Hongyang Zhang

TrustGen: A Platform of Dynamic Benchmarking on the Trustworthiness of Generative Foundation Models

EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

The Matrix: Infinite-Horizon World Generation with Real-Time Moving Control

Asking Specifically Instead of Ambiguously to Your GPT Improves Image Caption

Pseudo- vs. True-Randomness: Rethinking Distortion-Free Watermarks of Language Models under Watermark Key Collisions

Revisiting Referring Expression Comprehension Evaluation in the Era of Large Multimodal Models