Guosheng Zhao

9 papers · 2023–2026 · 5 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (16) ⚡ Prolific Year · Productive

Venues

CVPR (4) ICCV (2) AAAI (1) ECCV (1) EMNLP (1)

Top co-authors

Xiaofeng Wang (7) Guan Huang (7) Zheng Zhu (7) Chaojun Ni (6) Xingang Wang (6) Wenjun Mei (4) Xinze Chen (3) Wenkang Qin (3) Boyuan Wang (3) Xueyang Zhang (2)

Research topics

Computer Vision (5) Artificial Intelligence (4) Core AI (4) Deep Learning (3) Analysis (3) Domain-Specific (3) Generation (2) Models (2) Computer Science (1) Machine Learning (1) Applications (1) Learning Types · Deep Learning (1) Learning Types · Machine Learning (1)

Keywords

world model (3) autonomous driving (3) video generation (3) scene reconstruction (2) diffusion model (2) 3d gaussian splatting (2) scene representation (1) generative model (1) 3d generation (1) vision-language model (1) neural radiance field (1) real-time rendering (1) novel view synthesis (1) edge device (1) 3d scene generation (1) vision-language-action model (1) view synthesis (1) memory network (1) spatio-temporal reasoning (1) human motion generation (1)

Papers

SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overhead CVPR 2026 DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation AAAI 2025 DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation CVPR 2025 HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation CVPR 2025 ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration CVPR 2025 ReconDreamer++: Harmonizing Generative and Reconstructive Models for Driving Scene Representation ICCV 2025 WonderTurbo: Generating Interactive 3D World in 0.72 Seconds ICCV 2025 CoReS: Orchestrating the Dance of Reasoning and Segmentation ECCV 2024 Normal-Abnormal Decoupling Memory for Medical Report Generation EMNLP 2023