publications

2025

  1. PairBench: Are Vision-Language Models Reliable at Comparing What They See?
    Feizi, Aarash, Rajeswar, Sai, Romero-Soriano, Adriana, Rabbany, Reihaneh, Gella, Spandana, Zantedeschi, Valentina,  and Monteiro, João
    arXiv preprint arXiv:2502.15210 2025
  2. EMNLP 2025)
    WebMMU: A benchmark for multimodal multilingual website understanding and code generation
    Awal, Rabiul, Massoud, Mahsa,  Feizi, Aarash, Li, Zichao, Wang, Suyuchen, Pal, Christopher, Agrawal, Aishwarya, Vazquez, David, Reddy, Siva, Rodriguez, Juan A,  and others,
    arXiv preprint arXiv:2508.16763 2025
    HTML
  3. NeurIPS 2025)
    Alignvlm: Bridging vision and language latent spaces for multimodal understanding
    Masry, Ahmed, Rodriguez, Juan A, Zhang, Tianyu, Wang, Suyuchen, Wang, Chao,  Feizi, Aarash, Suresh, Akshay Kalkunte, Puri, Abhay, Jian, Xiangru, Noël, Pierre-André,  and others,
    arXiv preprint arXiv:2502.01341 2025
  4. NeurIPS 2025)
    Rendering-Aware Reinforcement Learning for Vector Graphics Generation
    Rodriguez, Juan A, Zhang, Haotian, Puri, Abhay,  Feizi, Aarash, Pramanik, Rishav, Wichmann, Pascal, Mondal, Arnab, Samsami, Mohammad Reza, Awal, Rabiul, Taslakian, Perouz,  and others,
    arXiv preprint arXiv:2505.20793 2025
  5. ICLR 2025
    BigDocs: An Open and Permissively-Licensed Dataset for Training Multimodal Models on Document and Code Tasks
    Rodriguez, Juan A, Jian, Xiangru, Panigrahi, Siba Smarak, Zhang, Tianyu,  Feizi, Aarash, Puri, Abhay, Suresh, Akshay Kalkunte, Savard, François,  and others,
    In International Conference on Learning Representations 2025
    HTML PDF

2024

  1. arXiv
    GPS-SSL: Guided Positive Sampling to Inject Prior Into Self-Supervised Learning
    Feizi, Aarash, Balestriero, Randall, Romero-Soriano, Adriana,  and Rabbany, Reihaneh
    arXiv preprint arXiv:2401.01990 2024
    PDF
  2. arXiv
    FairLoRA: Unpacking Bias Mitigation in Vision Models with Fairness-Driven Low-Rank Adaptation
    Sukumaran, Rohan,  Feizi, Aarash, Romero-Sorian, Adriana,  and Farnadi, Golnoosh
    arXiv preprint arXiv:2410.17358 2024

2022

  1. DataPerf WS
    ICML 2022
    Revisiting Hotels-50K and Hotel-ID
    Feizi, Aarash, Casanova, Arantxa, Romero-Soriano, Adriana,  and Rabbany, Reihaneh
    arXiv preprint arXiv:2207.10200 2022
    PDF

2020

  1. EMNLP 2020
    Structure Aware Negative Sampling in Knowledge Graphs
    Ahrabian, Kian,  Feizi, Aarash, Salehi, Yasmin, Hamilton, William L.,  and Bose, Avishek Joey
    arXiv preprint arXiv:2009.11355 2020
    PDF