8 papers
Kimi K3: Open Frontier Intelligence
Kimi Team, Tongtong Bai, Yifan Bai +398
We introduce Kimi K3, a 2.8T parameter Mixture-of-Experts model with 104 billion activated parameters, native vision capabilities, and a 1-million-token context window. Kimi K3 is…
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…
RLinf-USER: A Unified and Extensible System for Real-World Online Policy Learning in Embodied AI
Hongzhi Zang, Shu'ang Yu, Hao Lin +14
Online policy learning directly in the physical world is a promising yet challenging direction for embodied intelligence. Unlike simulation, real-world systems cannot be arbitraril…
RLinf-VLA: A Unified and Efficient Framework for Reinforcement Learning of Vision-Language-Action Models
Hongzhi Zang, Mingjie Wei, Si Xu +15
Recent studies have demonstrated the potential of reinforcement learning (RL) to improve the task performance of vision-language-action (VLA) models through interaction. However, c…
: Online RL Fine-tuning for Flow-based Vision-Language-Action Models
Kang Chen, Zhihao Liu, Tonghe Zhang +11
Vision-Language-Action (VLA) models enable robots to understand and perform complex tasks from multimodal input. Although recent work explores using reinforcement learning (RL) to…