HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation

Janus-Series: Unified Multimodal Understanding and Generation Models

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

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

An open-source implementaion for fine-tuning Qwen2-VL and Qwen2.5-VL series by Alibaba Cloud.

从底层机理了解Transformer

[ICCV2023] Official Implementation of "UniTR: A Unified and Efficient Multi-Modal Transformer for Bird’s-Eye-View Representation"

Offical PyTorch implementation of "BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework"

[ICRA'23] BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation

SECOND for KITTI/NuScenes object detection

[ECCV 2024] OPEN: Object-wise Position Embedding for Multi-view 3D Object Detection

The official GitHub page for the review paper "Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models".

[AAAI-25] Cobra: Extending Mamba to Multi-modal Large Language Model for Efficient Inference

[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.

[CVPR 2022] PointCLIP: Point Cloud Understanding by CLIP

[CVPR 2023] Hierarchical Supervision and Shuffle Data Augmentation for 3D Semi-Supervised Object Detection

[AAAI 2024] BEV-MAE: Bird's Eye View Masked Autoencoders for Point Cloud Pre-training in Autonomous Driving Scenarios

[ECCV 2024] Embodied Understanding of Driving Scenarios

HEDNet (NeurIPS 2023) & SAFDNet (CVPR 2024 Oral)

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

🤖 PaddleViT: State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 2.0+

🤖 PaddleViT: State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 2.0+

[ICCV 2021] Official Pytorch implementation for Discriminative Region-based Multi-Label Zero-Shot Learning SOTA results on NUS-WIDE and OpenImages

LAVIS - A One-stop Library for Language-Vision Intelligence

Official implementation of "Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfer".

[ICCV 2023] SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection