Optimizing a single constant initial noise vector for frozen generative robot policies improves success rates on 38 of 43 tasks by up to 58% relative improvement.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
background 1representative citing papers
TouchGuide improves contact-rich robot manipulation by steering diffusion or flow-matching visuomotor policies with tactile feasibility scores from a contrastively trained Contact Physical Model.
Conflict-Aware Additive Guidance (g^car) is a lightweight learnable method that dynamically resolves gradient conflicts to prevent off-manifold drift in compositional guided sampling for flow models.
Feedback world model closes the prediction-observation loop at inference time to correct errors and improve diffusion policy performance under distribution shift in robotics.
DeLock mitigates lock-in in low-data VLA post-training via visual grounding preservation and test-time contrastive prompt guidance, outperforming baselines across eight evaluations while matching data-heavy generalist policies.
citing papers explorer
-
You've Got a Golden Ticket: Improving Generative Robot Policies With A Single Noise Vector
Optimizing a single constant initial noise vector for frozen generative robot policies improves success rates on 38 of 43 tasks by up to 58% relative improvement.
-
TouchGuide: Inference-Time Steering of Visuomotor Policies via Touch Guidance
TouchGuide improves contact-rich robot manipulation by steering diffusion or flow-matching visuomotor policies with tactile feasibility scores from a contrastively trained Contact Physical Model.
-
Conflict-Aware Additive Guidance for Flow Models under Compositional Rewards
Conflict-Aware Additive Guidance (g^car) is a lightweight learnable method that dynamically resolves gradient conflicts to prevent off-manifold drift in compositional guided sampling for flow models.
-
Feedback World Model Enables Precise Guidance of Diffusion Policy
Feedback world model closes the prediction-observation loop at inference time to correct errors and improve diffusion policy performance under distribution shift in robotics.
-
Breaking Lock-In: Preserving Steerability under Low-Data VLA Post-Training
DeLock mitigates lock-in in low-data VLA post-training via visual grounding preservation and test-time contrastive prompt guidance, outperforming baselines across eight evaluations while matching data-heavy generalist policies.