Ao Ding

The paper investigates the security risk of extracting knowledge from quantized LLMs deployed on edge devices, showing that structured querying can effectively bypass quantization protections.

The paper introduces SafeMed-R1, a clinically audited LLM that significantly improves safety and ethical alignment for medical applications, matching or exceeding resident performance on safety-critical tasks.

DeepTool introduces a novel Process-Supervised Reinforcement Learning framework to enhance Tool-Integrated Reasoning by explicitly supervising and rewarding intermediate, interleaved deliberation steps during sequential tool use.

StressDream proposes a novel method to steer video world model imaginations toward high-impact, yet plausible outcomes, enabling robust policy evaluation and improvement by identifying undesirable future scenarios.

DeMaVLA is a generalizable Vision-Language-Action foundation model designed for deformable object manipulation, achieving strong real-world performance on folding tasks by leveraging large-scale real-world data and corrective learning.