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

conglu authored a paper 9 days ago

The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning

conglu authored a paper 9 days ago

The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

yuki-imajuku updated a model 9 days ago

SakanaAI/Metom

View all activity

SakanaAI's activity

conglu

authored 2 papers 9 days ago

The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning

Paper • 2402.12527 • Published Feb 19, 2024

The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

Paper • 2504.08066 • Published 13 days ago • 10

yuki-imajuku

updated a model 9 days ago

SakanaAI/Metom

Updated 9 days ago • 81 • 1

Taishi-N324

authored a paper 22 days ago

Building Instruction-Tuning Datasets from Human-Written Instructions with Open-Weight Large Language Models

Paper • 2503.23714 • Published 24 days ago

tkasasagi

published a model 23 days ago

SakanaAI/Llama-3-Karamaru-v1

Text Generation • Updated 23 days ago • 1.18k • 14

tkasasagi

published a Space 23 days ago

Llama 3 Karamaru V1

Classical Japanese Chatbot

tkasasagi

updated a model 23 days ago

SakanaAI/Llama-3-Karamaru-v1

Text Generation • Updated 23 days ago • 1.18k • 14

tkasasagi

updated a Space 24 days ago

Llama 3 Karamaru V1

Classical Japanese Chatbot

mkshing

updated a model 24 days ago

SakanaAI/Llama-3-Karamaru-v1

Text Generation • Updated 23 days ago • 1.18k • 14

Taishi-N324

authored 3 papers about 2 months ago

Balancing Speed and Stability: The Trade-offs of FP8 vs. BF16 Training in LLMs

Paper • 2411.08719 • Published Nov 10, 2024

Why We Build Local Large Language Models: An Observational Analysis from 35 Japanese and Multilingual LLMs

Paper • 2412.14471 • Published Dec 19, 2024

Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Branching Tree Search

Paper • 2503.04412 • Published Mar 6 • 1

iwiwi

authored 2 papers about 2 months ago

Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Branching Tree Search

Paper • 2503.04412 • Published Mar 6 • 1

Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization

Paper • 2502.19261 • Published Feb 26 • 7

Taishi-N324

authored a paper about 2 months ago

Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization

Paper • 2502.19261 • Published Feb 26 • 7

takkyu2

authored a paper 3 months ago

TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models

Paper • 2501.16937 • Published Jan 28 • 6

iwiwi

authored a paper 3 months ago

TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models

Paper • 2501.16937 • Published Jan 28 • 6

mkshing

authored 2 papers 3 months ago

Release of Pre-Trained Models for the Japanese Language

Paper • 2404.01657 • Published Apr 2, 2024 • 1

TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models

Paper • 2501.16937 • Published Jan 28 • 6

lfsm

authored a paper 3 months ago

$\text{Transformer}^2$: Self-adaptive LLMs

Paper • 2501.06252 • Published Jan 9 • 55