conglu1997 / ACDLinks
Automated Capability Discovery via Foundation Model Self-Exploration
☆65Updated 8 months ago
Alternatives and similar repositories for ACD
Users that are interested in ACD are comparing it to the libraries listed below
Sorting:
- Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models☆65Updated 8 months ago
- A suite of open-ended, non-imitative tasks involving generalizable skills for large language model chatbots and agents to enable bootstra…☆41Updated 8 months ago
- OMNI: Open-endedness via Models of human Notions of Interestingness☆57Updated 9 months ago
- ☆40Updated last year
- Repository for the paper Stream of Search: Learning to Search in Language☆151Updated 8 months ago
- look how they massacred my boy☆63Updated last year
- Skill Design From AI Feedback☆31Updated 8 months ago
- Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.☆188Updated 7 months ago
- ☆93Updated 4 months ago
- accompanying material for sleep-time compute paper☆117Updated 5 months ago
- ☆135Updated 7 months ago
- Collection of LLM completions for reasoning-gym task datasets☆30Updated 3 months ago
- ☆142Updated last month
- The Prime Intellect CLI provides a powerful command-line interface for managing GPU resources across various providers☆100Updated last week
- ☆124Updated 10 months ago
- A virtual environment for developing and evaluating automated scientific discovery agents.☆188Updated 7 months ago
- Training-Ready RL Environments + Evals☆132Updated this week
- ☆11Updated last year
- OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code (ICLR 2025).☆69Updated 10 months ago
- Alice in Wonderland code base for experiments and raw experiments data☆131Updated last month
- Open source interpretability artefacts for R1.☆163Updated 6 months ago
- Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data genera…☆97Updated this week
- ☆51Updated 3 months ago
- QAlign is a new test-time alignment approach that improves language model performance by using Markov chain Monte Carlo methods.☆24Updated this week
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆172Updated 9 months ago
- Latent Program Network (from the "Searching Latent Program Spaces" paper)☆102Updated 3 weeks ago
- Public repository containing METR's DVC pipeline for eval data analysis☆124Updated 6 months ago
- Implementation of SOAR☆42Updated last month
- Intrinsic Motivation from Artificial Intelligence Feedback☆131Updated last year
- ☆123Updated last year