HAODONG DUAN

KennyUTC

AI & ML interests

Video Understanding; Multi-Modal Learning

Recent Activity

Organizations

Blog-explorers's profile picture OpenCompass's profile picture VLMEval's profile picture Chinese LLMs on Hugging Face's profile picture WePOINTS's profile picture

KennyUTC's activity

reacted to mervenoyan's post with ๐Ÿ”ฅ 4 months ago
reacted to their post with โค๏ธ 9 months ago
view post
Post
1491
OPEN VLM LEADERBOARD JUST RELEASED the FULL EVALUATION RESULTS of GPT-4o

[TL;DR]
GPT-4o shows steady progress compared to GPT-4v (0419), with a 3% improvement on the average score (68.7% -> 72.1%). GPT-4o displays stronger perception and less hallucination.

opencompass/open_vlm_leaderboard
  • 1 reply
ยท
posted an update 9 months ago
view post
Post
1491
OPEN VLM LEADERBOARD JUST RELEASED the FULL EVALUATION RESULTS of GPT-4o

[TL;DR]
GPT-4o shows steady progress compared to GPT-4v (0419), with a 3% improvement on the average score (68.7% -> 72.1%). GPT-4o displays stronger perception and less hallucination.

opencompass/open_vlm_leaderboard
  • 1 reply
ยท
posted an update 10 months ago
view post
Post
2626
Open VLM Leaderboard just updated the performance of GPT-4v (20240409), the new proprietary model ranked 1st across 50+ VLMs. Compared to the pervious version (20231106), the improvements on multimodal perception and reasoning are both huge.

Check the results:
opencompass/open_vlm_leaderboard