Xin Li

fujikoli's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 3 days ago

Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding

Paper • 2601.20430 • Published 4 days ago • 14

upvoted 2 papers 4 days ago

Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers

Paper • 2601.17367 • Published 8 days ago • 33

Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding

Paper • 2601.20430 • Published 4 days ago • 14

authored a paper 4 days ago

Youtu-VL: Unleashing Visual Potential via Unified Vision-Language Supervision

Paper • 2601.19798 • Published 5 days ago • 40

upvoted a paper 4 days ago

Youtu-VL: Unleashing Visual Potential via Unified Vision-Language Supervision

Paper • 2601.19798 • Published 5 days ago • 40

upvoted a collection 5 days ago

Youtu

Collection

12 items • Updated 4 days ago • 21

liked a model 5 days ago

tencent/Youtu-Embedding

Sentence Similarity • 2B • Updated Dec 20, 2025 • 1.04k • 67

liked a Space 5 days ago

Running on Zero

11

Youtu-Parsing

🚀

11

Try out Youtu-Parsing on your PDFs or images

liked 6 models 5 days ago

tencent/Youtu-LLM-2B

Text Generation • 2B • Updated 3 days ago • 6.91k • 222

tencent/Youtu-LLM-2B-Base

Text Generation • Updated 3 days ago • 5.61k • 41

tencent/Youtu-LLM-2B-GGUF

Text Generation • 2B • Updated 27 days ago • 2.65k • 23

tencent/Youtu-Parsing

Image-Text-to-Text • 3B • Updated 4 days ago • 74 • 31

tencent/Youtu-VL-4B-Instruct-GGUF

Image-Text-to-Text • 5B • Updated 4 days ago • 990 • 45

tencent/Youtu-VL-4B-Instruct

Image-Text-to-Text • 5B • Updated 4 days ago • 292 • 109