Shukang Yin

xjtupanda

xjtupanda

AI & ML interests

Computer Vision, Multimodal learning

Recent Activity

upvoted a paper 28 days ago

OmniAssistBench: Assistant-style Interaction Benchmark for Omni-LLMs

published a model 4 months ago

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

upvoted a paper 4 months ago

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

View all activity

Organizations

None yet

Collections 1

Papers 1

arxiv:2310.16045

models 4

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

xjtupanda/MiniCPM-V-200K-video-finetune

Video-Text-to-Text • 9B • Updated Jul 24, 2025 • 14

xjtupanda/MiniCPM-V-30K-mix-finetune

Video-Text-to-Text • 9B • Updated Jul 24, 2025 • 9

xjtupanda/HawkVL-2B

Image-Text-to-Text • 2B • Updated Jun 11, 2025 • 419

datasets 6

xjtupanda/VisualProbe_Medium

Viewer • Updated Sep 28, 2025 • 268 • 47

xjtupanda/VisualProbe_Easy

Viewer • Updated Sep 28, 2025 • 141 • 54

xjtupanda/VisualProbe_Hard

Viewer • Updated Sep 28, 2025 • 106 • 49

xjtupanda/VLMsAreBlind

Viewer • Updated Sep 23, 2025 • 8.02k • 10

xjtupanda/VStar_Bench

Viewer • Updated Aug 11, 2025 • 191 • 533

xjtupanda/Sparrow-Synthetic

Preview • Updated Jul 24, 2025 • 186