← Back to all news
arXiv AI By Youngjun Jun, Kyumin Choi, Youngmin Kim, Seonghyun Jin, Sunwoo Park, Jangho Park, Jong Chul Ye

DriftOPD: Sequence-Level Reverse-KL Distillation for One-Step VLA Policies

Read the original on arXiv AI →

DriftOPD is a teacher‑free, rollout‑free framework that performs sequence‑level on‑policy distillation of continuous Vision‑Language‑Action (VLA) action experts. It decomposes the sequence‑level reverse‑KL divergence into a chunk‑level reverse‑KL term and a future‑potential term, optimizing them with a one‑step drifting objective and a Q‑function critic learned from offline demonstrations. Experiments on multiple VLA architectures in simulation and real‑world manipulation show that DriftOPD outperforms existing one‑step distillation baselines while matching the task success of multi‑step teacher policies.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Aug 19

Q-Learning With World Models

The paper introduces QWM, a framework that integrates world models with standard Q‑learning to perform test‑time search over imagined trajectories. By training the policy and value function solely on real transitions, QWM avoids compounding model bias while still benefiting from predictive search. Experiments on the Robomimic and LIBERO manipulation benchmarks show that QWM outperforms strong prior state‑of‑the‑art methods in both sample efficiency and performance.

By Perry Dong, Yueru Jia, Chelsea Finn, Dorsa Sadigh
reinforcement-learningroboticsfine-tuningmultimodalbenchmarkssafety
More like this →
arXiv AI
Jun 11

Vision-Language-Action Jump-Starting for Reinforcement Learning Robotic Agents

arXiv:2604. 13733v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) enables high-frequency, closed-loop control for robotic manipulation, but scaling to long-horizon tasks with sparse or imperfect rewards remains difficult due to inefficient exploration and poor credit assignment.

By Angelo Moroncelli, Roberto Zanetti, Marco Maccarini, Loris Roveda
agentsreinforcement-learningroboticsefficiencymultimodalsafety
More like this →
arXiv AI
Sep 18

HIL-UMI: Bringing Human-in-the-Loop Post-Training of Vision-Language-Action Models to Universal Manipulation Interface

HIL-UMI is a policy-guided Universal Manipulation Interface that enables robot‑free, human‑in‑the‑loop post‑training of vision‑language‑action models. By querying the current policy during handheld demonstrations and using an Energy Score to detect out‑of‑distribution states, it selectively collects new data and refines a progress‑based advantage estimator. The updated estimator then drives advantage‑conditioned behavioral cloning, improving performance on long‑horizon and precise manipulation tasks while reducing per‑frame collection time compared to HG‑DAgger.

By Zimu Han, Yiming Zeng, Jiyao Zhang, Zihao Zhao, Yuanfei Wang, Yixiang Jin, Shiqi Li, Shuangben Chen, Wei Huang, Ruodai Li, Hui Shen, Hao Dong
roboticsfine-tuningmultimodal
More like this →
arXiv AI
Sep 24

BEE: Intervention-Adaptive Real-World Reinforcement Learning with Vision-Language-Action Models

arXiv:2609.27450v1 Announce Type: cross Abstract: Vision-language-action (VLA) models handle long-horizon manipulation, yet success hinges on a few precision-critical phases where millimeter-scale er...

By Weihui Zhao, Xiaohan Yan, Zunian Wan, Xuan Du, Zhaozhan Chi, Jianbo Mao, Ruipu Wu, Rushuai Yang, Houlin Li, Shukai Yang, Jing Wu, Yuxiang Yan, Yongcheng Liu, Chuankang Li, Guanghui Ren, Wei Shan, Maoqing Yao
reinforcement-learningroboticsmultimodal
More like this →