5 papers
Echo: Coupled Action and Task Status Signal Denoising for Vision Language Action Models
Yufeng Liu, Bohao Fan, Juntu Zhao +11
Recognizing task completion and failure enables robots to stop upon success and initiate recovery or replanning after failure. Existing methods augment Vision Language Action (VLA)…
TadA-Bench: A Million-Variant Benchmark for Future-Round Discovery Toward Agentic Protein Engineering
Jin Gao, Juntu Zhao, Zirui Zeng +5
AI for scientific discovery is entering an agentic era, where protein-engineering systems are expected to prioritize future wet-lab experiments rather than merely fit static measur…
Learning Native Continuation for Action Chunking Flow Policies
Yufeng Liu, Hang Yu, Juntu Zhao +9
Action chunking enables Vision Language Action (VLA) models to run in real time, but naive chunked execution often exhibits discontinuities at chunk boundaries. Real-Time Chunking…
Saying the Unsaid: Revealing the Hidden Language of Multimodal Systems Through Telephone Games
Juntu Zhao, Jialing Zhang, Chongxuan Li +1
Recent closed-source multimodal systems have made great advances, but their hidden language for understanding the world remains opaque because of their black-box architectures. In…
Do You Need Proprioceptive States in Visuomotor Policies?
Juntu Zhao, Wenbo Lu, Di Zhang +10
Imitation-learning-based visuomotor policies have been widely used in robot manipulation, where both visual observations and proprioceptive states are typically adopted together fo…