AI Paper Atlas

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

CVPR 2026 · Reinforcement learning › Visual and representation RL · approach: Dexterous manipulation transfer · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
add the in-loop modulator (R+O+T) to the general tracker (ablation)AdaDexTrack · Unseen Trajectory (sim)success rate (mean-error): 62.20 -> 88.99Improved
add the modulator (R+O+T) to the general tracker (ablation)AdaDexTrack · Unseen Object (sim)success rate (mean-error): 24.08 -> 46.12Improved
add reference modulation (R) to the general tracker (ablation)AdaDexTrack · Unseen Trajectory (sim)success rate (mean-error): 62.20 -> 67.09Improved
add positional target modulation (T) on top of R (ablation)AdaDexTrack · Unseen Trajectory (sim)success rate (mean-error): 67.09 -> 84.45Improved
add object latent modulation (O) on top of R+T (ablation)AdaDexTrack · Unseen Trajectory (sim)success rate (completion): 80.42 -> 77.92Mixed
add object latent modulation (O) on top of R+T (ablation)AdaDexTrack · Unseen Object (sim)success rate (mean-error): 37.55 -> 46.12Improved
add reference modulation (R) alone to the general tracker (ablation)AdaDexTrack · Unseen Object (sim)success rate (mean-error): 24.08 -> 25.71Improved
add the modulator at zero-shot sim-to-real (ablation)AdaDexTrack · Real-world Unseen Trajectorycompletion rate: 26.63% -> 52.36%Improved
add the modulator at zero-shot sim-to-real (ablation)AdaDexTrack · Real-world Unseen Objectcompletion rate: 22.27% -> 36.71%Improved
remove grip tape from objects in real worldAdaDexTrack · Real-world Unseen Trajectorycompletion rate: 52.36% -> 65.71%Improved
use partial single-view point cloud instead of ground-truth geometryAdaDexTrack · Real-world no tape, Unseen Trajectorycompletion rate: 65.71% -> 49.46%Hurt
use reconstructed point cloud instead of ground-truth geometryAdaDexTrack · Real-world no tape, Unseen Objectcompletion 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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy