MAGI-1: Autoregressive Video Generation at Scale

[CVPR 2025] GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding

The first decoder-only multimodal state space model

Pathology Foundation Model - Nature Medicine

finetuning SAM with non-promptable decoder on medical images

From a video, automatically create an Instance Segmentation dataset using Detectors like YoloX and Segment Anything

[MedIA'25] UN-SAM: Domain-Adaptive Self-Prompt Segmentation for Universal Nuclei Images

[AAAI 2025] Linear-complexity Visual Sequence Learning with Gated Linear Attention

[ICLR 2025] This is the official repository of our paper "MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine“

Segment Anything in Medical Images

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

[KBS'25] NuSegDG: Integration of Heterogeneous Space and Gaussian Kernel for Domain-Generalized Nuclei Segmentation

[CVPR 2025 Highlight] Truncated Diffusion Model for Real-Time End-to-End Autonomous Driving

[ECCV 2024] Code for "Unleashing the Power of Prompt-driven Nucleus Instance Segmentation"

Bridging Large Vision-Language Models and End-to-End Autonomous Driving

Swin-LiteMedSAM: A Lightweight Box-Based Segment Anything Model for Large-Scale Medical Image Datasets

Accepted in CVPR 2023

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

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…

[arXiv '24] Efficient Cell Nuclei Instance Segmentation with Large Convolution Kernels

Multi-modality pre-training

Code for CVPR25 paper "VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos"

Video Highlight generation using short time analysis and keyframe algorithm

[ECCV 2024🔥] Official implementation of the paper "ST-LLM: Large Language Models Are Effective Temporal Learners"

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

mllm-npu: training multimodal large language models on Ascend NPUs

Official Repository of paper VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding