publications

2025

1. ICLR

   

   Aligning Visual Contrastive learning models via Preference Optimization

   Amirabbas Afzali^*, Borna Khodabandeh^*, Ali Rasekh, and 3 more authors

   International Conference on Learning Representations, 2025

   arXiv Bib

   @article{afzali2025aligningvisualcontrastivelearning,
     title = {Aligning Visual Contrastive learning models via Preference Optimization},
     author = {Afzali, Amirabbas and Khodabandeh, Borna and Rasekh, Ali and JafariNodeh, Mahyar and kazemi, Sepehr and Gottschalk, Simon},
     year = {2025},
     journal = {International Conference on Learning Representations},
     archiveprefix = {arXiv},
     primaryclass = {cs.CV},
     url = {https://arxiv.org/abs/2411.08923},
     equal_contribution = {Amirabbas Afzali and Borna Khodabandeh},
   }

2. RLC

   

   One Goal, Many Challenges: Robust Preference Optimization Amid Content-Aware and Multi-Source Noise

   Amirabbas Afzali, Amirhossein Afsharrad, Seyed Shahabeddin Mousavi, and 1 more author

   Reinforcement Learning Conference, 2025

   arXiv Bib

   @article{afzali2025goalchallengesrobustpreference,
     title = {One Goal, Many Challenges: Robust Preference Optimization Amid Content-Aware and Multi-Source Noise},
     author = {Afzali, Amirabbas and Afsharrad, Amirhossein and Mousavi, Seyed Shahabeddin and Lall, Sanjay},
     year = {2025},
     journal = {Reinforcement Learning Conference},
     archiveprefix = {arXiv},
     primaryclass = {cs.LG},
     url = {https://arxiv.org/abs/2503.12301},
   }

3. AAAI

   

   Clustering Time Series Data with Gaussian Mixture Embeddings in a Graph Autoencoder Framework

   Amirabbas Afzali^*, Hesam Hosseini^*, Mohmmadamin Mirzai, and 1 more author

   AI4Research Workshop at AAAI, 2025

   arXiv Bib

   @article{afzali2024clusteringtimeseriesdata,
     title = {Clustering Time Series Data with Gaussian Mixture Embeddings in a Graph Autoencoder Framework},
     author = {Afzali, Amirabbas and Hosseini, Hesam and Mirzai, Mohmmadamin and Amini, Arash},
     year = {2025},
     journal = {AI4Research Workshop at AAAI},
     archiveprefix = {arXiv},
     primaryclass = {cs.LG},
     url = {https://arxiv.org/abs/2411.16972},
     equal_contribution = {Amirabbas Afzali and Hesam Hosseini},
   }

4. 

   ULTra: Unveiling Latent Token Interpretability in Transformer-Based Understanding and Segmentation

   Hesam Hosseini, Ghazal Hosseini Mighan, Amirabbas Afzali, and 2 more authors

   2025

   arXiv Bib

   @article{hosseini2025ultraunveilinglatenttoken,
     title = {ULTra: Unveiling Latent Token Interpretability in Transformer-Based Understanding and Segmentation},
     author = {Hosseini, Hesam and Mighan, Ghazal Hosseini and Afzali, Amirabbas and Amini, Sajjad and Houmansadr, Amir},
     year = {2025},
     archiveprefix = {arXiv},
     primaryclass = {cs.CV},
     url = {https://arxiv.org/abs/2411.12589},
   }