Antoine Chaffin's picture

Antoine Chaffin

NohTow

·

https://antoine.chaffin.fr

AI & ML interests

NLP, Computer Vision, Multimodal classification

Recent Activity

updated a dataset about 1 hour ago

lightonai/nv-embed-supervised-distill-dedup

published a dataset about 6 hours ago

lightonai/nv-embed-supervised-distill-dedup

updated a dataset about 6 hours ago

lightonai/nv-embed-supervised-distill

View all activity

Organizations

upvoted an article 5 days ago

Article

LightOnOCR-1B: The Case for End-to-End and Efficient Domain-Specific Vision-Language Models for OCR

By

and 2 others •

5 days ago

• 48

upvoted 2 papers 11 days ago

Simple Projection Variants Improve ColBERT Performance

Paper • 2510.12327 • Published 14 days ago • 5

Fantastic (small) Retrievers and How to Train Them: mxbai-edge-colbert-v0 Tech Report

Paper • 2510.14880 • Published 12 days ago • 13

upvoted an article about 2 months ago

Article

Welcome EmbeddingGemma, Google's new efficient embedding model

Sep 4

• 250

upvoted an article 3 months ago

Article

Introducing ColQwen-Omni: Retrieve in every modality

By

and 4 others •

Jul 17

• 75

upvoted a paper 3 months ago

Seq vs Seq: An Open Suite of Paired Encoders and Decoders

Paper • 2507.11412 • Published Jul 15 • 28

upvoted an article 3 months ago

Article

Seq vs Seq: the Ettin Suite of Paired Encoders and Decoders

Jul 16

• 74

upvoted a collection 4 months ago

PyLate 🐕

4 items • Updated Jul 2 • 3

upvoted a collection 5 months ago

BioClinical ModernBERT

This project was a collaboration between members of the Dana-Farber Cancer Institute, LightOn, MIT, OpenEvidence and Microsoft. • 3 items • Updated Sep 9 • 11

upvoted an article 8 months ago

Article

Introducing EuroBERT: A High-Performance Multilingual Encoder Model

By

and 3 others •

Mar 10

• 146

upvoted a paper 8 months ago

Rank1: Test-Time Compute for Reranking in Information Retrieval

Paper • 2502.18418 • Published Feb 25 • 28

upvoted a collection 9 months ago

Qwen2.5-VL

Vision-language model series based on Qwen2.5 • 11 items • Updated Jul 21 • 544

upvoted an article 9 months ago

Article

Finally, a Replacement for BERT: Introducing ModernBERT

Dec 19, 2024

• 705

upvoted a collection 10 months ago

ModernGLiNER

GLiNER models based on modern encoder architectures • 2 items • Updated Dec 24, 2024 • 7

upvoted a paper 10 months ago

Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference

Paper • 2412.13663 • Published Dec 18, 2024 • 156

upvoted a collection 10 months ago

ModernBERT

Bringing BERT into modernity via both architecture changes and scaling • 3 items • Updated Dec 19, 2024 • 150

upvoted a paper about 1 year ago

Reducing the Footprint of Multi-Vector Retrieval with Minimal Performance Impact via Token Pooling

Paper • 2409.14683 • Published Sep 23, 2024 • 12

upvoted a paper about 2 years ago

Three Bricks to Consolidate Watermarks for Large Language Models

Paper • 2308.00113 • Published Jul 26, 2023 • 14