Wafa Aissa

Temporary Teaching/Research
Personal website:
Office: 37.1.40

I am a last-year Ph.D. student under the supervision of Michel Crucianu and Marin Ferecatu. The context of my PhD thesis is compositional visual reasoning. When presented with an image and a question pair, our objective is to have neural networks models answer the question by following a reasoning chain defined by a program. We assess the model's reasoning ability through a Visual Question Answering (VQA) setup. Compositional VQA breaks down complex questions into modular easier sub-problems. These sub-problems include reasoning skills such as object and attribute detection, relation detection, logical operations, counting, and comparisons. Each sub-problem is assigned to a different module. This approach discourages shortcuts, demanding an explicit understanding of the problem. It also promotes transparency and explainability.

2026

Unpublished

  1. Zouhar, V.; Choudhary, M.; Z"ufle, M.; Rajaee, S.; Chen, P.; Vamvas, J.; Papi, S.; de Gibert, O.; Malik, B.; Habba, E.; Mastromichalakis, O. M.; Schmidtov'a, P.; Wastl, M.; Issaka, S.; Choshen, L.; Biderman, S.; Anastasopoulos, A.; Niehues, J.; Sennrich, R.; Sachan, M.; Bojar, O. r.; Murray, K.; Tiedemann, J.; Aji, A. F.; Koehn, P.; Monz, C.; Birch, A.; Vajjala, S.; Kranti, C.; Espa~na-Bonet, C.; Sarwar, N.; Kaczér, D.; Asano, S.; Marmonier, M.; Jaff, D. Q.; Mishra, V.; Khalifa, H. A-.; Sarti, G.; Saha, S.; Rehlinger, N.; Villa, J. D. C.; Tonglet, J.; Purkayastha, S.; Mach'av cek, D.; Ramanujam, J.; Do, H.; Nadova, Z.; Philippy, F.; Retkowski, F.; Lymperaiou, M.; Casola, S.; Yukhymenko, H.; Dipta, S. R.; Ryu, S.; Jerez, A.; Keinan, R.; Yusuf, S. S.; Vempati, A.; Staiano, M. C.; Purkayastha, S.; Cosma, A.; Babenko, V.; Inan, E.; Nigam, A.; Aissa, W.; Haouari, F.; Gummadi, V. P. K.; Jafarzadeh, M.; Scourneau, V.; Edman, L.; Sun, K.; Tan, S.; Gholizadeh, M. S.; David, J-R.; Srirag, D.; Gilabert, J. G.; Binkyte, R.; Ali, M.; Bucur, A-M.; Farrag, S. E.; Saber, Y.; Liu, Y.; Maillard, J.; Nicoleta, C.; Yuan, X.; Ahmadi, S.; Mondorf, P.; Dhole, K.; Wixinger, R.; Qian, S.; Tuor, M.; Troshin, S.; Yahav, J.; Thoker, F. M.; Rezapour, A. A.; Gamboa, L. C. L.; Reusens, M.; Kukk, K.; Chowdhury, K. D.; Gallipoli, G.; Hoang, C.; Saha, S.; Aycock, S.; Koco'n, J.; Chen, Bo; Vu, L.; Venkatkrishna, V.; Ahsan, A.; Nguyen, L. T.; Soliman, H.; Dementieva, D.; Rampisela, T. V.; Do, N. Q. T.; Huber, M.; Egashira, K.; Wasi, A. T.; Poritski, V.; Zhang, M.; Shah, D.; Gavrikov, P.; Salim, L. F.; Africa, D.; Damanhuri, R.; Bello, B. U.; Garg, A.; Rao, G.; Ammanamanchi, P. S.; Dementaviciute, K.; Michail, A.; Teja, L D M S S.; Zhu, D.; Fan, Yi; Liu, W.; Farsi, F.; Herranen, E.; Chowdhury, S. P.; Sanchez, K.; Shami, F.; Urlana, A.; Wang, Z.; Limisiewicz, T.; Pattnayak, P.; Ojastu, M.; Na, H.; Radoi, E.; Zhao, C.; Hinojosa, C.; de Varda, A. G.; Alyafeai, Z.; Alzahrani, R.; Kathrotia, N.; Fl"uckiger, A.; Carr, U. S. T.; Layacan, J. P.; Kaplan, G.; Tiwari, R.; Dagli, R.; Volchek, O.; Caswell, I. R; Yi, B.; K"ovér, B.; Yari, A. H.; Chorana, A.; Wang, Z.; Ker"anen, S.; Simko, S.; Olusanya, J.; Chim, J.; Doyen, E.; Lakkamaneni, V. H.; Conrad, S.; Sadeghi, P.; Panayiotou, P.; Lara, L.; Nayem, J.; Yahav, E.; Das, D.; Karamolegkou, A.; Goel, A.; Mandal, A.; Cerruti, T.; Zhao, R.; Haltiuk, M.; Aung, T.; Almousa, N.; Kargaran, A. H.; Bawden, R.; Zheng, Q.; Lango, M.; Egressy, B.; Vel'asquez, F. R.; Jongwiriyanurak, N.; Do, M. N.; Gaido, M.; Libon, L.; Kuzmin, D.; Nyalang, B.; Taroni, A.; Niculae, A.; Kani, A. N.; Zawar, R.; v Suppa, M.; Savoldi, B.; Simons, A.; Merchant, R.; Levy, I. Y.; Pinto, F.; Yang, Z.; Xavier, Y.; Frontull, S.; Habibi, M. R. S.; Enevoldsen, K.; Majid, H. A.; Padovani, F.; Graf, T.; Bielakova, T.; Djurabaeva, S.; Ji, S.; Ahmad, R. A.; Stepachev, P.; Qi, J.; Munot, A. S.; Pakniat, A.; Terryn, A. R.; Lu, Y.; Paniv, Y.; Fu, X.; Adewumi, T.; Kumar, S.; Thunus, S. J. P. S.; Satish, S. H. B.; Bali, S.; Gupta, P.; Diallo, P. A. K. K.; Akrap, M.; Culjak, M.; Onderkov'a, K.; Attieh, J.; Tensay, E. T.; Fittschen, E.; Sagot, B.; Ni, J. and Fan, Yu Last Translation Benchmark. , working paper or preprint. www 

