Skywork (SkyworkAI)

Skywork

SkyworkAI

Organization data from Github https://github.com/SkyworkAI

Transfer knowledge, Unlock creativity.

Location:Singapore

Home Page:https://skywork.ai/

GitHub:@SkyworkAI

Skywork 's repositories

SkyReels-V2

SkyReels-V2: Infinite-length Film Generative model

Language:PythonLicense:NOASSERTIONStargazers:4909Issues:59Issues:84

Skywork-R1V

Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI (Kunlun Inc.), specializing in vision-language reasoning.

Language:PythonLicense:MITStargazers:2947Issues:152Issues:38

DeepResearchAgent

DeepResearchAgent is a hierarchical multi-agent system designed not only for deep research tasks but also for general-purpose task solving. The framework leverages a top-level planning agent to coordinate multiple specialized lower-level agents, enabling automated task decomposition and efficient execution across diverse and complex domains.

Language:JavaScriptLicense:MITStargazers:2860Issues:18Issues:67

SkyReels-V1

SkyReels V1: The first and most advanced open-source human-centric video foundation model

Language:PythonLicense:NOASSERTIONStargazers:2452Issues:31Issues:96

Matrix-Game

Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model

Language:PythonLicense:MITStargazers:1714Issues:70Issues:38

Skywork

Skywork series models are pre-trained on 3.2TB of high-quality multilingual (mainly Chinese and English) and code data. We have open-sourced the model, training data, evaluation data, evaluation methods, etc.

Language:PythonLicense:NOASSERTIONStargazers:1452Issues:31Issues:64

UniPic

Unified Multimodal Model for image generation/editing/understanding

Language:PythonLicense:MITStargazers:802Issues:10Issues:26

Skywork-OR1

Unleashing the Power of Reinforcement Learning for Math and Code Reasoners

Language:PythonLicense:Apache-2.0Stargazers:730Issues:13Issues:33

SkyReels-A2

SkyReels-A2: Compose anything in video diffusion transformers

Language:PythonLicense:NOASSERTIONStargazers:683Issues:18Issues:32

Vitron

NeurIPS 2024 Paper: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing

SkyReels-A1

SkyReels-A1: Expressive Portrait Animation in Video Diffusion Transformers

Language:PythonLicense:NOASSERTIONStargazers:566Issues:12Issues:22

Matrix-3D

Generate large-scale explorable 3D scenes with high-quality panorama videos from a single image or text prompt.

Language:PythonLicense:MITStargazers:552Issues:9Issues:33

MoH

MoH: Multi-Head Attention as Mixture-of-Head Attention

Language:PythonLicense:Apache-2.0Stargazers:288Issues:3Issues:5

MoE-plus-plus

[ICLR 2025] MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts

Language:PythonLicense:Apache-2.0Stargazers:250Issues:2Issues:2

Skywork-Reward-V2

Scaling Preference Data Curation via Human-AI Synergy

Stargazers:125Issues:0Issues:0
Language:PythonLicense:Apache-2.0Stargazers:98Issues:7Issues:18

skyreels-a3.github.io

project for skyreels-a3

Language:JavaScriptStargazers:72Issues:7Issues:0

MVGamba

[NeurIPS2024] MVGamba: Unify 3D Content Generation as State Space Sequence Modeling

Mureka-mcp

generate lyrics, song and background music(instrumental). Model Context Protocol (MCP) server.

Language:PythonLicense:MITStargazers:58Issues:2Issues:0

DAQ-VS

Code For Our Work: DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries [ECCV-2024]

agent-studio

Environments, tools, and benchmarks for general computer agents

Language:PythonLicense:AGPL-3.0Stargazers:12Issues:1Issues:0

CSVQA

A Multimodal Benchmark for Evaluating Scientific Reasoning Capabilities of VLMs

Language:PythonLicense:Apache-2.0Stargazers:6Issues:0Issues:0
Language:JavaScriptStargazers:5Issues:0Issues:0
Language:JavaScriptStargazers:4Issues:0Issues:0