46 citations · 54 across the 13 of their papers we have counts for
5 papers · 1 filter
ACCRUE: Continual Off-Policy Reinforcement Learning for Robot Foundation Models
Changyeon Kim, Kimin Lee, Yashraj Narang +1
Reinforcement learning (RL) post-training improves robot foundation models (RFMs) beyond their demonstrations, but real-world deployment demands more: learning new tasks efficientl…
Q-Learning with Scalar Adjoint Matching
Yonghoon Dong, Minsung Yoon, Jaehyuk Kim +3
Flow policies capture rich and diverse action distributions, and fine-tuning them with off-policy RL to improve beyond the demonstrations has drawn growing interest. However, fine-…
Trust Region Q Adjoint Matching
Yonghoon Dong, Kyungmin Lee, Changyeon Kim +2
Off-policy reinforcement learning of pretrained flow policies remains challenging due to the instability of optimization arising from the multi-step sampling process. Recently, Q-l…
Learning Multi-View Spatial Reasoning from Cross-View Relations
Suchae Jeong, Jaehwi Song, Haeone Lee +9
Vision-language models (VLMs) have achieved impressive results on single-view vision tasks, but lack the multi-view spatial reasoning capabilities essential for embodied AI systems…
Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning
Huihan Liu, Changyeon Kim, Bo Liu +2
Continual learning is a long-standing challenge in robot policy learning, where a policy must acquire new skills over time without catastrophically forgetting previously learned on…