Research map / Vision-language and multimodal / Robot action and navigation
AffordDexGrasp: Open-set Language-guided Dexterous Grasp with Generalizable-Instructive Affordance
Yi-Lin Wei, Mu Lin, Yuhao Lin, Jian-Jian Jiang, Xiao-Ming Wu, Ling-An Zeng, Wei-Shi Zheng
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 generalizable-instructive affordance (ablation) | AffordDexGrasp · Open Set A | R-Precision Top1: 0.369 -> 0.480 | Improved |
| add generalizable-instructive affordance (ablation) | AffordDexGrasp · Open Set B | FID: 0.322 -> 0.176 | Improved |
| use our affordance instead of predicted object part (ablation) | AffordDexGrasp · Open Set A | FID: 0.313 -> 0.242 | Improved |
| use our affordance instead of predicted contact map (ablation) | AffordDexGrasp · Open Set B | CD: 3.25 -> 2.76 | Improved |
| use ground-truth contact map instead of our predicted affordance (ablation) | AffordDexGrasp · Open Set A | FID: 0.242 -> 0.113 | Mixed |
| add key cues extraction by MLLM (ablation) | AffordDexGrasp · Open Set A | R-Precision Top1: 0.463 -> 0.480 | Improved |
| add grasp direction cue (ablation) | AffordDexGrasp · Open Set A | R-Precision Top1: 0.432 -> 0.480 | Improved |
| use flow matching instead of DDIM (ablation) | AffordDexGrasp · Open Set B | FID: 0.211 -> 0.176 | Improved |
| use flow matching instead of DDPM (ablation) | AffordDexGrasp · Open Set B | FID: 0.204 -> 0.176 | Improved |
| use flow matching (AFM+GFM) for faster inference than DDPM (ablation) | AffordDexGrasp · time per sample | seconds: 1.14 -> 0.233 | Improved |
| add affordance-guided optimization (ablation) | AffordDexGrasp · Open Set A | Pen.: 0.501 -> 0.293 | Improved |
| add affordance-guided optimization (ablation) | AffordDexGrasp · Open Set A | Q1: 0.0240 -> 0.0531 | Improved |
Closest papers by meaning
- RAGNet: Large-scale Reasoning-based Affordance Segmentation Benchmark towards General Grasping (ICCV 2025 · similarity 0.92)
- Towards Affordance-Aware Robotic Dexterous Grasping with Human-like Priors (AAAI 2026 · similarity 0.91)
- Grasp as You Say: Language-guided Dexterous Grasp Generation (NeurIPS 2024 · similarity 0.91)
- AffordDP: Generalizable Diffusion Policy with Transferable Affordance (CVPR 2025 · similarity 0.89)
- OpenHOI: Open-World Hand-Object Interaction Synthesis with Multimodal Large Language Model (NeurIPS 2025 · similarity 0.88)
- RealVLG-R1: A Large-Scale Real-World Visual-Language Grounding Benchmark for Robotic Perception and Manipulation (CVPR 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.
