Haoqi Fan

Beijing University of Technology — China

Computer Science · Physical Sciences

29h-index22.9kcitations69works3.82yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

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

Research Topics

Domain Adaptation and Few-Shot Learning(27), Human Pose and Action Recognition(26), Multimodal Machine Learning Applications(26), Advanced Neural Network Applications(23), Advanced Image and Video Retrieval Techniques(14)

Publications69 total

Electroplating Cu with rich grain boundaries via gelatin addition for electrocatalytic reduction of low-concentration CO
Surfaces and Interfaces·2026
LightFusion: A Light-weighted, Double Fusion Framework for Unified Multimodal Understanding and Generation
ArXiv.org·2025Open Access
LLLaVA-Critic: Learning to Evaluate Multimodal Models
2025· 2 cited
Seed1.5-VL Technical Report
arXiv (Cornell University)·2025Open Access
Painting with Words: Elevating Detailed Image Captioning with Benchmark and Alignment Learning
arXiv (Cornell University)·2025Open Access
Causal Diffusion Transformers for Generative Modeling
arXiv (Cornell University)·2024Open Access
Classification Done Right for Vision-Language Pre-Training
arXiv (Cornell University)·2024· 2 citedOpen Access
LLaVA-Critic: Learning to Evaluate Multimodal Models
arXiv (Cornell University)·2024· 2 citedOpen Access
Investigation on wear induced by solid-liquid two-phase flow in a centrifugal pump based on EDEM-Fluent coupling method
Flow Measurement and Instrumentation·2024· 32 cited
Classification Done Right for Vision-Language Pre-Training
2024
Diffusion Models as Masked Autoencoders
2023· 32 cited
The effectiveness of MAE pre-pretraining for billion-scale pretraining
2023· 37 cited
Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference
2023· 49 cited
Scaling Language-Image Pre-Training via Masking
2023· 206 cited
Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles
arXiv (Cornell University)·2023· 58 citedOpen Access
Diffusion Models as Masked Autoencoders
arXiv (Cornell University)·2023· 2 citedOpen Access
The effectiveness of MAE pre-pretraining for billion-scale pretraining
arXiv (Cornell University)·2023· 2 citedOpen Access
Impacts of Cavitation on Flow Field Distributions and Pump Stability in Cryogenic Pumps
Journal of Low Temperature Physics·2023· 4 cited
Reversible Vision Transformers
arXiv (Cornell University)·2023Open Access
MAViL: Masked Audio-Video Learners
arXiv (Cornell University)·2022· 17 citedOpen Access
page 1 of 4Next →

Frequent Co-authors

Christoph Feichtenhofer(27), Jitendra Malik(13), Yanghao Li(13), Kaiming He(12), Ross Girshick(10), Chao-Yuan Wu(10), Karttikeya Mangalam(10), Bo Xiong(10), Saining Xie(5), Zhicheng Yan(5), Alan Yuille(5), Kris Kitani(4), Po-Yao Huang(4), Jiashi Feng(3), Wei Chen(3), Vaibhav Aggarwal(3), Kalyan Vasudev Alwala(3), Aaron Adcock(3), Ishan Misra(3), Yanghao Li(3)