Research map / Vision-language and multimodal / Robot action and navigation
Learning to Grasp Anything By Playing with Random Toys
Dantong Niu, Yuvan Sharma, Baifeng Shi, Rachel Ding, Matteo Gioia, Haoru Xue, Henry Tsai, Konstantinos Kallidromitis, Anirudh Pai, S. Shankar Sastry, Trevor Darrell, Jitendra Malik and 1 more
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 detection pooling instead of attention pooling (ablation) | LEGO · ManiSkill zero-shot grasping on YCB (65 objects), 2500 demos | success rate (%): 51.63 -> 80.00 | Improved |
| use detection pooling instead of CLS pooling (ablation) | LEGO · ManiSkill zero-shot grasping on YCB (65 objects), 2500 demos | success rate (%): 49.81 -> 80.00 | Improved |
| use detection pooling instead of mean pooling (ablation) | LEGO · ManiSkill zero-shot grasping on YCB (65 objects), 2500 demos | success rate (%): 40.58 -> 80.00 | Improved |
| use absolute joint control instead of delta control (ablation) | LEGO · ManiSkill zero-shot grasping on YCB (65 objects), 2500 demos | success rate (%): 37.02 -> 80.00 | Improved |
| train on toys with four colors instead of red only (ablation) | LEGO · ManiSkill zero-shot grasping on YCB (65 objects), 2500 demos | success rate (%): 76.35 -> 80 | Improved |
| include sphere primitives in toys (ablation) | LEGO · ManiSkill grasping, primitive removed from toys, 1000 demos | success rate (%): 63.08 -> 72.12 | Improved |
| include ring primitives in toys (ablation) | LEGO · ManiSkill grasping, primitive removed from toys, 200 demos | success rate (%): 72.6 -> 72.12 | No clear effect |
| train on two-primitive toys rather than five-primitive toys (ablation) | LEGO · ManiSkill grasping, toy complexity (250 demos) | success rate (%): 10.19 -> 44.42 | Improved |
| increase condition length c from 4 to 16 (ablation) | LEGO · ManiSkill zero-shot grasping on YCB (65 objects), 2500 demos | success rate (%): 54.30 -> 80.00 | Improved |
| increase prediction length k from 4 to 16 (ablation) | LEGO · ManiSkill zero-shot grasping on YCB (65 objects), 2500 demos | success rate (%): 70.67 -> 80.00 | Improved |
| increase prediction length k from 4 to 16 (ablation) | LEGO · ManiSkill zero-shot grasping on YCB (65 objects), 250 demos | success rate (%): 63.65 -> 56.63 | Hurt |
| scale policy transformer from ViT-Base (86M) to ViT-Large (307M) (ablation) | LEGO · ManiSkill zero-shot grasping on YCB (65 objects) | success rate (%) | No clear effect |
Closest papers by meaning
- Data Scaling Laws in Imitation Learning for Robotic Manipulation (ICLR 2025 · similarity 0.89)
- Generalizing 6-DoF Grasp Detection via Domain Prior Knowledge (CVPR 2024 · similarity 0.88)
- Entity-Centric Reinforcement Learning for Object Manipulation from Pixels (ICLR 2024 · similarity 0.87)
- Zero-Shot Robotic Manipulation with Pre-Trained Image-Editing Diffusion Models (ICLR 2024 · similarity 0.87)
- AffordDP: Generalizable Diffusion Policy with Transferable Affordance (CVPR 2025 · similarity 0.86)
- Contact Map Transfer with Conditional Diffusion Model for Generalizable Dexterous Grasp Generation (NeurIPS 2025 · similarity 0.86)
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.
