@zhengtoong Profile picture

Tong Zheng

@zhengtoong

PhD Student @ UMD CS

#EMNLP2024 Accepted to EMNLP 2024 Main Conference 🎉 Is prompting really enough for accurate author attribution with LLMs? 🧐 Our large-scale study shows prompting alone has its limits. We introduce the first Bayesian framework designed for efficient and accurate author…

Tweet Image 1

Tong Zheng Reposted

🚀🔥Introducing LLaVA-Critic--the first open-source large multimodal model designed to assess model performance across diverse multimodal tasks! LLaVA-Critic excels in two primary scenarios: - 👨‍⚖️LMM-as-a-Judge: It provides pointwise scores and pairwise rankings that closely…

Tweet Image 1

United States Trends
Loading...

Something went wrong.


Something went wrong.