Skywork ORG

SkyReels-V2: Infinite-length Film Generative model

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.

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

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

Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory

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.

Open-source SOTA multi-image editing model

Unleashing the Power of Reinforcement Learning for Math and Code Reasoners

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

SkyReels-A2: Compose anything in video diffusion transformers

SkyReels-A1: Expressive Portrait Animation in Video Diffusion Transformers

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

SkyReels V3: Multimodal Video Generation Model

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

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

Skywork Agent Skills for AI office suites, including AI PPT, AI Document, AI Excel, AI Image, AI Search/DeepResearch and AI Music. These skills can be used by any skills-compatible agent, including Claude Code, Codex CLI and OpenClaw.

[TPAMI] Gamba: Marry Gaussian Splatting with Mamba for single view 3D reconstruction

Point Cloud Mamba: Point Cloud Learning via State Space Model

Scaling Preference Data Curation via Human-AI Synergy

SkyClaw-v1.0: A Million-Context Agent Model at Ultra-Low Cost

Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models

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

No description.

project for skyreels-a3

No description.

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

No description.

Environments, tools, and benchmarks for general computer agents

A high-throughput and memory-efficient inference and serving engine for LLMs

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

Skywork Reward Model Series

[CVPR 2026] SkyReels-Text: Fine-grained Font-Controllable Text Editing for Poster Design

A Multimodal Benchmark for Evaluating Scientific Reasoning Capabilities of VLMs

No description.

No description.

No description.

No description.

No description.