Hao Li
Senior Applied Scientist
Amazon AGI / AWS AI Labs

Email  /  Google Scholar  /  Github  /  Twitter

I am a Sr. Applied Scientist at Amazon AGI, working on vision foundation models, especially for text-to-image generation. My research aims at developing efficient, scalable, automatic, transferable and interpretable ML alogrithms, models and systems. I have contributed to various image generation and analysis services including Titan Image Generator model on Amazon Bedrock, as well as AWS Rekognition's Custom Labels, Lookout for Vision and Content Moderation. Before joining Amazon, I received my Ph.D. in Computer Science from University of Maryland, College Park, advised by Prof. Tom Goldstein and Prof. Hanan Samet, with a focus on accelerating and understanding deep neural nets.

News

  • [02/2024] "On the Scalability of Diffusion-based Text-to-Image Generation" is accepted in CVPR 2024.
  • [11/2023] Our AWS Titan Image Generator is anounced at AWS re:Invent and is avaliable for preview.
  • [02/2023] "Guided Recommendation for Model Fine-Tuning" is accepted in CVPR 2023.
  • [02/2023] We are looking for research interns for summer 2023 at AWS AI Labs, if you are interested in working on VLMs/generative models for image synthesis, please drop me an email.

Selected Publications

On the Scalability of Diffusion-based Text-to-Image Generation
Hao Li, Yang Zou, Ying Wang, Orchid Majumder, Yusheng Xie, R. Manmatha,
Ashwin Swaminathan, Zhuowen Tu, Stefano Ermon, Stefano Soatto
CVPR 2024 [comming soon]
Guided Recommendation for Model Fine-Tuning
Hao Li, Charless Fowlkes, Hao Yang, Onkar Dabeer, Zhuowen Tu, Stefano Soatto
CVPR 2023 [ pdf / video / poster ]
Task Adaptive Parameter Sharing for Multi-Task Learning
Matthew Wallingford, Hao Li, Alessandro Achille, Avinash Ravichandran,
Charless Fowlkes, Rahul Bhotika, Stefano Soatto
CVPR 2022
Rethinking the Hyperparameters for Fine-tuning
Hao Li, Pratik Chaudhari, Hao Yang, Michael Lam, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto
ICLR 2020 [video]
Visualizing the Loss Landscape of Neural Nets
Hao Li, Zheng Xu, Gavin Taylor, Christoph Studer, Tom Goldstein
NeurIPS 2018 [project / code / poster]
Training Quantized Nets: A Deeper Understanding
Hao Li*, Soham De*, Zheng Xu, Christoph Studer, Hanan Samet, Tom Goldstein
NeurIPS 2017 [poster]
ICML 2017 PADL Workshop [slides] Google Best Student Paper
Pruning Filters for Efficient ConvNets
Hao Li, Asim Kadav, Igor Durdanovic, Hanan Samet, Hans Peter Graf
ICLR 2017 [poster]
NeurIPS 2016 EMDNN Workshop

Dissertation

Towards Fast and Efficient Representation Learning
Hao Li
University of Maryland, College Park, Aug 2018 [slides]

Academic Services

  • Journal Reviewer​
    • Journal of Machine Learning Research (JMLR) (editorial board reviewer)
    • International Journal of Computer Vision (IJCV)
    • IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
    • IEEE Transactions on Neural Network and Learning Systems (TNNLS)
    • IEEE Transactions on Multimedia (TMM)
    • Neurocomputing
  • Conference Reviewer
    • NeurIPS, ICML, ICLR, ICCV, CVPR, ECCV, KDD, AAAI