SakanaAI

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

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

Continuous Thought Machines, because thought takes time and reasoning is a process.

ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program Evolution 🧬

Official repository of Evolutionary Optimization of Model Merging Recipes

Hypernetworks that adapt LLMs for specific benchmark tasks using only textual task description as the input

A Self-adaptation Framework🐙 that adapts LLMs for unseen tasks in real-time!

Hypernetworks that update LLMs to remember factual information

The Agentic Scientist: Orchestrating Coding Agents for Automated Scientific (Co-)Discovery

A Tree Search Library with Flexible API for LLM Inference-Time Scaling

Automating the Search for Artificial Life with Foundation Models!

Training teachers with reinforcement learning able to make LLMs learn how to reason for test time scaling.

Code to train and evaluate Neural Attention Memory Models to obtain universally-applicable memory systems for transformers.

Multi-Agent Self-Supervision

DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation

Cuda kernels for leveraging LLM sparsity to improve throughput and decrease the memory requirements during inference and training.

PC-ALM

The official repository of ALE-Bench

Digital Red Queen: Adversarial Program Evolution in Core War with LLMs

Extending the Context of Pretrained LLMs by Dropping Their Positional Embedding

The code repository of the paper: Competition and Attraction Improve Model Fusion

Browser-based chat UI for TinySwallow-1.5B that runs without API calls.

Official implementation of "TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models"

Generate publication-ready, editable draw.io figures for research papers from a methods section, using LLM agents.

Interactive multi-agent NCA ecosystem simulation

RePo: Language Models with Context Re-Positioning

Sheaf-ADMM

Python-based chat demo for TinySwallow-1.5B that works completely offline

Reimagining Agent-based Modeling with Large Language Model Agents via Shachi