Research map / Reinforcement learning / Visual and representation RL
AdaDexTrack: Dynamic Modulation for Adaptive and Generalizable Dexterous Manipulation Tracking
Jianibieke Adalibieke, Qianwei Han, Xueyi Liu, Yuzhe Qin, Li Yi
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 the in-loop modulator (R+O+T) to the general tracker (ablation) | AdaDexTrack · Unseen Trajectory (sim) | success rate (mean-error): 62.20 -> 88.99 | Improved |
| add the modulator (R+O+T) to the general tracker (ablation) | AdaDexTrack · Unseen Object (sim) | success rate (mean-error): 24.08 -> 46.12 | Improved |
| add reference modulation (R) to the general tracker (ablation) | AdaDexTrack · Unseen Trajectory (sim) | success rate (mean-error): 62.20 -> 67.09 | Improved |
| add positional target modulation (T) on top of R (ablation) | AdaDexTrack · Unseen Trajectory (sim) | success rate (mean-error): 67.09 -> 84.45 | Improved |
| add object latent modulation (O) on top of R+T (ablation) | AdaDexTrack · Unseen Trajectory (sim) | success rate (completion): 80.42 -> 77.92 | Mixed |
| add object latent modulation (O) on top of R+T (ablation) | AdaDexTrack · Unseen Object (sim) | success rate (mean-error): 37.55 -> 46.12 | Improved |
| add reference modulation (R) alone to the general tracker (ablation) | AdaDexTrack · Unseen Object (sim) | success rate (mean-error): 24.08 -> 25.71 | Improved |
| add the modulator at zero-shot sim-to-real (ablation) | AdaDexTrack · Real-world Unseen Trajectory | completion rate: 26.63% -> 52.36% | Improved |
| add the modulator at zero-shot sim-to-real (ablation) | AdaDexTrack · Real-world Unseen Object | completion rate: 22.27% -> 36.71% | Improved |
| remove grip tape from objects in real world | AdaDexTrack · Real-world Unseen Trajectory | completion rate: 52.36% -> 65.71% | Improved |
| use partial single-view point cloud instead of ground-truth geometry | AdaDexTrack · Real-world no tape, Unseen Trajectory | completion rate: 65.71% -> 49.46% | Hurt |
| use reconstructed point cloud instead of ground-truth geometry | AdaDexTrack · Real-world no tape, Unseen Object | completion rate: 32.50% -> 34.73% | No clear effect |
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.
- DexTrack — DexTrack: Towards Generalizable Neural Tracking Control for Dexterous Manipulation from Human References (ICLR 2025) · better on 4 of 4 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
- DexTrack: Towards Generalizable Neural Tracking Control for Dexterous Manipulation from Human References (ICLR 2025 · similarity 0.91)
- DexHandDiff: Interaction-aware Diffusion Planning for Adaptive Dexterous Manipulation (CVPR 2025 · similarity 0.89)
- Scaffolding Dexterous Manipulation with Vision-Language Models (NeurIPS 2025 · similarity 0.88)
- ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning (CVPR 2025 · similarity 0.87)
- Object-Centric Prompt-Driven Vision-Language-Action Model for Robotic Manipulation (CVPR 2025 · similarity 0.87)
- Exploring the Limits of Vision-Language-Action Manipulation in Cross-task Generalization (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.
