Stars
Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long chain-of-thought reasoning processes.
New repo collection for NVIDIA Cosmos: https://github.com/nvidia-cosmos
anything you want can be built with morph cloud
Visualization of vehicle position and pose estimation in Google Earth
2025 - This is my deployment environment for real world AI robot policies, and a place to create training data for reinforcement learning and imitation learning.
Type annotations and runtime checking for shape and dtype of JAX/NumPy/PyTorch/etc. arrays. https://docs.kidger.site/jaxtyping/
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.
Entropy Based Sampling and Parallel CoT Decoding
VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.
T-GATE: Temporally Gating Attention to Accelerate Diffusion Model for Free!
Aidan Bench attempts to measure <big_model_smell> in LLMs.
GNSS satellite visibility simulation from Google Earth
Restoration for TEMPEST images using deep-learning
Utilities intended for use with Llama models.
Official implementation of the SIGGRAPH 2024 paper "A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets"
Code accompanying the paper "Massive Activations in Large Language Models"
[IEEE RA-L 2024] This repository contains the implementation code for the paper "P-GAT : Pose-Graph Attentional Network for Lidar Place Recognition".
Dynamic Gaussian Mesh: Consistent Mesh Reconstruction from Monocular Videos