Yongbin Choi

whybe-choi's activity

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

upvoted a paper 10 days ago

OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment

Paper • 2510.07743 • Published 25 days ago • 8

upvoted an article 12 days ago

view article

Article

Introducing MTEB v2: Evaluation of embedding and retrieval systems for more than just text

By and 2 others •

13 days ago

• 33

upvoted an article 29 days ago

view article

Article

Vocabulary is the most important element of Sparse Retrieval

By •

29 days ago

• 8

upvoted an article about 1 month ago

view article

Article

No GPU left behind: Unlocking Efficiency with Co-located vLLM in TRL

Jun 3

• 93

upvoted an article about 2 months ago

view article

Article

Welcome EmbeddingGemma, Google's new efficient embedding model

Sep 4

• 253

upvoted a paper about 2 months ago

Open Data Synthesis For Deep Research

Paper • 2509.00375 • Published Aug 30 • 68

upvoted an article 2 months ago

view article

Article

Reinforcement Learning for Large Language Models: Beyond the Agent Paradigm

By •

Mar 19

• 8

upvoted 2 collections 2 months ago

ViDoRe Benchmark v2

Collection

8 items • Updated May 23 • 3

RaDeR training datasets

Collection

These are some of the retrieval training datasets used for training RaDeR models, sonsisting of different types of query combinations. • 3 items • Updated Jun 12 • 1

upvoted 2 papers 3 months ago

SSRL: Self-Search Reinforcement Learning

Paper • 2508.10874 • Published Aug 14 • 94

Deep Researcher with Test-Time Diffusion

Paper • 2507.16075 • Published Jul 21 • 64

upvoted a collection 3 months ago

JinaVDR (Visual Document Retrieval)

Collection

max. ~1000 images and OCR text included • 42 items • Updated Jul 20 • 6

upvoted a paper 4 months ago

Solving math word problems with process- and outcome-based feedback

Paper • 2211.14275 • Published Nov 25, 2022 • 10

upvoted an article 4 months ago

view article

Article

MedEmbed: Fine-Tuned Embedding Models for Medical / Clinical IR

By •

Oct 20, 2024

• 51

upvoted 3 collections 5 months ago

BioClinical ModernBERT

Collection

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

Qwen3-Reranker

Collection

3 items • Updated Jul 21 • 64

Qwen3-Embedding

Collection

6 items • Updated Jul 21 • 132

upvoted an article 5 months ago

view article

Article

Mitigating False Negatives in Multiple Negatives Ranking Loss for Retriever Training

By •

May 25

• 20

upvoted a paper 6 months ago

ReasonIR: Training Retrievers for Reasoning Tasks

Paper • 2504.20595 • Published Apr 29 • 53

upvoted an article 7 months ago

view article

Article

Open-source DeepResearch – Freeing our search agents

Feb 4

• 1.31k