Lewei Lu

Group Sense (China) — China

Computer Science · Physical Sciences

16h-index5.5kcitations66works8.02yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Neural Network Applications(17), Multimodal Machine Learning Applications(14), Advanced Image and Video Retrieval Techniques(13), Topic Modeling(11), Advanced Vision and Imaging(10)

Publications66 total

DriveMLM: aligning multi-modal large language models with behavioral planning states for autonomous driving
Visual Intelligence·2025Open Access
Enhancing the Outcome Reward-based RL Training of MLLMs with Self-Consistency Sampling
arXiv (Cornell University)·2025Open Access
PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models
2025· 2 cited
MaskGWM: A Generalizable Driving World Model with Video Mask Reconstruction
2025
Docopilot: Improving Multimodal Models for Document-Level Understanding
2025· 2 cited
SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding
2025· 2 cited
HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language Embedding
2025· 1 cited
Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spaces
arXiv (Cornell University)·2025Open Access
InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
ArXiv.org·2025· 4 citedOpen Access
MaskGWM: A Generalizable Driving World Model with Video Mask Reconstruction
arXiv (Cornell University)·2025Open Access
SEAL: Speech Embedding Alignment Learning for Speech Large Language Model with Retrieval-Augmented Generation
arXiv (Cornell University)·2025Open Access
HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language Embedding
arXiv (Cornell University)·2024Open Access
Demystify Transformers & Convolutions in Modern Image Deep Networks
IEEE Transactions on Pattern Analysis and Machine Intelligence·2024
PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models
arXiv (Cornell University)·2024Open Access
SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding
arXiv (Cornell University)·2024Open Access
Mini-InternVL: a flexible-transfer pocket multi-modal model with 5% parameters and 90% performance
Visual Intelligence·2024· 19 citedOpen Access
Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
arXiv (Cornell University)·2024· 11 citedOpen Access
HoloDrive: Holistic 2D-3D Multi-Modal Street Scene Generation for Autonomous Driving
arXiv (Cornell University)·2024Open Access
ControlLLM: Augment Language Models with Tools by Searching on Graphs
Lecture notes in computer science·2024· 11 cited
Multimodal 3D Reasoning Segmentation with Complex Scenes
arXiv (Cornell University)·2024Open Access
page 1 of 4Next →

Frequent Co-authors

Jifeng Dai(32), Xizhou Zhu(26), Yu Qiao(21), Wenhai Wang(11), Hanming Deng(11), Xiaogang Wang(10), Hongsheng Li(10), Weijie Su(8), Tong Lü(8), Wenhai Wang(7), Chenxin Tao(7), Gao Huang(7), Jie Zhou(7), Chonghao Sima(6), Yuntao Chen(6), Dahua Lin(6), Shijian Lu(6), Zhiqi Li(5), Xiaolong Zhu(5), Zhe Chen(4)