collaborators

9 papers

cs.CL2026

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills

Siyuan Huang, Pengyu Cheng, Haotian Liu +10

LLM training is shifting from manual design and annotation to interaction-driven self-evolution. However, existing self-evolutionary methods face a fundamental dilemma between task…

cs.RO2026

ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretraining

Hao Li, Ganlong Zhao, Yufei Liu +8

Vision-Language-Action (VLA) models benefit from large-scale and diverse embodied data, yet scaling robot trajectory collection is costly and labor-intensive. Recent advances show…

cs.RO2026

Hierarchical Advantage Weighting for Online RL Fine-Tuning of VLAs from Sparse Episode Outcomes

Tongyan Fang, Siyuan Huang, Naiyu Fang +6

When pretrained VLA policies are fine-tuned through online RL, each rollout episode produces only a single binary outcome (success or failure), yet the actor update requires per-tr…

cs.LG2026

GDPO: Mitigating Multi-Reward Conflicts via Group-Dynamic reward-Decoupled Policy Optimization

Haotian Liu, Yihao Liu, Jingwei Ni +11

As LLMs advance, post-training reinforcement learning (RL) increasingly relies on multi-dimensional rewards to cultivate comprehensive capabilities. This shift demands new algorith…

cs.RO2026

Test-time Adversarial Takeover: A Real-time Hijacking Interface against Robotic Diffusion Policies

Zi Yin, Peilin Chai, Siyuan Huang +1

Diffusion-based action generation has become a foundational component of embodied AI, but its reliance on visual conditioning leaves deployed visuomotor policies vulnerable to adve…

cs.LG2026

Skill-RM: Unifying Heterogeneous Evaluation Criteria via Agent Skill

Tao Chen, Gangwei Jiang, Pengyu Cheng +10

Reward models (RMs) provide critical feedback signals for LLM post-training, notably in reinforced fine-tuning (RFT) and reinforcement learning (RL) pipelines. However, current rew…