[NeurIPS 2024 Datasets and Benchmarks Track] Closed-Loop E2E-AD Benchmark Enhanced by World Model RL Expert

airda(Air Data Agent)是面向数据分析的多智能体，能够理解数据开发和数据分析需求、理解数据、生成面向数据查询、数据可视化、机器学习等任务的SQL和Python代码

VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model

RoboTwin 2.0 Offical Repo

Train your Agent model via our easy and efficient framework

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

"MiniRAG: Making RAG Simpler with Small and Open-Sourced Language Models"

【ICML 2025 Spotlight】 Official Repo for Paper ‘’HealthGPT : A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation‘’

Recipes to train reward model for RLHF.

Distributed GPU-Accelerated Framework for Evolutionary Computation. Comprehensive Library of Evolutionary Algorithms & Benchmark Problems.

[CVPR2025] We present StableAnimator, the first end-to-end ID-preserving video diffusion framework, which synthesizes high-quality videos without any post-processing, conditioned on a reference ima…

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

[TPAMI 2025🔥] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators

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

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

Uncommon Objects in 3D dataset

VGGSfM: Visual Geometry Grounded Deep Structure From Motion

( TPAMI2022 / CVPR2019 Oral ) Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation

[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

An intelligent assistant serving the entire software development lifecycle, powered by a Multi-Agent Framework, working with DevOps Toolkits, Code&Doc Repo RAG, etc.

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

[ICLR 2025] SOTA discrete acoustic codec models with 40/75 tokens per second for audio language modeling

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