From the 1 of 12 linked papers with an AI index.
12 papers
Critic-Free Pretraining for Efficient Online Reinforcement Learning Fine-Tuning
Daoyi Li, Yixian Zhang, Chao Yu +2
Offline-to-online (O2O) reinforcement learning aims to leverage policies pretrained on static datasets while improving them through online interaction. However, directly reusing an…
Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agents
Yixian Zhang, Huanming Zhang, Feng Gao +13
The paper introduces Harness VLA, a memory-augmented framework that combines a frozen vision‑language‑action model with a small set of analytic manipulation primitives to improve r…
STEAM: Self-Supervised Temporal Ensemble Advantage Modeling for Real-World Robot Learning
Zhihao Liu, Qiuyi Gu, Yitao Wang +16
Real-world robot learning increasingly relies on heterogeneous data, but demonstrations and rollouts often mix useful progress with stalls, corrections, and suboptimal behavior. Ef…
WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL
Zhennan Jiang, Shangqing Zhou, Yutong Jiang +11
Reinforcement learning (RL) promises to unlock capabilities beyond imitation learning for Vision--Language--Action (VLA) models, but its requirement for massive real-world interact…
Beyond Imitation: Reinforcement Learning-Based Sim-Real Co-Training for VLA Models
Liangzhi Shi, Shuaihang Chen, Feng Gao +8
Simulation offers a scalable and low-cost way to enrich vision-language-action (VLA) training, reducing reliance on expensive real-robot demonstrations. However, most sim-real co-t…
StreamingVLA: Streaming Vision-Language-Action Model with Action Flow Matching and Adaptive Early Observation
Yiran Shi, Dongqi Guo, Tianchen Zhao +8
Vision-language-action (VLA) models have demonstrated exceptional performance in natural language-driven perception and control. However, the high computational cost of VLA models…