Zhuoqing Mao

SWINGARENA: Adversarial Programming Arena for Long-context GitHub Issue Solving

MARS: Harmonizing Multimodal Convergence via Adaptive Rank Search

PhyX: Does Your Model Have the "Wits" for Physical Reasoning?

Compute or Load KV Cache? Why Not Both?

AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs

Plato: Plan to Efficient Decode for Large Language Model Inference

Cocoon: Robust Multi-Modal Perception with Uncertainty-Aware Sensor Fusion

Safeguard is a Double-edged Sword: Denial-of-service Attack on Large Language Models

Compute Or Load KV Cache? Why Not Both?