55 428

Kazuaki Hiraga

kazuakey

AI & ML interests

NLP, Sentiment Analysis, Named Entity Recognition

Recent Activity

liked a model 13 days ago

CohereLabs/cohere-transcribe-03-2026

liked a model 16 days ago

sbintuitions/sarashina2.2-tts

liked a model 21 days ago

openai/privacy-filter

View all activity

Organizations

upvoted an article 3 months ago

Article

Transformers.js v4: Now Available on NPM!

Xenova, nico-martin

•

Feb 9

• 95

upvoted a collection 5 months ago

OpenProvence

Collection

OpenProvence is a fully open-source implementation of Provence-style reranker–pruner models. These models remove irrelevant context while simultaneous • 5 items • Updated Oct 30, 2025 • 1

upvoted an article 5 months ago

Article

Transformers v5: Simple model definitions powering the AI ecosystem

lysandre, ArthurZ, cyrilvallez, reach-vb

•

Dec 1, 2025

• 310

upvoted a paper 5 months ago

Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer

Paper • 2511.22699 • Published Nov 27, 2025 • 245

upvoted an article 6 months ago

Article

Small Language Models (SLM): A Comprehensive Overview

jjokah

•

Feb 22, 2025

• 150

upvoted an article 8 months ago

Article

Nemotron-Personas-Japan: Synthesized Data for Sovereign AI

nvidia

•

Sep 23, 2025

• 27

upvoted a collection 8 months ago

EmbeddingGemma

Collection

3 items • Updated Mar 12 • 118

upvoted an article 8 months ago

Article

Welcome EmbeddingGemma, Google's new efficient embedding model

tomaarsen, Xenova, alvarobartt, ariG23498, pcuenq, sergiopaniego

•

Sep 4, 2025

• 274

upvoted 2 articles 9 months ago

Article

Evaluating Audio Reasoning with Big Bench Audio

mhillsmith, georgewritescode

•

Dec 20, 2024

• 29

Article

SmolVLM - small yet mighty Vision Language Model

andito, merve, mfarre, eliebak, pcuenq

•

Nov 26, 2024

• 417

upvoted a collection 9 months ago

PEFT papers

Collection

A collection of methods that have been implemented in the 🤗 PEFT library • 12 items • Updated Jan 30, 2024 • 32

upvoted an article 9 months ago

Article

Welcome GPT OSS, the new open-source model family from OpenAI!

reach-vb, pcuenq, lewtun, clem, Rocketknight1, clefourrier, celinah, Wauplin, marcsun13, pagezyhf, ahadnagy, joaogante

•

Aug 5, 2025

• 513

upvoted a paper 9 months ago

FinTagging: An LLM-ready Benchmark for Extracting and Structuring Financial Information

Paper • 2505.20650 • Published May 27, 2025 • 17

upvoted 2 articles 10 months ago

Article

SmolLM3: smol, multilingual, long-context reasoner

eliebak, cmpatino, anton-l, edbeeching, m-ric, nouamanetazi, akseljoonas, guipenedo, hynky, clefourrier, SaylorTwift, kashif, qgallouedec, hlarcher, glutamatt, Xenova, reach-vb, ngxson, craffel, lewtun, loubnabnl, lvwerra, thomwolf

•

Jul 8, 2025

• 773

Article

Reachy Mini - The Open-Source Robot for Today's and Tomorrow's AI Builders

thomwolf, matthieu-lapeyre

•

Jul 9, 2025

• 798

upvoted a paper 10 months ago

SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Paper • 2502.14786 • Published Feb 20, 2025 • 164

upvoted an article 10 months ago

Article

SigLIP 2: A better multilingual vision language encoder

ariG23498, merve, qubvel-hf

•

Feb 21, 2025

• 212

upvoted a paper 11 months ago

FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language

Paper • 2506.20920 • Published Jun 26, 2025 • 78

upvoted a collection 11 months ago

V-JEPA 2

Collection

A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of https://ai.meta.com/blog/v-jepa-yann • 8 items • Updated Jun 13, 2025 • 212

upvoted an article about 1 year ago

Article

Tiny Agents: an MCP-powered agent in 50 lines of code

julien-c

•

Apr 25, 2025

• 308

Kazuaki Hiraga

AI & ML interests

Recent Activity

Organizations

kazuakey's activity

Transformers.js v4: Now Available on NPM!

Transformers v5: Simple model definitions powering the AI ecosystem

Small Language Models (SLM): A Comprehensive Overview

Nemotron-Personas-Japan: Synthesized Data for Sovereign AI

Welcome EmbeddingGemma, Google's new efficient embedding model

Evaluating Audio Reasoning with Big Bench Audio

SmolVLM - small yet mighty Vision Language Model

Welcome GPT OSS, the new open-source model family from OpenAI!

SmolLM3: smol, multilingual, long-context reasoner

Reachy Mini - The Open-Source Robot for Today's and Tomorrow's AI Builders

SigLIP 2: A better multilingual vision language encoder

Tiny Agents: an MCP-powered agent in 50 lines of code