Xiaofeng Wang

25 papers · 2018–2025 · 9 conferences · across top CS/AI conferences

Achievements

🏃 Academic Marathon (7) 🗺️ Taxonomy Completionist (43) 🌈 Renaissance Researcher (6) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐝 Cross-Pollinator (5) 🌍 Conference Polyglot (9) 🤝 Dynamic Duo (11) 💎 Century Club (25) ⚡ Prolific Year (14) ❓ The Questioner (2) 🗃️ Keyword Collector (91)

Conferences

CVPR (7) ICCV (5) ECCV (3) ICLR (3) AAAI (2) EMNLP (2) ACL (1) IJCAI (1) MICCAI (1)

Top co-authors

Zheng Zhu (11) Xingang Wang (11) Guan Huang (10) Guosheng Zhao (6) Yun Ye (5) Chaojun Ni (5) Xinze Chen (3) Wenkang Qin (3) Xu Chi (3) Dalong Du (3)

Keywords

autonomous driving (6) video generation (4) world model (3) diffusion model (3) 3d vision (2) efficient computing (2) scene reconstruction (2) 3d gaussian splatting (2) prompt engineering (1) attention mechanism (1) decision making (1) multi-modal learning (1) video understanding (1) trajectory prediction (1) depth estimation (1) self-supervised learning (1) neural rendering (1) gaussian splatting (1) scene representation (1) bird's eye view (1)

Papers

ProCut: LLM Prompt Compression via Attribution Estimation EMNLP 2025

WonderTurbo: Generating Interactive 3D World in 0.72 Seconds ICCV 2025

ReconDreamer++: Harmonizing Generative and Reconstructive Models for Driving Scene Representation ICCV 2025

Predicting Radiation Therapy Response based on Dynamic Temporal Feature Difference Fusion from Longitudinal MRI MICCAI 2025

Do Large Language Models Truly Understand Geometric Structures? ICLR 2025

DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation CVPR 2025

Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model CVPR 2025

ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration CVPR 2025

Rethinking Lanes and Points in Complex Scenarios for Monocular 3D Lane Detection CVPR 2025

HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation CVPR 2025

Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned Model ICLR 2025

DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation AAAI 2025

DynImg: Key Frames with Visual Prompts are Good Representation for Multi-Modal Video Understanding ICCV 2025

Debt Collection Negotiations with Large Language Models: An Evaluation System and Optimizing Decision Making with Multi-Agent ACL 2025

SSL-Cleanse: Trojan Detection and Mitigation in Self-Supervised Learning ECCV 2024

DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving ECCV 2024

Layer-wise Importance Matters: Less Memory for Better Performance in Parameter-efficient Fine-tuning of Large Language Models EMNLP 2024

Bridging Stereo Geometry and BEV Representation with Reliable Mutual Interaction for Semantic Scene Completion IJCAI 2024

OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception ICCV 2023

Crafting Monocular Cues and Velocity Guidance for Self-Supervised Multi-Frame Depth Learning AAAI 2023

LiftedCL: Lifting Contrastive Learning for Human-Centric Perception ICLR 2023

CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification ICCV 2023

Are We Ready for Vision-Centric Driving Streaming Perception? The ASAP Benchmark CVPR 2023

MVSTER: Epipolar Transformer for Efficient Multi-View Stereo ECCV 2022

Optimizing Filter Size in Convolutional Neural Networks for Facial Action Unit Recognition CVPR 2018