KuKu

dragonkue's activity

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

upvoted a paper 1 day ago

Sharpening Tax in Post-Training

Paper • 2610.01509 • Published 3 days ago • 78

upvoted a paper 5 days ago

Beyond Hard Negatives: The Importance of Score Distribution in Knowledge Distillation for Dense Retrieval

Paper • 2604.04734 • Published Apr 6 • 15

upvoted a paper 11 days ago

Ovis-Embedding: Pushing the Frontiers of Universal Omni-Modal Embeddings

Paper • 2609.25165 • Published 13 days ago • 77

upvoted an article 26 days ago

view article

Article

NeoMME: an efficient Multimodal-native and Multilingual Encoder

• 

Hcompany

•

about 1 month ago

• 120

upvoted a paper 27 days ago

Iris: Climbing to the Search Frontier

Paper • 2609.04304 • Published Sep 3 • 73

upvoted 2 articles about 1 month ago

view article

Article

Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers

• 

tomaarsen

•

Aug 26

• 144

view article

Article

How Hugging Face Inference Endpoints, Jobs, and Buckets Power Search on Papers with Code

• 

nielsr

•

Aug 21

• 33

upvoted a paper about 1 month ago

jina-reranker-v3: Last but Not Late Interaction for Document Reranking

Paper • 2509.25085 • Published Sep 29, 2025 • 13

upvoted a collection about 1 month ago

SauerkrautLM-Multilingual-(Reason)-ColBERT

Collection

SauerkrautLM ColBERT is a suite of Late-Interaction retrieval models built with PyLate’s ColBERT architecture and tuned for seven European languages. • 7 items • Updated Aug 3, 2025 • 21

upvoted a paper about 1 month ago

Prism-Reranker: Beyond Relevance Scoring -- Jointly Producing Contributions and Evidence for Agentic Retrieval

Paper • 2604.23734 • Published Apr 26 • 4

upvoted an article about 2 months ago

view article

Article

LEMUR and Mean Centering for Late-Interaction Retrieval in txtai

• 

NeuML

•

Aug 13

• 9

upvoted a paper about 2 months ago

Bekko Embedding: Parameter-Efficient Multilingual Retrieval with Ultra-Compact Encoders

Paper • 2607.25180 • Published Jul 28 • 4

upvoted an article about 2 months ago

view article

Article

GLInt: Geometry-Matched Hard Negatives for Late-Interaction Retrieval

• 

chungimungi

•

Aug 8

• 13

upvoted 3 papers about 2 months ago

Compact Language Models via Pruning and Knowledge Distillation

Paper • 2407.14679 • Published Jul 19, 2024 • 43

DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Search

Paper • 2607.27178 • Published Jul 29 • 8

NOLLI: A Difficulty-Calibrated Puzzle Benchmark for Diagnosing the English-Korean Performance Gap

Paper • 2608.04397 • Published Aug 5 • 23

upvoted 2 articles 2 months ago

view article

Article

After the party comes the free lunch: regularizing ColBERT models to enhance pooling capabilities and reduce index footprint

• 

lightonai

•

Jul 6

• 17

view article

Article

mDenseOn with the mLateOn: Open Multilingual, Long-Context, and Code Retrieval Models

• 

lightonai

•

Jul 30

• 39

upvoted 2 papers 2 months ago

jina-reranker-v3.5: An Efficient Listwise Reranker with Hybrid Attention and Self-Distillation

Paper • 2607.18152 • Published Jul 20 • 6

ProRank: Prompt Warmup via Reinforcement Learning for Small Language Models Reranking

Paper • 2506.03487 • Published Jun 4, 2025 • 7