Guohui Zhang's picture

4 1

Guohui Zhang

zghhui

·

zghhui

AI & ML interests

None yet

Recent Activity

upvoted a paper 29 days ago

IF-VidCap: Can Video Caption Models Follow Instructions?

upvoted a paper 29 days ago

MT-Video-Bench: A Holistic Video Understanding Benchmark for Evaluating Multimodal LLMs in Multi-Turn Dialogues

upvoted a paper about 1 month ago

RLFR: Extending Reinforcement Learning for LLMs with Flow Environment

View all activity

Organizations

None yet

zghhui 's models 6

zghhui/Janus-Pro-1B-GCPO-HPS

Text-to-Image • 2B • Updated Sep 28 • 2

zghhui/Janus-Pro-1B-GCPO-Geneval

Text-to-Image • 2B • Updated Sep 28 • 3

zghhui/Janus-Pro-7B-GCPO-HPS

Text-to-Image • 7B • Updated Sep 28 • 4

zghhui/LlamaGen-T2I-GCPO

Text-to-Image • 0.8B • Updated Sep 28 • 6

zghhui/Janus-Pro-7B-GCPO-Geneval

Text-to-Image • 7B • Updated Sep 28 • 2

zghhui/LlamaGen-T2I

0.8B • Updated Sep 26 • 5