Highlights
- Pro
Stars
A collection of formalized statements of conjectures in Lean.
Further computation of R(N) in #321, see https://github.com/teorth/erdosproblems/issues/161.
Official code for StochasTok: Improving Fine-Grained Subword Understanding in LLMs
Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents
The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
Automated Capability Discovery via Foundation Model Self-Exploration
Reinforcement learning on general 2D physics environments in JAX. ICLR 2025 Oral.
Benchmark for studying the imitation gap when training autonomous driving policies from human demonstrations
[ICLR 2025] Automated Design of Agentic Systems
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning
aider is AI pair programming in your terminal
Related papers for reinforcement learning, including classic papers and latest papers in top conferences
Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models
Code for Stable Control Representations
Official implementation of the RLC 2024 paper "Policy-Guided Diffusion"
Research Code for "ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL"
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
Official implementation of Reach-Aware Value Estimation (RAVL) from the paper: "The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning."
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
High throughput synchronous and asynchronous reinforcement learning
Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)
floatingsun / gpt-neox
Forked from EleutherAI/gpt-neoxAn implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.
A JAX-based simulator for autonomous driving research.