Jianhua Li

A simple physical object can hijack an agent's internal imagination rollouts, trapping its downstream policy in an adversarial trajectory long after the trigger leaves the scene.

SPARGen achieves competitive performance across diverse spatial tasks by unifying perception and reasoning into a single generative framework, challenging the need for separate architectures.

Multi-turn jailbreaks exploit user intent in ways that traditional safety measures fail to detect, revealing a critical vulnerability in LLM interactions.

A single unified model can outperform specialized systems across various computer vision tasks, all without the need for custom architectures.

SpikeTimer achieves a remarkable balance between copyright protection and performance, maintaining high accuracy on authorized data while effectively misclassifying unauthorized inputs.

LLM defenses can achieve a 79% reduction in attack success rate against evolving multi-round attacks by using a stateful, multi-agent cooperative framework.

Semantic disagreement between LLMs reveals crucial uncertainty that single-model metrics miss, and Collaborative Entropy (CoE) captures it.