google-deepmind / alphaevolve_resultsLinks
☆224Updated 2 months ago
Alternatives and similar repositories for alphaevolve_results
Users that are interested in alphaevolve_results are comparing it to the libraries listed below
Sorting:
- ☆443Updated 3 months ago
- Training teachers with reinforcement learning able to make LLMs learn how to reason for test time scaling.☆329Updated 2 months ago
- ☆474Updated last month
- ☆264Updated 4 months ago
- Decentralized RL Training at Scale☆472Updated this week
- Evaluation of LLMs on latest math competitions☆160Updated 2 weeks ago
- Repository for Zochi's Research☆258Updated last month
- Self-Adapting Language Models☆770Updated 3 weeks ago
- ☆177Updated last week
- Open source interpretability artefacts for R1.☆158Updated 4 months ago
- Testing baseline LLMs performance across various models☆305Updated 2 weeks ago
- Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'☆229Updated last month
- Code for the paper: "Learning to Reason without External Rewards"☆347Updated last month
- ☆200Updated 4 months ago
- ☆94Updated last month
- ☆69Updated last week
- Scaling Data for SWE-agents☆378Updated this week
- ☆275Updated 3 weeks ago
- Preference-based Recursive Language Modeling for Exploratory Optimization of Reasoning☆229Updated 6 months ago
- MLGym A New Framework and Benchmark for Advancing AI Research Agents☆546Updated 2 weeks ago
- Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"☆327Updated 9 months ago
- ☆89Updated 2 months ago
- ☆213Updated 6 months ago
- Technical report of Kimina-Prover Preview.☆323Updated last month
- A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning☆245Updated 2 weeks ago
- Pretraining and inference code for a large-scale depth-recurrent language model☆816Updated last month
- AlgoTune is a benchmark made up of 154 math, physics, and computer science problems. The goal is write code that solves each problem, and…☆51Updated 2 weeks ago
- ☆79Updated last week
- ☆621Updated last month
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆344Updated 8 months ago