SakanaAI / ShinkaEvolveLinks
ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program Evolution
☆773Updated this week
Alternatives and similar repositories for ShinkaEvolve
Users that are interested in ShinkaEvolve are comparing it to the libraries listed below
Sorting:
- Library for text-to-text regression, applicable to any input string representation and allows pretraining and fine-tuning over multiple r…☆305Updated 3 weeks ago
- ☆253Updated 6 months ago
- Training teachers with reinforcement learning able to make LLMs learn how to reason for test time scaling.☆355Updated 6 months ago
- Code to train and evaluate Neural Attention Memory Models to obtain universally-applicable memory systems for transformers.☆346Updated last year
- Open-source release accompanying Gao et al. 2025☆486Updated last month
- ☆213Updated 4 months ago
- An AI benchmark for creative, human-like problem solving using Sudoku variants☆147Updated 3 weeks ago
- This repo contains the source code for the paper "Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning"☆284Updated last month
- A Tree Search Library with Flexible API for LLM Inference-Time Scaling☆512Updated last month
- The official repository of ALE-Bench☆147Updated this week
- ☆600Updated 7 months ago
- 🧬 The Huxley-Gödel Machine☆317Updated last month
- Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"☆341Updated 2 months ago
- Super basic implementation (gist-like) of RLMs with REPL environments.☆390Updated this week
- MLGym A New Framework and Benchmark for Advancing AI Research Agents☆583Updated 5 months ago
- Async RL Training at Scale☆985Updated this week
- Testing baseline LLMs performance across various models☆332Updated last week
- ☆482Updated 5 months ago
- Pretraining and inference code for a large-scale depth-recurrent language model☆857Updated last week
- An interface library for RL post training with environments.☆973Updated this week
- ☆106Updated 6 months ago
- RLP: Reinforcement as a Pretraining Objective☆222Updated 3 months ago
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆366Updated last year
- Training API and CLI☆305Updated 3 weeks ago
- Automating the Search for Artificial Life with Foundation Models!☆448Updated 2 months ago
- ☆164Updated 4 months ago
- ☆277Updated 8 months ago
- Simple & Scalable Pretraining for Neural Architecture Research☆306Updated last month
- Open source interpretability artefacts for R1.☆165Updated 8 months ago
- OpenTinker is an RL-as-a-Service infrastructure for foundation models☆547Updated this week