Youngjoon Jang

yjoonjang's activity

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

updated a Space about 4 hours ago

Running

ReviewSearch

🔍

Semantic hybrid search over 206k ML/NLP peer reviews

updated a dataset about 11 hours ago

yjoonjang/reviewsearch-index

Updated about 11 hours ago

updated 2 models about 11 hours ago

yjoonjang/reviewsearch-sparse

Feature Extraction • Updated about 11 hours ago

yjoonjang/reviewsearch-dense

Sentence Similarity • 0.3B • Updated about 11 hours ago

published a Space about 11 hours ago

Running

ReviewSearch

🔍

Semantic hybrid search over 206k ML/NLP peer reviews

published a dataset about 11 hours ago

yjoonjang/reviewsearch-index

Updated about 11 hours ago

published 2 models about 11 hours ago

yjoonjang/reviewsearch-sparse

Feature Extraction • Updated about 11 hours ago

yjoonjang/reviewsearch-dense

Sentence Similarity • 0.3B • Updated about 11 hours ago

liked a model about 14 hours ago

sionic-ai/comsat-embed-ko-8b-preview

Sentence Similarity • 8B • Updated 1 day ago • 6

New activity in whybe-choi/ko-vdr-hn 4 days ago

Replace ko-vdr-train-public-v2.0_reranked with training-ready flat schema (positive + 8 negatives + reranked_scores)

#5 opened 4 days ago by

yjoonjang

Rename reranker config to ko-vdr-train-public-v2.0_reranked + note source coverage

❤️🚀 1

1

#4 opened 4 days ago by

yjoonjang

Add ko-vdr-train-public-v2.0_reranked config (Qwen3-VL reranker-scored candidates, mined from ko-vdr-train-public-v2.0 only)

1

#3 opened 4 days ago by

yjoonjang

Add reranked_qwen3_vl_8b config (Qwen3-VL reranker-scored candidates for distillation)

❤️🚀 1

1

#2 opened 4 days ago by

yjoonjang

liked a model 10 days ago

baidu/Unlimited-OCR

Image-Text-to-Text • 3B • Updated 1 day ago • 885k • 1.7k

upvoted a paper 17 days ago

jina-embeddings-v5-text: Task-Targeted Embedding Distillation

Paper • 2602.15547 • Published Feb 17 • 31

liked a model 23 days ago

google/diffusiongemma-26B-A4B-it

Image-Text-to-Text • 26B • Updated 1 day ago • 1.48M • 1.09k

liked a model about 1 month ago

google/gemma-4-12B-it

Any-to-Any • 12B • Updated 30 days ago • 3.02M • 1.24k

upvoted a paper about 1 month ago

Is Position Bias in Dense Retrievers Built In-or Learned from Data?

Paper • 2605.26578 • Published May 26 • 20

commented on Introducing the Ettin Reranker Family about 1 month ago

view reply

Great work! Love that you used stratified sampling.
It's great to see its power on cross-encoders, too!

liked a dataset about 1 month ago

cross-encoder/ettin-reranker-v1-data

Viewer • Updated May 21 • 143M • 1.16k • 7