Yongbin Choi's picture

Yongbin Choi

whybe-choi

·

AI & ML interests

LLM, RAG, Information Retrieval

Recent Activity

liked a dataset about 11 hours ago

slyipae1/MedBookVQA

updated a dataset 1 day ago

whybe-choi/kovidore-v2-hr-beir

liked a model 1 day ago

tomaarsen/Qwen3-VL-Embedding-2B-vdr

View all activity

Organizations

upvoted an article 2 days ago

Article

Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers

3 days ago

•

44

upvoted a collection 6 days ago

KoViDoRe Benchmark (BEIR) v2

Korean Vision Document Retrieval Benchmark • 4 items • Updated Mar 2 • 6

upvoted a paper 9 days ago

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

Paper • 2604.04734 • Published 13 days ago • 12

upvoted an article 9 days ago

Article

Multimodal Embedding & Reranker Models with Sentence Transformers

10 days ago

•

45

upvoted an article 16 days ago

Article

Build a Domain-Specific Embedding Model in Under a Day

29 days ago

•

68

upvoted an article 19 days ago

Article

How I contributed a new model to the Transformers library using Codex

19 days ago

•

46

upvoted a paper about 1 month ago

NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval

Paper • 2603.12824 • Published Mar 13 • 5

upvoted an article about 1 month ago

Article

A framework and leaderboard for Retrieval Pipelines evaluation on ViDoRe v3

Feb 27

•

12

upvoted a paper about 1 month ago

ModernVBERT: Towards Smaller Visual Document Retrievers

Paper • 2510.01149 • Published Oct 1, 2025 • 33

upvoted a collection about 1 month ago

VisionDocumentRetrieval Datasets

Datasets for vision document retrieval (VDR) • 19 items • Updated Mar 17 • 10

upvoted an article about 2 months ago

Article

ColFlor: Towards BERT-Size Vision-Language Document Retrieval Models

Oct 18, 2024

•

21

upvoted a paper about 2 months ago

SDS KoPub VDR: A Benchmark Dataset for Visual Document Retrieval in Korean Public Documents

Paper • 2511.04910 • Published Nov 7, 2025 • 1

upvoted a collection 2 months ago

pplx-embed

Diffusion-Pretrained Dense and Contextual Embeddings • 7 items • Updated Feb 26 • 96

upvoted a paper 2 months ago

Training Sparse Mixture Of Experts Text Embedding Models

Paper • 2502.07972 • Published Feb 11, 2025 • 10

upvoted 2 articles 3 months ago

Article

How We Built a Semantic Highlight Model To Save Token Cost for RAG

Jan 15

•

66

Article

Continuous batching from first principles

+1

Nov 25, 2025

•

360

upvoted 2 papers 3 months ago

ViDoRe V3: A Comprehensive Evaluation of Retrieval Augmented Generation in Complex Real-World Scenarios

Paper • 2601.08620 • Published Jan 13 • 12

MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval

Paper • 2412.14475 • Published Dec 19, 2024 • 58

upvoted a collection 3 months ago

ViDoRe Community benchmark contributions

This collection regroups works done by the community to improve together Visual Retrieval ! • 4 items • Updated Jan 9 • 1

upvoted an article 3 months ago

Article

Small Yet Mighty: Improve Accuracy In Multimodal Search and Visual Document Retrieval with Llama Nemotron RAG Models

Jan 6

•

28