Le Zhang

Le Zhang

Ph.D @ Mila - Quebec AI Institute

About me

Greetings, I am Le Zhang, a Ph.D student at the Mila - Quebec AI Institute. Currently, I’m working with Prof. Aishwarya Agrawal in the domain of vision-language learning. Perviously, I obtained Bachelor degree from Fudan University. Besides, I worked with Prof Zhongyu Wei and I conducted a summer research with Prof. Diyi Yang, and interned at Shanghai AI Lab with Dr. Siqi Sun.

Reaserach Interests

My research primarily centers around the domains of computer vision and multimodal learning.

News and Updates

  • [Sep 2024] Two papers got accepted at NeurIPS 2024, one on MSA augmentation for protein structure prediction with language models and one on visual minimal-change understanding for vision-language models.
  • [Sep 2024] One paper on Information Retrieval with Large Language Model has been accepted to EMNLP 2024 findings
  • [May 2024] One paper on Graph Convolution and Contrastive Learning has been accepted to KDD 2024
  • [Feb 2024] One paper on vision-language compositional understanding has been accepted to CVPR 2024
  • One paper for zero-shot multimodal question answering got accepted into EMNLP 2023 findings
  • Start graduate study at Mila!
  • Interned at Shanghai AI Lab from 2022/02-2022/09
  • Two paper got accepted at NAACL 2022

Publications

  • Enhancing the Protein Tertiary Structure Prediction by Multiple Sequence Alignment Generation
    Le Zhang, Jiayang Chen, Tao Shen, Yu Li, Siqi Sun.
    NeurIPS 2024 [arxiv | code]
  • VisMin: Visual Minimal-Change Understanding
    Rabiul Awal*, Saba Ahmadi*, Le Zhang*, Aishwarya Agrawal
    NeurIPS 2024 project
  • Exploring the Best Practices of Query Expansion with Large Language Models
    Le Zhang, Qian Yang, Yihong Wu.
    EMNLP 2024 findings [arxiv | code]
  • Unifying Graph Convolution and Contrastive Learning in Collaborative Filtering
    Yihong Wu, Le Zhang, Fengran Mo, Tianyu Zhu, Weizhi Ma, Jian-Yun Nie
    KDD 2024
  • Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding
    Le Zhang, Rabiul Awal, Aishwarya Agrawal
    CVPR 2024 [arXiv | code]
  • MoqaGPT: Zero-Shot Multi-modal Open-domain Question Answering with Large Language Model
    Le Zhang, Yihong Wu, Fengran Mo, Jian-Yun Nie, Aishwarya Agrawal.
    EMNLP 2023 Findings [arxiv | code]

  • Investigating Prompting Techniques for Zero- and Few-Shot Visual Question Answering
    Rabiul Awal, Le Zhang, Aishwarya Agrawal.
    CVPR2024W Oral [arxiv]

  • SUBS: Subtree Substitution for Compositional Semantic Parsing
    Jingfeng Yang*, Le Zhang*, Diyi Yang.
    NAACL 2022 [arxiv | code]
  • TreeMix: Compositional Constituency-based Data Augmentation for Natural Language Understanding
    Le Zhang, Zichao Yang, Diyi Yang.
    NAACL 2022 [arxiv | code]

Services