Shi Yu

yushi's activity

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

authored a paper 13 days ago

Empowering Edge Agents: A Systematic Analysis of Edge-Cloud Collaboration in LLM Agent Execution

Paper • 2610.17816 • Published 22 days ago • 14

upvoted 3 papers 13 days ago

Empowering Edge Agents: A Systematic Analysis of Edge-Cloud Collaboration in LLM Agent Execution

Paper • 2610.17816 • Published 22 days ago • 14

Chaos in the Text: Revealing the Modality Preference in Mixed-Modality Retrievers

Paper • 2610.11816 • Published 27 days ago • 17

Skill-Decoupled On-Policy Expert Distillation for Unified Vision-Language Models

Paper • 2610.22217 • Published 20 days ago • 13

upvoted a changelog 26 days ago

view changelog

Hugging Face Changelog

P(doom) on user profiles

29 days ago

• 361

liked a model about 2 months ago

openbmb/MiniCPM5-2B

Text Generation • 3B • Updated Sep 29 • 1.07M • 1.84k

published a dataset 8 months ago

XBKYS/aaa

Viewer • Updated Oct 30, 2024 • 2.77M • 7

liked 2 models 9 months ago

openbmb/MiniCPM-SALA

Text Generation • 9B • Updated May 7 • 3.73k • 686

openbmb/MiniCPM-o-4_5

Any-to-Any • 9B • Updated 10 days ago • 203k • 1.56k

liked 2 datasets about 1 year ago

HuggingFaceFW/finewiki

Viewer • Updated Oct 22, 2025 • 61.6M • 15.2k • 343

OctoThinker/MegaMath-Web-Pro-Max

Viewer • Updated Jul 6, 2025 • 69.2M • 2.93k • 41

liked 2 models about 1 year ago

openbmb/Ultra-FineWeb-classifier

Updated Aug 19 • 244 • 58

openbmb/MiniCPM-V-4

Image-Text-to-Text • 4B • Updated Aug 18 • 28.9k • 465

liked a model over 1 year ago

HuggingFaceTB/SmolLM3-3B

Text Generation • 3B • Updated Sep 10, 2025 • 568k • 1.07k

upvoted a paper over 1 year ago

MiniCPM4: Ultra-Efficient LLMs on End Devices

Paper • 2506.07900 • Published Jun 9, 2025 • 100

commented a paper over 1 year ago

DeepResearchGym: A Free, Transparent, and Reproducible Evaluation Sandbox for Deep Research

Paper • 2505.19253 • Published May 25, 2025 • 33 •

2

upvoted 2 papers over 1 year ago

DeepResearchGym: A Free, Transparent, and Reproducible Evaluation Sandbox for Deep Research

Paper • 2505.19253 • Published May 25, 2025 • 33

Efficient Agent Training for Computer Use

Paper • 2505.13909 • Published May 20, 2025 • 42

updated a collection over 1 year ago

MiniCPM RAG Suite

Collection

Embedding, re-ranking, generation -- the cornerstone of RAG. • 7 items • Updated Sep 15 • 21