5 papers
iFLYTEK-Embodied-Omni Technical Report
Yuan Zhang, Jingfei Ni, Guanchen Lu +12
General-purpose embodied agents must understand multimodal instructions, anticipate how their environment will evolve, and produce precise control actions over extended horizons. E…
A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning
Shaopeng Zhai, Qi Zhang, Tianyi Zhang +7
Robotic real-world reinforcement learning (RL) with vision-language-action (VLA) models is bottlenecked by sparse, handcrafted rewards and inefficient exploration. We introduce VLA…
CURE: Critical-Token-Guided Re-Concatenation for Entropy-Collapse Prevention
Qingbin Li, Rongkun Xue, Jie Wang +8
Recent advances in Reinforcement Learning with Verified Reward (RLVR) have driven the emergence of more sophisticated cognitive behaviors in large language models (LLMs), thereby e…
Efficient Skill Discovery via Regret-Aware Optimization
He Zhang, Ming Zhou, Shaopeng Zhai +2
Unsupervised skill discovery aims to learn diverse and distinguishable behaviors in open-ended reinforcement learning. For existing methods, they focus on improving diversity throu…
Atomic-to-Compositional Generalization for Mobile Agents with A New Benchmark and Scheduling System
Yuan Guo, Tingjia Miao, Zheng Wu +3
Autonomous agents powered by multimodal large language models have been developed to facilitate task execution on mobile devices. However, prior work has predominantly focused on a…