🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Happy to collaborate with Raghuveer, Bhuwan and others to work on batch mining for VLM2Vec. Now it's the SoTA on the MMEB benchmark. huggingface.co/spaces/TIGER-L…

Finally, the crazy weeks of NeurIPS ddl, ICCV rebuttal and EMNLP ddl have passed. Now it's time to take a rest till Sep!

Our General Reasoner paper is coming out on Arxiv at arxiv.org/abs/2505.14652 We have re-trained our general-reasoner models to obtain much better performance! - Our 4B General Reasoner can even beat the NVDIA's Nemotron-CrossThink-7B significantly. - Our 14B General-Reasoner

Thanks for sharing! - Our 4B General Reasoner can even beat the NVDIA's Nemotron-CrossThink-7B significantly. - Our 14B General-Reasoner (Qwen3) can already achieve MMLU-Pro of 70.3%, GPQA of 56%, SuperGPQA of 39.9%, and TheoremQA of 54.4%. It's one of the most powerful

Veo 3 blew people's mind in generating talking characters! It's so exciting! But we need evaluation benchmark for that! Cong just released the MochaBench used in our Mocha paper to evaluate talking character models. Github: github.com/congwei1230/Mo… Mocha Paper:

Arxiv is going crazy after NeurIPS/EMNLP deadline. It's impossible to catch up.

Thanks for sharing our paper! We are able to incentivize VLMs to conduct reasoning in the pixel/image space in the o3-style. Paper: arxiv.org/abs/2505.15966