19 papers
When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAs
Yu Fang, Yuchun Feng, Dong Jing +5
The paper studies how Vision-Language-Action (VLA) models often ignore language instructions by relying on visual shortcuts, introduces a counterfactual benchmark (LIBERO-CF) to ev…
DenseReward: Dense Reward Learning via Failure Synthesis for Robotic Manipulation
Yu Fang, Wanxi Dong, Jiaqi Liu +7
The paper presents DenseReward, a dense visual‑language reward model for robotic manipulation that is trained on automatically synthesized failure trajectories in simulation, enabl…
Learning Action Priors for Cross-embodiment Robot Manipulation
Dong Jing, Tianqi Zhang, Jiaqi Liu +5
Most Vision-Language-Action (VLA) models build on a Vision-Language Model (VLM) backbone by attaching an action module and optimizing the full policy jointly. This design inherits…
TempoVLA: Learning Speed-Controllable Vision-Language-Action Policies
Dong Jing, Jingchen Nie, Tianqi Zhang +4
Robot manipulation alternates between low-risk transit phases that call for fast execution and high-risk contact stages that demand slow, precise motion. Yet existing Vision-Langua…
Mixture of Horizons in Action Chunking
Dong Jing, Gang Wang, Jiaqi Liu +7
Vision-language-action (VLA) models have shown remarkable capabilities in robotic manipulation, but their performance is sensitive to the used during…
AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration
Jiaqi Liu, Shi Qiu, Mairui Li +33
Automating scientific discovery requires more than generating papers from ideas. Real research is iterative: hypotheses are challenged from multiple perspectives, experiments fail…