Takumi Okoshi

takuoko's activity

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

liked a Space 9 days ago

Running

7

Dbv4 Full Tagger Ranklist (dbv4-full)

🏆

7

Ranklist of ALL dbv4-full models

upvoted an article 18 days ago

view article

Article

Nemotron-Personas-Japan: Synthesized Data for Sovereign AI

• 

Sep 23

•

27

liked a dataset 21 days ago

zhihefang/UltraHR-100K

Viewer • Updated about 10 hours ago • 900 • 16.8k • 22

liked 2 models 28 days ago

nvidia/omnivinci

Feature Extraction • Updated 22 days ago • 15.4k • 159

AIDC-AI/Marco-MT-Algharb

Translation • 15B • Updated 28 days ago • 717 • 22

liked 2 datasets about 1 month ago

WithAnyone/MultiID-2M

Updated Oct 20 • 7.73k • 7

JackyZhuo/SructVisuals

Viewer • Updated Oct 9 • 1.34M • 458 • 4

liked 3 models about 1 month ago

tencent/SongPrep-7B

Automatic Speech Recognition • 8B • Updated 28 days ago • 118 • 40

google/timesfm-2.5-200m-pytorch

Time Series Forecasting • Updated Oct 2 • 148

ByteDance/FaceCLIP

Text-to-Image • Updated 10 days ago • 85

liked a dataset about 2 months ago

nvidia/Nemotron-Personas-Japan

Viewer • Updated Sep 24 • 1M • 3.5k • 88

liked 2 models 2 months ago

bytedance-research/UMO

Text-to-Image • Updated Sep 12 • 361 • 59

tencent/SRPO

Text-to-Image • Updated Sep 15 • 4.02k • • 958

liked a model 3 months ago

bytedance-research/USO

Text-to-Image • Updated Sep 1 • 228 • 179

liked a dataset 3 months ago

opencompass/VerifierBench

Viewer • Updated Aug 26 • 2.82k • 125 • 3

upvoted a collection 3 months ago

CompassVerifier

Collection

CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward • 5 items • Updated Aug 31 • 7

liked a model 4 months ago

Skywork/Skywork-UniPic-1.5B

Any-to-Any • Updated Sep 8 • 91 • 113

liked a dataset 4 months ago

UCSC-VLAA/GPT-Image-Edit-1.5M

Viewer • Updated Aug 21 • 2.78M • 8.77k • 63

liked a model 5 months ago

AIDC-AI/Ovis-U1-3B

Any-to-Any • 4B • Updated Jul 3 • 3.08k • 203

upvoted a collection 5 months ago

Tar

Collection

[NeurIPS 2025] Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations • 11 items • Updated Sep 20 • 1