Stars
ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program Evolution
Training teachers with reinforcement learning able to make LLMs learn how to reason for test time scaling.
The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
A lightweight framework for evaluating visual-language models.
A live stream development of RL tunning for LLM agents
Atomistic simulation hands on tutorial on Matlantis
Browser-based chat UI for TinySwallow-1.5B that runs without API calls.
Japanese Language Model Financial Evaluation Harness
Python-based chat demo for TinySwallow-1.5B that works completely offline
PaSa -- an advanced paper search agent powered by large language models. It can autonomously make a series of decisions, including invoking search tools, reading papers, and selecting relevant refe…
Official repository of Evolutionary Optimization of Model Merging Recipes
Heat-conductivity benchmark test for foundational machine-learning potentials
[ICLR 2025] Automated Design of Agentic Systems
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
A Self-adaptation Framework🐙 that adapts LLMs for unseen tasks in real-time!
New repo collection for NVIDIA Cosmos: https://github.com/nvidia-cosmos
A collection of AI Agents papers (Updated biweekly)
A generative world for general-purpose robotics & embodied AI learning.
This repository includes the official implementation of OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs.
Train transformer language models with reinforcement learning.
Github Copilot-like LSP code completion server with local LLM powered by llama.cpp