SakanaAI / asal
Automating the Search for Artificial Life with Foundation Models!
☆348Updated 2 weeks ago
Alternatives and similar repositories for asal:
Users that are interested in asal are comparing it to the libraries listed below
- ☆98Updated last month
- Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"☆285Updated 2 months ago
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆291Updated last month
- General multi-task deep RL Agent☆174Updated 7 months ago
- Code to train and evaluate Neural Attention Memory Models to obtain universally-applicable memory systems for transformers.☆282Updated 3 months ago
- Diffusion model derived evolutionary algorithm☆187Updated last week
- Gymnasium framework for training language model agents on constructive tasks☆127Updated this week
- Pretraining Code for METAGENE-1☆61Updated 3 weeks ago
- The boundary of neural network trainability is fractal☆194Updated 11 months ago
- Testing baseline LLMs performance across various models☆211Updated last week
- Latent Program Network (from the "Searching Latent Program Spaces" paper)☆45Updated 2 months ago
- Code for Discovering Preference Optimization Algorithms with and for Large Language Models☆177Updated 7 months ago
- Bootstrapping ARC☆94Updated 2 months ago
- Draw more samples☆185Updated 7 months ago
- Implementation of Diffusion Transformer (DiT) in JAX☆261Updated 7 months ago
- Tools for working with the Abstraction & Reasoning Corpus☆178Updated 5 months ago
- Muon optimizer for neural networks: >30% extra sample efficiency, <3% wallclock overhead☆220Updated 3 weeks ago
- Cellular Automata Accelerated in JAX☆79Updated 2 months ago
- Training Large Language Model to Reason in a Continuous Latent Space☆746Updated this week
- GRadient-INformed MoE☆261Updated 4 months ago
- Simplified Masked Diffusion Language Model☆262Updated 2 months ago
- σ-GPT: A New Approach to Autoregressive Models☆61Updated 5 months ago
- The history files when recording human interaction while solving ARC tasks☆96Updated this week
- Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAI☆271Updated 2 months ago
- Diffusion on syntax trees for program synthesis☆439Updated 7 months ago
- ☆96Updated 3 months ago
- MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering☆601Updated 2 weeks ago
- Reverse Engineering the Abstraction and Reasoning Corpus☆219Updated 3 months ago