Sakana AI

company

Verified

https://sakana.ai/

AI & ML interests

We are a Tokyo-based R&D company on a quest to create a new kind of foundational AI model based on nature-inspired intelligence.

Recent Activity

speed updated a dataset 9 days ago

SakanaAI/EDINET-Bench

Rujikorn new activity 13 days ago

SakanaAI/doc-to-lora:This is one of the more amazing papers I've seen

Rujikorn published a dataset 16 days ago

SakanaAI/self_gen_qa_d2l

View all activity

Papers

Fast-weight Product Key Memory

RePo: Language Models with Context Re-Positioning

View all Papers

speed

updated a dataset 9 days ago

SakanaAI/EDINET-Bench

Viewer • Updated 9 days ago • 2.59k • 409 • 10

in SakanaAI/doc-to-lora 13 days ago

This is one of the more amazing papers I've seen

#1 opened 15 days ago by

published a dataset 16 days ago

SakanaAI/self_gen_qa_d2l

Viewer • Updated about 1 month ago • 9.91M • 9.5k

published a model 16 days ago

SakanaAI/doc-to-lora

Updated about 1 month ago • 12

tksii

authored 2 papers 19 days ago

EDINET-Bench: Evaluating LLMs on Complex Financial Tasks using Japanese Financial Statements

Paper • 2506.08762 • Published Jun 10, 2025

How Can I Publish My LLM Benchmark Without Giving the True Answers Away?

Paper • 2505.18102 • Published May 23, 2025

speed

authored 4 papers 26 days ago

WAON: Large-Scale and High-Quality Japanese Image-Text Pair Dataset for Vision-Language Models

Paper • 2510.22276 • Published Oct 25, 2025 • 3

Llama-Mimi: Speech Language Models with Interleaved Semantic and Acoustic Tokens

Paper • 2509.14882 • Published Sep 18, 2025 • 1

EDINET-Bench: Evaluating LLMs on Complex Financial Tasks using Japanese Financial Statements

Paper • 2506.08762 • Published Jun 10, 2025

llm-jp-modernbert: A ModernBERT Model Trained on a Large-Scale Japanese Corpus with Long Context Length

Paper • 2504.15544 • Published Apr 22, 2025

updated a model 27 days ago

SakanaAI/Metom

5.64M • Updated 27 days ago • 402 • 6

updated a dataset about 1 month ago

SakanaAI/self_gen_qa_d2l

Viewer • Updated about 1 month ago • 9.91M • 9.5k

updated a model about 1 month ago

SakanaAI/doc-to-lora

Updated about 1 month ago • 12

authored a paper about 1 month ago

On the Optimal Reasoning Length for RL-Trained Language Models

Paper • 2602.09591 • Published Feb 10 • 5

in SakanaAI/Llama-2-7b-hf-DroPE about 2 months ago

Make the model loading self-contained

#2 opened about 2 months ago by

published a model 2 months ago

SakanaAI/Llama-2-7b-hf-DroPE

7B • Updated Jan 20 • 59 • 2

updated a collection 2 months ago

DroPE

Extending the Context of Pretrained LLMs by Dropping Their Positional Embedding (https://www.arxiv.org/abs/2512.12167) • 1 item • Updated Jan 11 • 2

updated a model 2 months ago

SakanaAI/Llama-2-7b-hf-DroPE

7B • Updated Jan 20 • 59 • 2

in SakanaAI/Llama-2-7b-hf-DroPE 2 months ago

Upload folder using huggingface_hub

#1 opened 2 months ago by

in SakanaAI/Llama-2-7b-hf-DroPE 2 months ago

Upload folder using huggingface_hub

#1 opened 2 months ago by