Yasunori Ozaki's picture

In a Training Loop 🔄

Yasunori Ozaki PRO

alfredplpl

·

https://alfredplpl.github.io/en/index.html

AI & ML interests

Computer Vision, LLM

Recent Activity

liked a Space about 3 hours ago

huggingface-projects/gemma-4-31b-it

liked a model about 3 hours ago

unsloth/gemma-4-26B-A4B-it-GGUF

liked a model about 3 hours ago

unsloth/gemma-4-31B-it-GGUF

View all activity

Organizations

upvoted a collection about 3 hours ago

Gemma 4

8 items • Updated about 6 hours ago • 182

upvoted a collection 2 days ago

Sarashina2.2

Large Language Models developed by SB Intuitions. Pretrained and instruction-tuned models are available in three sizes: 0.5B, 1B, and 3B. • 6 items • Updated Mar 5, 2025 • 9

upvoted a collection 3 days ago

LLM-jp-4 Models

5 items • Updated 3 days ago • 10

upvoted a collection 7 days ago

Domain-Specific LLMs: Japanese Finance

ドメイン特化LLM：日本語金融 • 6 items • Updated 25 days ago • 3

upvoted a paper 7 days ago

Constructing Synthetic Instruction Datasets for Improving Reasoning in Domain-Specific LLMs: A Case Study in the Japanese Financial Domain

Paper • 2603.01353 • Published Mar 2 • 3

upvoted a changelog 11 days ago

Hugging Face Changelog

Protected Spaces with Public URLs

13 days ago

• 105

upvoted a paper 13 days ago

Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation

Paper • 2603.19220 • Published 14 days ago • 64

upvoted a paper 20 days ago

InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing

Paper • 2603.09877 • Published 23 days ago • 47

upvoted a paper 26 days ago

DEJIMA: A Novel Large-scale Japanese Dataset for Image Captioning and Visual Question Answering

Paper • 2512.00773 • Published Nov 30, 2025 • 1

upvoted a paper about 1 month ago

SkyReels-V4: Multi-modal Video-Audio Generation, Inpainting and Editing model

Paper • 2602.21818 • Published Feb 25 • 56

upvoted 3 collections about 1 month ago

Qwen3.5

Qwen3.5 is Qwen's new model family including Qwen3.5 Small: 0.8B, 2B, 4B, 9B and Qwen3.5 Medium: 35B-A3B, 27B, 122B-A10B and 397B-A17B. • 25 items • Updated 22 days ago • 128

GPT-OSS-Swallow-v0.1

4 items • Updated Feb 20 • 13

Qwen3-Swallow-v0.2

12 items • Updated Feb 23 • 9

upvoted an article about 1 month ago

Article

NVIDIA Nemotron 2 Nano 9B Japanese: 日本のソブリンAIを支える最先端小規模言語モデル

Feb 17

•

24

upvoted a collection about 1 month ago

BitDance

BitDance: Open-source autoregressive model with binary visual tokens. A research project for building powerful multimodal autoregressive model. • 10 items • Updated Mar 2 • 11

upvoted 2 collections about 2 months ago

Qwen3.5

21 items • Updated 24 days ago • 1.4k

NEST-Ja

Japanese speech self-supervised learning model developed by SB Intuitions. • 2 items • Updated Feb 10 • 1

upvoted a collection 3 months ago

ArrowIdeative-series

GRPOのみを事後学習に使用したモデルです。 • 5 items • Updated Jan 11 • 1

upvoted 2 papers 3 months ago

Atlas: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning

Paper • 2601.03872 • Published Jan 7 • 45

LTX-2: Efficient Joint Audio-Visual Foundation Model

Paper • 2601.03233 • Published Jan 6 • 174