Fuwen Tan
fuwen.tan@gmail.com
About me
I'm a researcher in Efficient Machine Learning, working on making LLM and Video Diffusion Models faster.
Research
Progressive Mixed-Precision Decoding for Efficient LLM Inference
Hao Mark Chen, Fuwen Tan, Alexandros Kouris, Royson Lee, Hongxiang Fan, Stylianos I. VenierisInternational Conference on Learning Representations (ICLR), 2025.
[ paper ] [ code ] [bibtex]
MobileQuant: Mobile-friendly Quantization for On-device Language Models
Fuwen Tan, Royson Lee, Lukasz Dudziak, Shell Xu Hu, Sourav Bhattacharya, Timothy Hospedales, Georgios Tzimiropoulos, Brais MartinezConf. on Empirical Methods in Natural Language Processing, EMNLP Findings, 2024
[ paper ] [ code ] [bibtex]
iBoot: Image-bootstrapped Self-Supervised Video Representation Learning
Fatemeh Saleh, Fuwen Tan, Adrian Bulat, Georgios Tzimiropoulos, Brais Martinez[ paper ] [bibtex]
EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers
Junting Pan, Adrian Bulat, Fuwen Tan, Xiatian Zhu, Lukasz Dudziak, Hongsheng Li, Georgios Tzimiropoulos, Brais MartinezEuropean Conference on Computer Vision (ECCV), 2022.
[ paper ] [ code ] [bibtex]
Instance-level Image Retrieval using Reranking Transformers
Fuwen Tan, Jiangbo Yuan, Vicente OrdonezInternational Conference on Computer Vision (ICCV), 2021.
[ paper ] [ code ] [bibtex]
Curriculum Labeling: Self-paced Pseudo-Labeling for Semi-Supervised Learning
Paola Cascante-Bonilla, Fuwen Tan, Yanjun Qi, Vicente OrdonezAAAI Conference on Artificial Intelligence (AAAI), 2021.
[ paper ] [ code ] [ bibtex ]
Drill-down: Interactive Retrieval of Complex Scenes using Natural Language Queries
Fuwen Tan, Paola Cascante-Bonilla, Xiaoxiao Guo, Hui Wu, Song Feng, Vicente OrdonezConf. on Neural Information Processing Systems (NeurIPS), 2019
[ paper ] [ code ] [ poster ] [ bibtex ]
Text2Scene: Generating Compositional Scenes from Textual Descriptions
Fuwen Tan, Song Feng, Vicente OrdonezConf. on Computer Vision and Pattern Recognition (CVPR), 2019, (~Oral presentation + Best Paper Finalist)
Posts from NVIDIA Developer News, IBM Research Blog
[ paper ] [ code ] [ poster ] [ slides ] [ bibtex ]
Where and Who? Automatic Semantic-Aware Person Composition
Fuwen Tan, Crispin Bernier, Benjamin Cohen, Vicente Ordonez, Connelly BarnesWinter Conf. on Applications of Computer Vision (WACV), 2018
[ paper ] [ supplemental PDF ] [ code ] [ video ] [ bibtex ]
FaceCollage: A Rapidly Deployable System for Real-time Head Reconstruction for On-The-Go 3D Telepresence
Fuwen Tan, Chi-Wing Fu, Teng Deng, Jianfei Cai, Tat Jen ChamACM Multimedia (ACM MM, full paper), 2017
[ paper ] [ video] [ poster ] [ bibtex ]
High-Quality Kinect Depth Filtering For Real-time 3D Telepresence
Mengyao Zhao, Fuwen Tan, Chi-Wing Fu, Chi-Keung Tang, Jianfei Cai, Tat Jen ChamConf. on Multimedia and Expo (ICME), 2013
[ IEEE Xplorer ] [bibtex]
Field-guided Registration for Feature-conforming Shape Composition
Hui Huang, Minglun Gong, Daniel Cohen-Or, Yaobin Ouyang, Fuwen Tan, Hao ZhangACM Transactions on Graphics (Proc. SIGGRAPH Asia), 2012
[ project ] [paper] [bibtex]
Thesis
PhD Dissertation: Learning Local Representations of Images and Text
Images and text inherently exhibit hierarchical structures, e.g. scenes built from objects, sentences built from words. In many computer vision and natural language processing tasks, learning accurate prediction models requires analyzing the correlation of the local primitives of both the input and output data. In this thesis, we develop techniques for learning local representations of images and text and demonstrate their effectiveness on visual recognition, retrieval, and synthesis. ...