1 citations · 1 across the 6 of their papers we have counts for
6 papers · 1 filter
FastOPD: On-Policy Distillation for Lightweight VLA Deployment
Yoojin Oh, Jeongsol Kim, Yeonwoo Seo +7
Vision-Language-Action (VLA) foundation models have scaled rapidly to enhance manipulation performance and generalizability, but this scaling incurs high computational costs that r…
DriftOPD: Sequence-Level Reverse-KL Distillation for One-Step VLA Policies
Youngjun Jun, Kyumin Choi, Youngmin Kim +4
Vision-Language-Action (VLA) models increasingly rely on action experts that generate short action chunks under receding-horizon control. While chunk-level training is convenient a…
Adjoint Guidance Flow: Amortized Critic Guidance for VLA Policies
Jeongsol Kim, Youngjun Jun, Kyumin Choi +6
Flow-based Vision-Language-Action (VLA) policies are typically trained by behavior cloning and thus do not explicitly optimize long-term task return. Critic guidance steers generat…
Don't Throw Away the Tail: Action Upcycling for Policy Acceleration
Taesung Kwon, Jangho Park, Sunwoo Park +5
Modern robot policies predict a chunk of future actions from a single observation, execute only a prefix, and discard the rest before replanning. Choosing the length of this prefix…
Physics in 2-Steps: Locking Motion Priors Before Visual Refinement Erases Them
Woojung Han, Seil Kang, Youngjun Jun +3
Image-to-Video diffusion models leverage input images to generate visually stunning content, yet frequently produce motion that violates physical laws. We reveal a surprising findi…
Interpretable Motion-Attentive Maps: Spatio-Temporally Localizing Concepts in Video Diffusion Transformers
Youngjun Jun, Seil Kang, Woojung Han +1
Video Diffusion Transformers (DiTs) have been synthesizing high-quality video with high fidelity from given text descriptions involving motion. However, understanding how Video DiT…