Dacheng Li

7

Papers

172

Total Citations

Papers (7)

SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

WorldModelBench: Judging Video Generation Models As World Models

Dual Contradistinctive Generative Autoencoder

Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference

NVILA: Efficient Frontier Visual Language Models

AMP: Automatically Finding Model Parallel Strategies with Heterogeneity Awareness

Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena