Han Qi

LLM agents can be made robust to complex, multi-turn adversarial attacks on tool use through a co-evolutionary game, outperforming prior methods on safety and capability benchmarks.

This work proposes RoboMP-DINOv2 (Robotics Mask-Prompted DINOv2), a full-scene vision encoder that treats masks as spatial prompts rather than visibility filters, and introduces masked-region color randomization (MCR) to improve appearance robustness, yielding RoboMP-DINOv2-MCR.