Shukang Yin

xjtupanda

xjtupanda

AI & ML interests

Computer Vision, Multimodal learning

Recent Activity

published a model about 1 month ago

xjtupanda/qwen3-vl-4b-thinking-tune

upvoted a paper about 2 months ago

UniPrefill: Universal Long-Context Prefill Acceleration via Block-wise Dynamic Sparsification

upvoted a paper 3 months ago

Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding

View all activity

Organizations

None yet

New activity in xjtupanda/MiniCPM-V-200K-video-finetune 12 months ago

Improve model card: Add abstract and sample usage

#2 opened 12 months ago by

New activity in xjtupanda/Sparrow-Synthetic 12 months ago

Update dataset card: Add library_name, project link, and sample usage

#2 opened 12 months ago by

New activity in xjtupanda/MiniCPM-V-30K-mix-finetune 12 months ago

Improve model card: Add comprehensive summary and usage example

#3 opened 12 months ago by

New activity in xjtupanda/MiniCPM-V-30K-mix-finetune over 1 year ago

Fix formatting

#2 opened over 1 year ago by

New activity in xjtupanda/MiniCPM-V-200K-video-finetune over 1 year ago

Update model card with paper information and correct Github link

#1 opened over 1 year ago by

New activity in xjtupanda/MiniCPM-V-30K-mix-finetune over 1 year ago

Add Github link to model card

#1 opened over 1 year ago by

New activity in xjtupanda/Sparrow-Synthetic over 1 year ago

Update task category and Github link

#1 opened over 1 year ago by