Future-House / ldp
Agent framework for constructing language model agents and training on constructive tasks.
☆67Updated this week
Alternatives and similar repositories for ldp:
Users that are interested in ldp are comparing it to the libraries listed below
- Gymnasium framework for training language model agents on constructive tasks☆153Updated 2 weeks ago
- Evaluation dataset for AI systems intended to benchmark capabilities foundational to scientific research in biology☆41Updated last month
- ☆66Updated 5 months ago
- Automated Hypothesis Testing with Agentic Sequential Falsifications☆159Updated last month
- reasoning model trained using GRPO towards rosetta REF2015 for protein stability☆57Updated last week
- Your favourite classical machine learning algos on the GPU/TPU☆20Updated 2 months ago
- ☆36Updated 5 months ago
- An aviary-based data science agent based on jupyter notebooks☆11Updated last week
- A virtual environment for developing and evaluating automated scientific discovery agents.☆136Updated 2 weeks ago
- Discovering Data-driven Hypotheses in the Wild☆64Updated 4 months ago
- LitQA Eval: A difficult set of scientific questions that require context of full-text research papers to answer☆38Updated 3 months ago
- Pretraining Code for METAGENE-1☆64Updated 2 months ago
- ☆99Updated 3 weeks ago
- ☆43Updated last year
- look how they massacred my boy☆63Updated 5 months ago
- Graph-Aware Attention for Adaptive Dynamics in Transformers☆55Updated 2 months ago
- Evaluation of neuro-symbolic engines☆35Updated 7 months ago
- Discovering Interpretable Features in Protein Language Models via Sparse Autoencoders☆163Updated last month
- BioDiscoveryAgent is an LLM-based AI agent for closed-loop design of genetic perturbation experiments☆51Updated 3 months ago
- Benchmark for LLM-based Agents in Computational Biology☆26Updated last week
- Train your own SOTA deductive reasoning model☆81Updated 2 weeks ago
- A virtual lab of LLM agents for science research☆146Updated last month
- ☆105Updated 3 months ago
- ☆28Updated last month
- A MAD laboratory to improve AI architecture designs 🧪☆108Updated 3 months ago
- ☆38Updated 7 months ago
- CiteME is a benchmark designed to test the abilities of language models in finding papers that are cited in scientific texts.☆43Updated 4 months ago
- ☆54Updated 2 weeks ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆91Updated 2 weeks ago
- A DSPy-based implementation of the tree of thoughts method (Yao et al., 2023) for generating persuasive arguments☆75Updated 5 months ago