Wenpu Li's picture

Wenpu Li

wincentIsMe

·

https://akawincent.github.io/

AI & ML interests

3D computer vision

Recent Activity

upvoted a paper 5 days ago

ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning

liked a model 23 days ago

Qwen/Qwen3-VL-4B-Instruct

published a model 23 days ago

wincentIsMe/Qwen3-0.6B-finetuned-astro-horoscope-deepspeed-best-hpo

View all activity

Organizations

None yet

New activity in lmms-lab/LLaVA-OneVision-1.5-8B-Instruct 4 months ago

fix: import `flash_attn_varlen_func` from `flash_attn` instead of `transformers.modeling_flash_attention_utils`

#4 opened 4 months ago by