4 papers
CAPER: Constrained and Procedural Reasoning for Robotic Scientific Experiments
Jinghan Yang, Jingyi Hou, Xinbo Yu +2
Robotic assistance in scientific laboratories requires procedurally correct long-horizon manipulation, reliable execution under limited supervision, and robustness in low-demonstra…
Differentiate-and-Inject: Enhancing VLAs via Functional Differentiation Induced by In-Parameter Structural Reasoning
Jingyi Hou, Leyu Zhou, Chenchen Jing +3
As robots are expected to perform increasingly diverse tasks, they must understand not only low-level actions but also the higher-level structure that determines how a task should…
Agentic Entropy-Balanced Policy Optimization
Guanting Dong, Licheng Bao, Zhongyuan Wang +11
Recently, Agentic Reinforcement Learning (Agentic RL) has made significant progress in incentivizing the multi-turn, long-horizon tool-use capabilities of web agents. While mainstr…
RED: Robust Environmental Design
Jinghan Yang
The classification of road signs by autonomous systems, especially those reliant on visual inputs, is highly susceptible to adversarial attacks. Traditional approaches to mitigatin…