Dexterous Grasp Transformer (CVPR 2024 · similarity 0.87)
- Contact Map Transfer with Conditional Diffusion Model for Generalizable Dexterous Grasp Generation (NeurIPS 2025 · similarity 0.87)
- Grasp2Grasp: Vision-Based Dexterous Grasp Translation via Schrödinger Bridges (NeurIPS 2025 · similarity 0.87)
- DexGrasp Anything: Towards Universal Robotic Dexterous Grasping with Physics Awareness (CVPR 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.
