AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

DynBridge: Bridging Imagination and Control through Interaction Dynamics for Robot Manipulation

Alex Wang, Zhiwei Dong, Qicheng Bai, Chenshi Zhang, Yujie Yi, Guang Dai, Yong Liu, Mengmeng Wang

CVPR 2026 · Image generation › Autoregressive and latent generation · approach: Diffusion planning and policies

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
train the interaction dynamics generator and action predictor jointly end-to-end instead of separately (ablation)DynBridge · LIBERO-Spatial, Goal, Longsuccess rateImproved
add trajectory reconstruction supervision alongside action imitation (ablation)DynBridge · LIBERO-Spatial, Goal, Longsuccess rateImproved
use latent interaction representation instead of explicit trajectory coordinates (ablation)DynBridge · LIBERO-Spatial, Goal, Longsuccess rateImproved
predict future trajectories (horizon L greater than 0) instead of none (ablation)DynBridge · LIBERO suitessuccess rateImproved
increase trajectory prediction horizon to a very long length (ablation)DynBridge · LIBERO suites, including LIBERO-Longsuccess rateHurt
add the action-conditioned dynamics aggregator across dynamic token counts 4, 8, 16, 32 (ablation)DynBridge · LIBEROsuccess rateImproved
increase number of dynamic tokens without aggregator (ablation)DynBridge w/o aggregator · LIBEROsuccess rateMixed
condition aggregator on action tokens rather than vision, language or learnable anchor (ablation)DynBridge aggregator · LIBERO-Spatial, Goal, Longsuccess rateImproved
add any aggregator conditioning (vision, language, learnable, action) versus none (ablation)DynBridge · LIBERO-Spatial, Goal, Longsuccess rateImproved
add interaction dynamics modeling for unseen goal positions (ablation)DynBridge · modified LIBERO-Goal, displaced targetssuccess rateImproved
add interaction dynamics modeling in real-world tasks (ablation)DynBridge · Franka Research 3, five real tasks, 10 trialssuccess rate: +22%Improved
transfer Panda-learned dynamics to XArm7 with imperfect demonstrationsDynBridge · XArm7 cross-robot transfersuccess rateImproved

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