2025

Conference Articles

  1. Aissa, W.; Ba~neras-Roux, T.; Vanzeveren, E.; Gao, L.; Wilkens, R. and Franc cois, T. Assessing French Readability for Adults with Low Literacy: A Global and Local Perspective. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 20528-20550, Association for Computational Linguistics, Suhzou, China, 2025. doi  www 

2023

Conference Articles

  1. Aissa, W.; Ferecatu, M. and Crucianu, M. Multimodal Representations for Teacher-Guided Compositional Visual Reasoning. In Advanced Concepts for Intelligent Vision Systems. ACIVS 2023. Lecture Notes in Computer Science, pages 357-369, Springer Nature, Kumamoto, Japan, Lecture Notes in Computer Science 14124, 2023. doi  www 
  1. Aissa, W.; Ferecatu, M. and Crucianu, M. Curriculum Learning for Compositional Visual Reasoning. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, pages 888-897, Scitepress, Lisbon, Portugal, 2023. doi  www 

PhD Theses

  1. Aissa, W. Neural Module Networks for Compositional Visual Reasoning. Ph.D. Thesis, HESAM Université, 2023. doi 

2018

Conference Articles

  1. Aissa, W.; Soulier, L. and Denoyer, L. A Reinforcement Learning-driven Translation Model for Search-Oriented Conversational Systems. In Proceedings of the 2018 EMNLP Workshop SCAI: The 2nd International Workshop on Search-Oriented Conversational AI, pages 33-39, Bruxelles, Belgium, 2018. www 
Top