Stars
OpenSeeker: A search agent with open-source data and models
Create stunning demos for free. Open-source, no subscriptions, no watermarks, and free for commercial use. An alternative to Screen Studio.
An open-sourced research agent system deeply rooted in your Zotero library.
Scalable toolkit for efficient model reinforcement
Algorithm powering the For You feed on X
An End-to-End Infrastructure for Training and Evaluating Various LLM Agents
Developer Asset Hub for NVIDIA Nemotron — A one-stop resource for training recipes, usage cookbooks, datasets, and full end-to-end reference examples to build with Nemotron models
MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.
Tongyi Deep Research, the Leading Open-source Deep Research Agent
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!
Application of Structured State Space Models to High energy physics with locality sensitive hashing
[ICLR 2025] Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
[ICML 2024] How Interpretable Are Interpretable Graph Neural Networks?
Reconstruct billions of particle trajectories with graph neural networks
[ICLR 2025 Spotlight] LayerDAG: A Layerwise Autoregressive Diffusion Model of Directed Acyclic Graphs
Tutorials for onboarding of the GNN Tracking project
All graph/GNN papers accepted at the International Conference on Machine Learning (ICML) 2024.
Explainability Library with Geometric Deep Learning for Scientific Tasks
OpenUI let's you describe UI using your imagination, then see it rendered live.
GameStream client for PCs (Windows, Mac, Linux, and Steam Link)
Fast and memory-efficient exact attention
⚡️Optimizing einsum functions in NumPy, Tensorflow, Dask, and more with contraction order optimization.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.