Stars
Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning, achieving state-of-the-art performance on 38 out of 60 public benchmarks.
NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.
[IROS 2025 Best Paper Award Finalist & IEEE TRO 2026] The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems
Janus-Series: Unified Multimodal Understanding and Generation Models
[NeurIPS 2025] Improving Video Generation with Human Feedback
A Next-Generation Training Engine Built for Ultra-Large MoE Models
NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.
FastPillars: A Deployment-friendly Pillar-based 3D Detector
codes for RFSR: Improving ISR Diffusion Models via Reward Feedback Learning
A Versatile Video-LLM for Long and Short Video Understanding with Superior Temporal Localization Ability
OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…
A curated list of awesome knowledge-driven autonomous driving (continually updated)
UniMD: Towards Unifying Moment retrieval and temporal action Detection
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
A curated list of awesome LLM/VLM/VLA/World Model for Autonomous Driving(LLM4AD) resources (continually updated)
InstaGen: Enhancing Object Detection by Training on Synthetic Dataset, CVPR2024
✨✨Latest Advances on Multimodal Large Language Models
Project Page for "LISA: Reasoning Segmentation via Large Language Model"
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
[ICLR 2023] Official implementation of the paper "DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection"
[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation