Stars
Physics-inspired transformer modules based on mean-field dynamics of vector-spin models in JAX
Implicit Generation and Generalization in Energy Based Models in PyTorch
Thermodynamic Hypergraphical Model Library in JAX
Excitation-inhibition balance brain network fitting
Binarized Neural Network (BNN) for pytorch
Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型
Source code for "Place Cells as Position Embeddings of Multi-Step Random Walk Transition Kernels -- Euclideanized and Sparsified Cognitive Maps for Path Planning" In NeurIPS 2025
Code for Implicit Generation and Generalization with Energy Based Models
Unofficial implementation of Titans, SOTA memory for transformers, in Pytorch
GPU-optimized framework for training diffusion language models at any scale. The backend of Quokka, Super Data Learners, and OpenMoE 2 training.
Cambrian-S: Towards Spatial Supersensing in Video
This is the official implementation for paper "On Powerful Ways to Generate: Autoregression, Diffusion, and Beyond".
Training VLM agents with multi-turn reinforcement learning
MMaDA - Open-Sourced Multimodal Large Diffusion Language Models
[ICLR 2020] Contrastive Representation Distillation (CRD), and benchmark of recent knowledge distillation methods
🍓 Build and train energy-based and diffusion models in PyTorch ⚡.