Sakana AI

company

Verified

https://sakana.ai/

SakanaAI

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

Rujikorn authored a paper 6 days ago

Cleanba: A Reproducible and Efficient Distributed Reinforcement Learning Platform

Rujikorn authored a paper 6 days ago

Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning

Rujikorn authored a paper 6 days ago

TDD Without Tears: Towards Test Case Generation from Requirements through Deep Reinforcement Learning

View all activity

Rujikorn

authored 3 papers 6 days ago

Cleanba: A Reproducible and Efficient Distributed Reinforcement Learning Platform

Paper • 2310.00036 • Published Sep 29, 2023 • 2

Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning

Paper • 2402.03046 • Published Feb 5, 2024 • 6

TDD Without Tears: Towards Test Case Generation from Requirements through Deep Reinforcement Learning

Paper • 2401.07576 • Published Jan 15, 2024

Taishi-N324

authored a paper 6 days ago

Rewriting Pre-Training Data Boosts LLM Performance in Math and Code

Paper • 2505.02881 • Published May 5 • 2

Rujikorn

authored 2 papers 6 days ago

From Grunts to Grammar: Emergent Language from Cooperative Foraging

Paper • 2505.12872 • Published May 19 • 2

Text-to-LoRA: Instant Transformer Adaption

Paper • 2506.06105 • Published 22 days ago • 1

edoarc

published 2 models 6 days ago

SakanaAI/RLT-32B

Text Generation • 33B • Updated 7 days ago • 105 • 2

SakanaAI/RLT-7B

Text Generation • 8B • Updated 7 days ago • 79 • • 7

edoarc

updated a collection 7 days ago

Reinforcement Learning Teachers

Students distilled from a 7B Reinforcement-Learned Teacher (RLT) from the paper "Reinforcement Learning Teachers of Test Time Scaling." • 2 items • Updated 6 days ago • 6

edoarc

updated 2 models 7 days ago

SakanaAI/RLT-7B

Text Generation • 8B • Updated 7 days ago • 79 • • 7

SakanaAI/RLT-32B

Text Generation • 33B • Updated 7 days ago • 105 • 2

edoarc

updated a collection 7 days ago

Reinforcement Learning Teachers

Students distilled from a 7B Reinforcement-Learned Teacher (RLT) from the paper "Reinforcement Learning Teachers of Test Time Scaling." • 2 items • Updated 6 days ago • 6

iwiwi

authored 3 papers 12 days ago

Adversarial Attacks and Defences Competition

Paper • 1804.00097 • Published Mar 31, 2018

Agent Skill Acquisition for Large Language Models via CycleQD

Paper • 2410.14735 • Published Oct 16, 2024 • 2

ALE-Bench: A Benchmark for Long-Horizon Objective-Driven Algorithm Engineering

Paper • 2506.09050 • Published 18 days ago • 7

iwiwi

updated a dataset 12 days ago

SakanaAI/ALE-Bench

Updated 12 days ago • 484 • 8

yuki-imajuku

updated a dataset 12 days ago

SakanaAI/ALE-Bench

Updated 12 days ago • 484 • 8

Rujikorn

published a model 17 days ago

SakanaAI/text-to-lora

Updated 23 days ago • 6

yuki-imajuku

updated a model 18 days ago

SakanaAI/Metom

0.0B • Updated 18 days ago • 326 • 4

speed

updated a dataset 18 days ago

SakanaAI/EDINET-Bench

Viewer • Updated 18 days ago • 2.59k • 1.8k • 7