About me

I am a PhD student at Université de Montréal and MILA (Quebec AI Institute) under supervision of Aaron Courville. I'm also a visiting research with AIM program at FAIR, Meta, collaborating with Adriana Romero-Soriano and Michal Drozdzal.

I am currently working on generative models, with a particular focus on text-to-image systems. My research explores generation fidelity and diversity, aiming to develop responsible AI algorithms.

Keywords: Generative models, Multi-modality, Responsible AI, Fairness, Diversity, etc.

News

  • Feb. 2026 One paper is accepted to ICLR 2026! Check out our paper about how prompt complexity affects the utilities (diversity, quality and consistency) of the generated images from text-to-image models, and also how they perform compared to real data.
  • Feb. 2026 World Modeling Workshop 26 at Mila! As an organizer, thrilled to share our first edition of World Modeling Workshop in Mila, Montreal! You can find the recordings of exciting talks and the list of posters on our website.
  • Dec. 2025 Attending NeurIPS 2025 in San Diego! Check out Chamfer Guidance about how chamfer distance can be used to ground the distribution of pre-trained text-to-image models.
  • Sept. 2025 Attending PAISS summer school in Grenoble! Check out our highlights on the website. Fantastic three days in Grenoble!
  • Aug. 2025 One paper is accepted to the Findings of EMNLP 2025! Check out CulturalFrames to know how SOTA closed-source and open-source text-to-image models perform with culturally-aware prompts and how they capture implicit and explicit cultural informations.
  • March 2025 Recipient of EDI in Research Scholarship! I am grateful to Mila for supporting my research through the EDI in research scholarship.

View all news →

Contact

MILA (Quebec AI Institute),

6666 Rue Saint-Urbain,

Montréal, QC H2S 3H1, Canada

xiaofng [DOT] zhang [AT] gmail [DOT] com



Potential Chat

I'm happy to connect with YOU. If you want to chat with me, please look at my available time slots in the following Google Calendar. You could directly send me an Google Calendar invite via my gmail address stating about what topic you would like to talk.


Daniel lewis
quote icon

Daniel lewis

Resume

Education

Experience

  1. Natural Language Processing Engineer    Pattern Recognition Center, Wechat AI, Tencent

    Dec. 2021 - Jun. 2022    supervised by Dr. Yikang Shen

    Worked on two research topics. Firstly, we propose a new attention mechanism called Mixture of Attention Heads (MoA), which is a combination of Mixture of Experts and Multi-head Attention Mechanism. MoA permits easily scale up the model capacity while constraining the same level of computational cost. We achieved better performance on Machine Translation and Language Modeling tasks compared to SOTA baselines. Secondly, we work on the model editing task in order to efficiently correct the false prediction of a pre-trained language model. We propose a new task named sequential editing task and conceive a novel way to edit the stored knowledge in the pre-trained language model. We add a few new neurons in the last Feed Forward layer of Transformer architecture. The experimental result show that our method outperforms other strong baselines.

Publication

Blog

News

  • Feb. 2026 One paper is accepted to ICLR 2026! Check out our paper about how prompt complexity affects the utilities (diversity, quality and consistency) of the generated images from text-to-image models, and also how they perform compared to real data.
  • Feb. 2026 World Modeling Workshop 26 at Mila! As an organizer, thrilled to share our first edition of World Modeling Workshop in Mila, Montreal! You can find the recordings of exciting talks and the list of posters on our website.
  • Dec. 2025 Attending NeurIPS 2025 in San Diego! Check out Chamfer Guidance about how chamfer distance can be used to ground the distribution of pre-trained text-to-image models.
  • Sept. 2025 Attending PAISS summer school in Grenoble! Check out our highlights on the website. Fantastic three days in Grenoble!
  • Aug. 2025 One paper is accepted to the Findings of EMNLP 2025! Check out CulturalFrames to know how SOTA closed-source and open-source text-to-image models perform with culturally-aware prompts and how they capture implicit and explicit cultural informations.
  • March 2025 Recipient of EDI in Research Scholarship! I am grateful to Mila for supporting my research through the EDI in research scholarship.
  • Dec. 2024 I will attend NeurIPS 2024 in Vancouver, presenting my work on bias analysis in unconditional image generative models!
  • Sep. 2024 I joined FAIR, Meta, as a Visiting Researcher!
  • Nov. 2023 One paper (Pre-trained Model Selection) is accepted to the Findings of EMNLP 2023!
  • Jan. 2023 One paper (Knowledge Update and Model Editing for LLMs) is accepted to ICLR 2023!
  • Sep. 2022 Two papers (MoE Attention architecture, Prompt Learning and Meta Learning) are accepted to EMNLP 2022!