Takumi Okoshi's picture

Takumi Okoshi

takuoko

·

AI & ML interests

None yet

Recent Activity

liked a model 7 days ago

iitolstykh/VIBE-Image-Edit

liked a model 13 days ago

zai-org/GLM-Image

liked a model 15 days ago

DAGroup-PKU/MHLA

View all activity

Organizations

upvoted 2 collections 20 days ago

Qwen3-VL-Embedding

2 items • Updated 20 days ago • 57

Qwen3-VL-Reranker

2 items • Updated 20 days ago • 38

upvoted 2 collections about 1 month ago

LLaDA 2.0

7 items • Updated about 15 hours ago • 40

T5Gemma 2

3 items • Updated Dec 18, 2025 • 66

upvoted an article 3 months ago

Article

Nemotron-Personas-Japan: Synthesized Data for Sovereign AI

Sep 23, 2025

•

27

upvoted a collection 6 months ago

CompassVerifier

CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward • 5 items • Updated Aug 31, 2025 • 7

upvoted a collection 7 months ago

Tar

[NeurIPS 2025] Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations • 11 items • Updated Sep 20, 2025 • 1

upvoted a collection 9 months ago

ReflectionFlow release

https://diffusion-cot.github.io/reflection2perfection/ • 6 items • Updated Apr 23, 2025 • 13

upvoted a collection 10 months ago

Science-T2I

Addressing Scientific Illusions in Image Synthesis • 10 items • Updated Apr 27, 2025 • 4

upvoted 2 collections 12 months ago

SFTvsRL Models & Data

This collection contains 4 initial checkpoints for https://github.com/LeslieTrue/SFTvsRL and necessary data for V-IRL training. • 7 items • Updated Mar 13, 2025 • 9

Eagle

Eagle is a family of frontier vision-language models with data-centric strategies. The model supports both HD image and long-context video input. • 15 items • Updated 8 days ago • 38

upvoted a collection over 1 year ago

Mantis

Mantis model family optimized for multi-image reasoning with interleaved text/image format • 11 items • Updated Jul 2, 2024 • 11

upvoted 2 collections almost 2 years ago

Pile-T5

T5 trained on the Pile with Llama Tokenizer • 4 items • Updated Feb 26, 2025 • 18

MGM

Official model collection for the paper "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models" • 13 items • Updated May 3, 2024 • 47