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 model about 10 hours ago

tori29umai/rtdetrv4-x-manga109s

liked a dataset 2 days ago

openai/healthbench-professional

liked a dataset 2 days ago

AlicanKiraz0/Cybersecurity-Dataset-Fenrir-v2.1

View all activity

Organizations

upvoted a paper 3 days ago

World-R1: Reinforcing 3D Constraints for Text-to-Video Generation

Paper • 2604.24764 • Published 5 days ago • 113

upvoted a collection 4 days ago

MiMo-V2.5

4 items • Updated 4 days ago • 70

upvoted a paper 4 days ago

AVControl: Efficient Framework for Training Audio-Visual Controls

Paper • 2603.24793 • Published Mar 25 • 27

upvoted a collection 5 days ago

MiDashengLM-7B-1021

4 items • Updated Oct 27, 2025 • 2

upvoted a collection 7 days ago

DeepSeek-V4

4 items • Updated 7 days ago • 592

upvoted a collection 9 days ago

Qwen3.6

4 items • Updated 9 days ago • 289

upvoted 2 collections 11 days ago

MOSS-Audio

An open-source audio understanding model supporting speech recognition, environmental sound analysis, music understanding, time-aware QA, and complex • 5 items • Updated 11 days ago • 52

AI Images

Collect of AI-generated/assisted Images • 14 items • Updated Oct 18, 2025 • 3

upvoted a paper 12 days ago

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

Paper • 2604.14268 • Published 17 days ago • 116

upvoted a paper 13 days ago

Lyra 2.0: Explorable Generative 3D Worlds

Paper • 2604.13036 • Published 18 days ago • 39

upvoted a paper 15 days ago

Seedance 2.0: Advancing Video Generation for World Complexity

Paper • 2604.14148 • Published 17 days ago • 153

upvoted a paper 16 days ago

Nucleus-Image: Sparse MoE for Image Generation

Paper • 2604.12163 • Published 18 days ago • 11

upvoted a collection 19 days ago

Qwen3-Omni

6 items • Updated Dec 31, 2025 • 197

upvoted a collection 22 days ago

WAON

WAON: Large-Scale and High-Quality Japanese Image-Text Pair Dataset for Vision-Language Models • 4 items • Updated Mar 2 • 2

upvoted a collection 26 days ago

Bonsai

1-bit Bonsai models • 7 items • Updated 14 days ago • 189

upvoted a collection 27 days ago

日本語LLM

297 items • Updated 17 days ago • 7

upvoted 2 collections 28 days ago

Marco-MoE

A suit of multilingual MoE models with highly-sparse architectures • 5 items • Updated 23 days ago • 16

PLaMo 2-VL

2 items • Updated 28 days ago • 3

upvoted an article 28 days ago

Article

Welcome Gemma 4: Frontier multimodal intelligence on device

+5

30 days ago

•

884

upvoted a collection 29 days ago

Gemma 4

8 items • Updated 29 days ago • 705