[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

Macaw-LLM: Multi-Modal Language Modeling with Image, Video, Audio, and Text Integration

A Fair and Scalable Time Series Forecasting Benchmark and Toolkit.

Recipes to train reward model for RLHF.

A Semantic Controllable Self-Supervised Learning Framework to learn general human representations from massive unlabeled human images, which can benefit downstream human-centric tasks to the maximu…

Official Repo For "Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos"

[ICLR'23 Spotlight🔥] The first successful BERT/MAE-style pretraining on any convolutional network; Pytorch impl. of "Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling"

Real-time and accurate open-vocabulary end-to-end object detection

[CVPR 2025] Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer

Official Repo For OMG-LLaVA and OMG-Seg codebase [CVPR-24 and NeurIPS-24]

Uncommon Objects in 3D dataset

VGGSfM: Visual Geometry Grounded Deep Structure From Motion

[CVPR'23] Universal Instance Perception as Object Discovery and Retrieval

Unified KV Cache Compression Methods for Auto-Regressive Models

一账通是一款开源的统一身份认证授权管理解决方案，支持多种标准协议(LDAP, OAuth2, SAML, OpenID)，细粒度权限控制，完整的WEB管理功能，钉钉、企业微信集成等，QQ group: 167885406

A plugin for IDA that can help to analyze binary file, it can be based on commonly used AI big models such as OpenAI and DeepSeek.

Res-SAM Framework for GPR Underground Hazard Detection

[NIPS'25 Spotlight] Mulberry, an o1-like Reasoning and Reflection MLLM Implemented via Collective MCTS

[CVPR'25]Tora: Trajectory-oriented Diffusion Transformer for Video Generation

One repository is all that is necessary for Multi-agent Reinforcement Learning (MARL)

[NeurIPS 2024] DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation

AI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment.

[CVPR2024 Highlight]GLEE: General Object Foundation Model for Images and Videos at Scale

PyTorch Implementation of AudioLCM (ACM-MM'24): a efficient and high-quality text-to-audio generation with latent consistency model.

[Neurips 2025] R-KV: Redundancy-aware KV Cache Compression for Reasoning Models

PantoMatrix: Generating Face and Body Animation from Speech

RLinf is a flexible and scalable open-source infrastructure designed for post-training foundation models (LLMs, VLMs, VLAs) via reinforcement learning.

[ICLR 2025 Oral] TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio-Motion Embedding and Diffusion Interpolation

Allegro is a powerful text-to-video model that generates high-quality videos up to 6 seconds at 15 FPS and 720p resolution from simple text input.