代码库
Official repository for "AM-RADIO: Reduce All Domains Into One"
Python
[CVPR 2025] Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone
Python
deep-learningfoundation-modelshuggingface-transformershybrid-modelsimage-classificationinstance-segmentationmambaobject-detectionself-attentionsemantic-segmentationtransformersvision-transformervisual-recognition
SoL-Pi: Scaling Auto-Research Loops for Efficient Agent Harnesses
TypeScript
AlpaGym is a reinforcement-learning framework for end-to-end autonomous-driving policies.
Python
autonomous-drivingautonomous-vehiclesclosed-loop-simulationend-to-end-drivingnvidiaphysical-aipolicy-learningreinforcement-learningrlroboticsself-driving-carsimulation
Official Code Release of SAGE: Scalable Agentic 3D Scene Generation for Embodied AI
Python
Speed of Light Analysis for ML Model Runtime
Python
[ICML 2025] RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression
Python
efficient-inferencelarge-language-modelspytorchtransformers
AutoGaze automatically removes redundant patches in a video, reducing #tokens in ViT/MLLM by 4x-100x.
Python
Sionna RT: The Ray Tracing Package of Sionna
Jupyter Notebook
channelcommunicationscoverage-mapsdifferentiable-simulationgpu-accelerationopen-sourceradio-mapsradio-propagationraytracingreproducible-research
FDFO: Finite Difference Flow Optimization
Python
Verilog evaluation benchmark for large language model
SystemVerilog
NVIDIA Alpamayo 1.5 Nano is an open 10B reasoning VLA model for autonomous vehicles with reinforcement-learning enhanced reasoning, navigation guidance, and visual question answering.
Python
alpamayoautonomous-drivingautonomous-vehicleschain-of-causationend-to-end-drivingnvidiaphysical-aireasoningroboticsself-driving-cartrajectory-predictionvision-language-actionvisual-question-answeringvlaworld-models
[CVPR 2025] Mosaic3D: Foundation Dataset and Model for Open-vocabulary 3D Segmentation
Python
CGBN: CUDA Accelerated Multiple Precision Arithmetic (Big Num) using Cooperative Groups
Cuda
Official PyTorch Implementation of Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention
Python
Python
Monocular whole-body 3D human pose estimation using the SOMA body model
Python
DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement Learning
Python
efficiencyefficient-reasoningllmreasoning
cuTAMP: Differentiable GPU-Parallelized Task and Motion Planning
Python
curobogpu-accelerationoptimization-based-planningplanningroboticssampling-based-planningtask-and-motion-planning
Flow Map OPD for AnyStep Video Diffusion
Python