Jingxuan Zhang

Current image generation models struggle with rendering dense, multi-region text, with fidelity dropping by over 14 points when clarity is prioritized.

Current AI-generated videos that mislead viewers are also the most challenging for existing detection systems to identify, revealing a critical vulnerability in misinformation defenses.

LLM agents struggle to generalize from experience to reusable skills, often performing worse than simply replaying past trajectories, revealing a critical gap in current abstraction methods.

Text-based speculative decoding falls flat for vision-language models, but ViSkip dynamically adapts to vision tokens for state-of-the-art acceleration.

LLMs can perfectly cluster speakers in overlapping multi-party conversations, enabling near-perfect Joint ASR-Clustering Error Rate in challenging CHiME-9 tasks.