Feng Gao

Applied Scientist, Amazon. Ph.D. from UCLA.

feng_202401.jpeg

Email: fenggo[AT]amazon[dot]com

Feng Gao is currently an applied scientist at Amazon. He received his Ph.D. from UCLA in 2022 co-advised by Ying Nian Wu and Mark S. Handcock. From 2017 to 2021, he was under the supervision of Song-Chun Zhu.

In Amazon, Feng Gao is affliated to store foundation AI (SFAI). Specifically, he is working on full stack multi-modal LLM including pre-training, IFT, alignment and evaluation.

Feng Gao’s research [Google Scholar] interests focus on computer vision, artificial intelligence and robotics. Targeting AGI for robotics, in particularly, he is actively working on

news

Oct 14, 2024 Our work about Embodied AI, Planning as In-Painting :robot: is accepted in NeurIPS2024 OWA. :rocket: [paper]
Sep 25, 2024 Two paper accepted to NeurIPS2024. They are about physically constrained Text-to-3D 🤸🏻‍♀️ [paper] [demo] and flow matching generative model [paper].
Jun 01, 2024 Our paper on spatial generalizable T2I 🐱🐭 is accepted in ECCV2024. [paper]
Apr 30, 2024 Our paper VR-GS 🐎 is accepted in SIGGRAPH 2024. [paper]
Dec 12, 2023 Our paper on non-Markovian Decision Making 🧠 is presented in NeurIPS2023. [paper]

selected publications

  1. NeurIPS
    neurips2024_atlas3d_preview.gif
    Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabrication
    Yunuo Chen, Tianyi Xie, Zeshun Zong, Xuan Li, Feng Gao, Yin Yang, and 2 more authors
    NeurIPS, 2024
    HTML PDF Code
  2. ECCV
    eccv2024_preview.png
    Skews in the Phenomenon Space Hinder Generalization in Text-to-Image Generation
    Yingshan Chang, Yasi Zhang, Zhiyuan Fang, Yingnian Wu, Yonatan Bisk, and Feng Gao
    ECCV, 2024
    PDF
  3. NeurIPS
    cvpr2024_preview.png
    Planning as In-Painting: A Diffusion-Based Embodied Task Planning Framework for Environments under Uncertainty
    Cheng-Fu Yang, Haoyang Xu, Te-Lin Wu, Xiaofeng Gao, Kai-Wei Chang, and Feng Gao
    NeurIPS OWA, 2024
    HTML PDF Code
  4. NeurIPS
    neurips2023_preview.png
    Learning non-Markovian Decision-Making from State-only Sequences
    Aoyang Qin, Feng Gao, Qing Li, Song-Chun Zhu, and Sirui Xie
    NeurIPS, 2023
    PDF Code
  5. CVPR
    cvpr2023_preview.png
    GIVL: Improving Geographical Inclusivity of Vision-Language Models with Pre-Training Methods
    Da Yin, Feng Gao, Govind Thattai, Michael Johnston, and Kai-Wei Chang
    CVPR, 2023
    PDF Supp
  6. tpa_preview.gif
    TPA-Net: Generate A Dataset for Text to Physics-based Animation
    Yuxing Qiu, Feng Gao, Minchen Li, Govind Thattai, Yin Yang, and Chenfanfu Jiang
    arXiv preprint arXiv:2211.13887, 2022
    HTML PDF
  7. CVPR
    cvpr2022_preview.png
    Transform-Retrieve-Generate: Natural Language-centric Outside-Knowledge Visual Question Answering
    Feng Gao, Qing Ping, Govind Thattai, Aishwarya Reganti, Ying Nian Wu, and Prem Natarajan
    CVPR, 2022
    PDF Supp Code
  8. Science Robotics
    sciencerobotics_preview.png
    A Tale of Two Explanations: Enhancing Human Trust by Explaining Robot Behavior
    Mark Edmonds*, Feng Gao*, Hangxin Liu*, Xu Xie*, Siyuan Qi, Brandon Rothrock, and 4 more authors
    Science Robotics, 2019
    (* co-first author)
    PDF Code
  9. NeurIPS
    neurips2019_preview.png
    Learning Perceptual Inference by Contrasting
    Chi Zhang, Baoxiong Jia, Feng Gao, Yixin Zhu, Hongjing Lu, and Song-Chun Zhu
    NeurIPS, 2019
    HTML PDF Code
  10. CVPR
    cvpr2019_preview.png
    RAVEN: A Dataset for Relational and Analogical Visual Reasoning
    Chi Zhang*, Feng Gao*, Baoxiong Jia, Yixin Zhu, and Song-Chun Zhu
    CVPR, 2019
    (* co-first author)
    HTML PDF Supp Code
  11. ICRA
    icra2018_preview.webp
    Unsupervised Learning of Hierarchical Models for Hand-object Interactions
    Xu Xie, Hangxin Liu, Mark Edmonds, Feng Gao, Siyuan Qi, Yixin Zhu, and 2 more authors
    ICRA, 2018
    PDF Video Code
  12. IROS
    iros2017_glove_preview.gif
    A Glove-based System for Studying Hand-object Manipulation via Joint Pose and Force Sensing
    Hangxin Liu, Xu Xie, Matt Millar, Mark Edmonds, Feng Gao, Yixin Zhu, and 3 more authors
    IROS, 2017
    PDF Code
  13. IROS
    iros2017_bottle_preview.gif
    Feeling the Force: Integrating Force and Pose for Fluent Discovery through Imitation Learning to Open Medicine Bottles
    Mark Edmonds*, Feng Gao*, Xu Xie, Hangxin Liu, Siyuan Qi, Yixin Zhu, and 2 more authors
    IROS, 2017
    (* co-first author)
    PDF Video Code