X-Imitator is a bidirectional action-pose interaction framework for spatial-aware imitation learning that outperforms vanilla policies and explicit pose guidance on 24 simulated and 3 real-world robotic tasks.
arXiv preprint arXiv:2509.18676 (2025)
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
fields
cs.RO 5years
2026 5verdicts
UNVERDICTED 5roles
background 3polarities
background 3representative citing papers
Trajectory consistency training, smoothness regularization, and higher-order integration for flow matching policies deliver 60-70% success on long-horizon real-robot tasks where baselines achieve 0%.
ChronoFlow-Policy uses a unified ChronoFlow representation of past-current-future dynamics learned jointly with actions in a diffusion policy, outperforming baselines on 14 simulated and 5 real manipulation tasks.
Human2Any transfers human video demonstrations to robots by representing tasks as object-object interactions and composing learned priors with robot-side planning.
A survey that clarifies boundaries and organizes World Action Models by generation requirements and predictive substrates, identifying a trend toward generating less of the future.
citing papers explorer
-
X-Imitator: Spatial-Aware Imitation Learning via Bidirectional Action-Pose Interaction
X-Imitator is a bidirectional action-pose interaction framework for spatial-aware imitation learning that outperforms vanilla policies and explicit pose guidance on 24 simulated and 3 real-world robotic tasks.
-
Trajectory-Consistent Flow Matching for Robust Visuomotor Policy Learning
Trajectory consistency training, smoothness regularization, and higher-order integration for flow matching policies deliver 60-70% success on long-horizon real-robot tasks where baselines achieve 0%.
-
ChronoFlow-Policy: Unifying Past-Current-Future Interaction Flow in Visuomotor Policy Learning
ChronoFlow-Policy uses a unified ChronoFlow representation of past-current-future dynamics learned jointly with actions in a diffusion policy, outperforming baselines on 14 simulated and 5 real manipulation tasks.
-
Human2Any: Human-to-Robot Transfer via Constraint-Aware Compositional Planning
Human2Any transfers human video demonstrations to robots by representing tasks as object-object interactions and composing learned priors with robot-side planning.
-
World Action Models: A Survey
A survey that clarifies boundaries and organizes World Action Models by generation requirements and predictive substrates, identifying a trend toward generating less of the future.