Framework to reduce autotune overhead to zero for well known deployments.

Official code of *Virgo: A Preliminary Exploration on Reproducing o1-like MLLM*

LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding

RLAIF-V: Aligning MLLMs through Open-Source AI Feedback for Super GPT-4V Trustworthiness

The official implementation of Tensor ProducT ATTenTion Transformer (T6)

MiniCPM-o 2.6: A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone

GRAPE: Guided-Reinforced Vision-Language-Action Preference Optimization

✨✨VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction

A comprehensive video analysis tool that combines computer vision, audio transcription, and natural language processing to generate detailed descriptions of video content. This tool extracts key fr…

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

3D Occupancy Prediction Benchmark in Autonomous Driving

[ECCV 2024] Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction

The public-facing frontend, www.svlsimulator.com

Large Driving Models

GaussianAD: Gaussian-Centric End-to-End Autonomous Driving

The official repo for the paper "In-Context Imitation Learning via Next-Token Prediction"

LLaVA-Mini is a unified large multimodal model (LMM) that can support the understanding of images, high-resolution images, and videos in an efficient manner.

🔥 Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos

A collection of reference AI microservices and workflows for Jetson Platform Services

Cosmos is a world model development platform that consists of world foundation models, tokenizers and video processing pipeline to accelerate the development of Physical AI at Robotics & AV labs. C…

A Telegram bot to recommend arXiv papers

FastBee开源物联网平台，简单易用，可用于搭建物联网平台以及二次开发和学习。适用于智能家居、智慧办公、智慧社区、农业监测、水利监测、工业控制等。

VLM-RL: A Unified Vision Language Models and Reinforcement Learning Framework for Safe Autonomous Driving

🔥 Official impl. of "TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation".

Low-level locomotion policy training in Isaac Lab

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.