Kazuaki Hiraga's picture

51 418

Kazuaki Hiraga

kazuakey

·

AI & ML interests

NLP, Sentiment Analysis, Named Entity Recognition

Recent Activity

upvoted an article about 17 hours ago

Small Language Models (SLM): A Comprehensive Overview

liked a model 7 days ago

ggml-org/gemma-3n-E2B-it-GGUF

liked a dataset 7 days ago

nvidia/Nemotron-VLM-Dataset-v2

View all activity

Organizations

upvoted an article about 17 hours ago

Article

Small Language Models (SLM): A Comprehensive Overview

Feb 22

•

103

upvoted an article about 2 months ago

Article

Nemotron-Personas-Japan: Synthesized Data for Sovereign AI

Sep 23

•

27

upvoted a collection 2 months ago

EmbeddingGemma

3 items • Updated Sep 11 • 97

upvoted an article 2 months ago

Article

Welcome EmbeddingGemma, Google's new efficient embedding model

Sep 4

•

256

upvoted 2 articles 3 months ago

Article

Evaluating Audio Reasoning with Big Bench Audio

Dec 20, 2024

•

26

Article

SmolVLM - small yet mighty Vision Language Model

Nov 26, 2024

•

382

upvoted a collection 3 months ago

PEFT papers

A collection of methods that have been implemented in the 🤗 PEFT library • 12 items • Updated Jan 30, 2024 • 31

upvoted an article 3 months ago

Article

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

Aug 5

•

505

upvoted a paper 3 months ago

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

Paper • 2505.20650 • Published May 27 • 17

upvoted 2 articles 4 months ago

Article

SmolLM3: smol, multilingual, long-context reasoner

Jul 8

•

721

Article

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

Jul 9

•

711

upvoted a paper 5 months ago

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

Paper • 2502.14786 • Published Feb 20 • 154

upvoted an article 5 months ago

Article

SigLIP 2: A better multilingual vision language encoder

Feb 21

•

192

upvoted a paper 5 months ago

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

Paper • 2506.20920 • Published Jun 26 • 75

upvoted a collection 5 months ago

V-JEPA 2

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 • 170

upvoted an article 6 months ago

Article

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

Apr 25

•

302

upvoted a paper 8 months ago

Survey on Evaluation of LLM-based Agents

Paper • 2503.16416 • Published Mar 20 • 95

upvoted a collection 8 months ago

Gemma 3 Release

28 items • Updated Aug 11 • 533

upvoted a paper 9 months ago

Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning

Paper • 2502.14768 • Published Feb 20 • 47

upvoted a paper 10 months ago

Towards Best Practices for Open Datasets for LLM Training

Paper • 2501.08365 • Published Jan 14 • 63