Senior Director & Head of DreamX, Alibaba Group
I build foundation AI systems that move from original research to reproducible open source and large-scale map, mobility, and interactive AI products. I lead DreamX at Alibaba AMAP, a 100+ member product-facing AI team building spatial intelligence models and systems that understand and predict, generate and simulate, plan and act in the real world. Our work is grounded in AMAP products serving 300M+ users every day. Across my research career, I have published 70+ papers at top-tier AI conferences.
15,000+ Total Citations
6,000+ As First Author
70+ Top-Conference Papers
300M+ Daily Users
Citation and publication metrics verified July 2026 · Source: Google Scholar. Top-conference count covers main-track papers and excludes Findings and workshops.
Recent Updates
2026.06.18 DreamX had five papers accepted to ECCV 2026, adding another strong top-venue signal to the team's recent research portfolio.
2026.06.15 DreamX-World 1.0 released its technical report and open-sourced a 5B model supporting one-minute interactive world generation. 2026.05.18 MobilityBench accepted as an oral paper at KDD 2026, benchmarking route-planning agents in real-world mobility scenarios. 2026.05.01 DreamX added four ICML 2026 papers across unified multimodal generation, data-efficient RL, long-video generation, and preference optimization.
View all updates
Featured Projects
Current Focus
LLM ReasoningA simple and strong reinforcement learning baseline for model reasoning — no critic, no reference model, no KL penalty. Adopted by ByteDance's
VERL framework as an official algorithm.
World ModelA general-purpose interactive world model that creates diverse, high-fidelity virtual environments with camera-controlled navigation and prompt-driven world events.
Spatial AIA scalable benchmark for evaluating route-planning agents in real-world mobility scenarios, connecting agent research with AMAP's spatial intelligence anchor.
AgentAgentic skill evolution from real interaction traces, turning reusable skills into collective libraries across sessions, devices, and agents.
Earlier Impact
DetectionIndustrial-grade real-time object detection framework with a full training-to-deployment toolchain, broad open-source adoption, and follow-up deployment work on RepVGG-style quantization.
Vision-LanguageA compact vision-language assistant designed for real-time on-device deployment, with 1B/3B models evaluated on mobile hardware such as Snapdragon 888.
ArchitectureRevisiting spatial attention in Vision Transformers. Outperforms Swin Transformer with simpler design and better deployment properties.
FoundationA unified LLaMA-style backbone for vision tasks, introducing auto-scaling 2D RoPE for multimodal Transformers and reporting strong results across generation, classification, segmentation, and detection.
Research Journey
2024 – Present · Alibaba AMAP
DreamX: Spatial Intelligence Models & Systems
Leading DreamX, a 100+ member product-facing AI team organized around one mission: spatial intelligence. The portfolio connects three core problems — understanding and predicting the world, generating and simulating the world, and planning and acting in the world — with shared foundations in spatial data, multimodal models, reinforcement learning, infrastructure, and evaluation. Representative systems include MobilityBench, DreamX-World, SkillClaw, GPG, Tree-GRPO, and Code2World. Research also connects to AMAP's Saojie Bang (扫街榜) pipeline and AI Companion (AI 伴行), alongside products serving 300M+ users every day. Published 50+ papers at top venues and open-sourced 30+ projects.
2020 – 2024 · Meituan
Vision Transformers, Multimodal Models & Industrial AI
Built the Visual Intelligence team from scratch. Created Twins (NeurIPS 2021), CPVT (ICLR 2023), VisionLLaMA (ECCV 2024); reproduced LLaMA 7B and built MobileVLM for on-device deployment; open-sourced YOLOv6; shipped autonomous delivery and drone perception systems.
2017 – 2020 · Xiaomi
Neural Architecture Search & AutoML
Founded Xiaomi's AutoML team. Produced a series of influential NAS works — FairNAS (ICCV 2021), FairDARTS (ECCV 2020), DARTS- (ICLR 2021), FALSR — establishing new standards for fair and robust architecture search. Featured by Lei Jun and major AI media.
2013 – 2017 · KingStar
Power Grid AI & Reinforcement Learning
Core contributor to the "Complex Power Grid Autonomous-Collaborative Automatic Voltage Control" project. Contributed 20 invention patents. Awarded the National Science and Technology Progress First Prize (2018).
2012 – 2013 · IBM Research China
Large-Scale Data Analytics
Research scientist working on large-scale data analytics and machine learning solutions.
Recognition
- Top 100 AI Scholars, AMiner 2023 — selected from hundreds of thousands of AI researchers worldwide
- 3 first-authored papers on PaperDigest's Most Influential lists: FairNAS, Twins, CPVT
- Area Chair: ICLR, NeurIPS | Senior Program Committee: AAAI, IJCAI
- 40+ domestic and 7 international invention patents
DreamX Technical System
Understand & Predict the World — Route-planning agents (MobilityBench), map-augmented geolocalization (Thinking-with-Map), urban scene understanding, mobility forecasting, recommendation, and industrial map systems
Generate & Simulate the World — Interactive world simulation (DreamX-World), GUI world models (Code2World), scene-text editing (FluxText), 3D editing (RL3DEdit), and controllable spatial content
Plan & Act in the World — Agent skill evolution (SkillClaw), reasoning and self-reflection for physical action (AutoDrive-R2), LLM reasoning (GPG), tree-search training (Tree-GRPO), and agent-data co-evolution (CoEvolve)
Shared Foundation — Spatial data and knowledge, multimodal foundation models, reinforcement learning, generative modeling, infrastructure, and evaluation across projects including SpatialGenEval, Omni-WorldBench, FASA, USP, and RealQA
Team & Opportunities
I lead DreamX at Alibaba Group, a 100+ member product-facing AI team building AMAP’s spatial intelligence models and systems. DreamX releases are hosted publicly through the AMAP-ML GitHub organization.
Our philosophy: We build systems where research quality, engineering discipline, open-source reproducibility, and product deployment reinforce each other. Many core projects ship with reproducible code, and our work contributes to AMAP products serving 300M+ users every day.
Open Source
We maintain 30+ DreamX projects on GitHub, organized around understanding and prediction, generation and simulation, planning and action, and a shared technical foundation.
Hiring
We are always looking for talented interns, full-time researchers, and AI engineers in LLM agents, reinforcement learning, world models, multimodal learning, spatial intelligence, and generative AI. Drop me an email if interested.
Education
- M.S. in Electrical Engineering, Tsinghua University, 2012
- B.S. in Electrical Engineering, Southeast University, 2010
