🔄 In a Training Loop

Yuichi Tateno PRO

hotchpotch

218 59 266

https://hotchpotch.dev/

AI & ML interests

Information Retrieval with LLMs

Recent Activity

updated a Space about 22 hours ago

hakari-bench/leaderboard

updated a dataset about 22 hours ago

hakari-bench/leaderboard_database

new activity about 22 hours ago

hakari-bench/results:Add benchmark results for codefuse-ai/F2LLM-v2-0.6B

View all activity

Organizations

upvoted 2 articles 16 days ago

Article

Tokenmaxxing BERT: 50x faster tokenization

huggingface

•

22 days ago

• 54

Article

SlideOn & mSlideOn: Sparsified Late-Interaction and Dense Retrievers

lightonai

•

18 days ago

• 29

upvoted a paper 16 days ago

UltraBERT: Beyond the Limit of BERT Pre-Training

Paper • 2610.15028 • Published 27 days ago • 62

upvoted a collection 18 days ago

🔮Decision 3.0

Collection

Towards Open Multimodal Foundation Decision Models • 9 items • Updated 12 days ago • 135

upvoted a collection about 1 month ago

LLM-jp-4.1 Models

Collection

6 items • Updated Sep 28 • 10

upvoted an article about 1 month ago

Article

tokenizers v1: encode, decode and scaling, measured

ArthurZ, sbrandeis, mcpotato, lysandre

•

Sep 21

• 97

upvoted 2 articles 2 months ago

Article

Training a coding model to paint watercolours with TRL and OpenEnv

sergiopaniego

•

Sep 3

• 82

Article

Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers

tomaarsen

•

Aug 26

• 144

upvoted 7 articles 3 months ago

Article

Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers

tomaarsen, NohTow, raphaelsty

•

Aug 18

• 120

Article

What We Learned by Reproducing 2,200 papers from ICML

abidlabs

•

Aug 13

• 121

Article

SSE in Practice: Fast Static Embeddings You Can Train, Serve, and Plug Into Your Agents

RikkaBotan

•

Jun 13

• 2

Article

SSE Retrieval MRL v2: Regularization of Representation Space and Performance Improvement via Hyperparameter Optimization

RikkaBotan

•

May 13

• 4

Article

SSE (Stable Static Embedding): Unlocking the Potential of Static Embeddings, A Dynamic Tanh Normalization Approach without Speed Penalty

RikkaBotan

•

Mar 14

• 5

Article

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

lightonai

•

Jul 30

• 41

Article

MTEB Leaderboard: From a slow demo to feature-rich leaderboard

Samoed

•

Jun 12

• 23

upvoted 4 articles 4 months ago

Article

Security incident disclosure — July 2026

system

•

Jul 16

• 814

Article

NVIDIA Nemotron 3 Embed Ranks #1 Overall on RTEB, Advancing Agentic Retrieval

nvidia

•

Jul 16

• 58

Article

Native-speed vLLM transformers modeling backend

hmellor, lysandre

•

Jul 8

• 77

Article

Featuring Every Eval Ever Results on Hugging Face Model Pages

deepmage121, evijit, SaylorTwift, janbatzner, borgr, irenesolaiman, julien-c

•

Jun 30

• 55

upvoted a paper 5 months ago

KaLM-Reranker-V1: Fast but Not Late Interaction for Compressed Document Reranking

Paper • 2606.22807 • Published Jun 22 • 50

Yuichi Tateno PRO

AI & ML interests

Recent Activity

Organizations

hotchpotch's activity

Tokenmaxxing BERT: 50x faster tokenization

SlideOn & mSlideOn: Sparsified Late-Interaction and Dense Retrievers

tokenizers v1: encode, decode and scaling, measured

Training a coding model to paint watercolours with TRL and OpenEnv

Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers

Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers

What We Learned by Reproducing 2,200 papers from ICML

SSE in Practice: Fast Static Embeddings You Can Train, Serve, and Plug Into Your Agents

SSE Retrieval MRL v2: Regularization of Representation Space and Performance Improvement via Hyperparameter Optimization

SSE (Stable Static Embedding): Unlocking the Potential of Static Embeddings, A Dynamic Tanh Normalization Approach without Speed Penalty

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

MTEB Leaderboard: From a slow demo to feature-rich leaderboard

Security incident disclosure — July 2026

NVIDIA Nemotron 3 Embed Ranks #1 Overall on RTEB, Advancing Agentic Retrieval

Native-speed vLLM transformers modeling backend

Featuring Every Eval Ever Results on Hugging Face Model Pages