6-day longest streak
Peiyu Wang (王沛雨) Research Engineer & Tech Lead @ Skywork AI Large Language Models · Multimodal Systems · Agent Architectures [email protected] --- About Me I've been involved in the full…
Peiyu Wang (王沛雨)
Research Engineer & Tech Lead @ Skywork AI
Large Language Models · Multimodal Systems · Agent Architectures
[email protected]
---
About Me
I've been involved in the full pipeline of foundation model development — pre-training, supervised fine-tuning, RL alignment, evaluation, and production deployment. My work spans several directions:
- Video Generation: Co-developed SkyReels V4, a multimodal video model with 1080p/32FPS output and audio-video synchronization, trained with full-modal reinforcement learning.
- World Models: Built Matrix-Game 3.0, a memory-augmented interactive world model supporting 720p/40FPS real-time streaming with long-horizon consistency.
- Agent Systems: Developed SkyClaw-v1.0 and Super Agents, agent models with million-token context optimized for tool use, multi-turn execution, and code generation.
- Multimodal Reasoning: Contributed to the R1V Series (38B VLM) and UniPic Series (1.5B unified generation/understanding model).
Selected Projects
SkyReels V4 — Multimodal video generation with full-modal RL. #1 on Artificial Analysis for text-to-video with audio.
Matrix-Game 3.0 — Memory-augmented interactive world model for real-time streaming video. Paper
SkyClaw-v1.0 — Agent model with million-token context for tool use and code generation.
R1V Series — 38B VLM with multimodal chain-of-thought reasoning. Paper
UniPic Series — 1.5B unified model for image understanding, generation, and editing. Paper
VL Reward Model — Multimodal reward model for RL alignment of MLLMs.
Super Agents — End-to-end agent system for autonomous task execution.
RED Recommendation — Large-scale ranking, retrieval, and multi-objective optimization.
---
News
- ML Summit 2026 Talk — Interactive World Models
- ML Summit 2025 Talk — Agent System Design
- Skywork Office AI Super Agent — Official Launch
Skywork Office AI Super Agent
---
Media Coverage
SkyReels V4
- 量子位 — 杀进全球榜TOP2!国产视频模型黑马刚刚出现了
- 量子位 — 刚刚,全球视频模型新王诞生了!
- 机器之心 — 又一国产全模态视频大模型杀入Artificial Analysis榜单Top 2
- 新智元 — 刚刚,国产视频模型登顶全球第一
Matrix-Game 3.0
SkyClaw-v1.0
---
Research Interests
- Large-scale language models: pre-training, RL alignment, and evaluation
- Multimodal foundation models: reasoning, generation, and unified architectures
- World models: interactive simulation and robotic embodiment
- Agent systems: autonomous decision-making and tool orchestration
Contribution Activity
Built by SkyClaw v1.0 — the agent that writes resumes so you don't have to.
-
Skywork-R1V ★ PINNED ⑂
Pioneering Multimodal Reasoning with CoT
★ 2 1y agoExplain → -
Awesome-VLA ★ PINNED
✨✨latest advancements in VLA models(VIsion Language Action)
★ 120 3mo agoExplain → -
Awesome-RL-in-Generative-AI ★ PINNED
✨✨latest advancements of RL in generative ai
★ 16 10mo agoExplain → -
Orlando-CS
No description.
HTML ★ 2 19h agoExplain → -
snk ⑂
🟩⬜ Generates a snake game from a github user contributions graph and output a screen capture as animated svg or gif
★ 2 1y agoExplain → -
Awesome-Multimodal-Large-Language-Models ⑂
:sparkles::sparkles:Latest Advances on Multimodal Large Language Models
★ 2 1y agoExplain → -
CSVQA ⑂
The official repo of CSVQA Benchmark
★ 1 1y agoExplain →
No repos match these filters.