Amirabbas Afzali

Joined

September 2024

Names

Amirabbas Afzali (Preferred)

Emails

****@gmail.com (Confirmed)

,

****@ee.sharif.edu (Confirmed)

,

****@aktus.ai (Confirmed)

,

****@epfl.ch (Confirmed)

Personal Links

Career & Education History

Undergrad student

Electrical Engineering , Sharif University of Technology, Sharif University of Technology (ee.sharif.edu)

2021 – 2025

Advisors, Relations & Conflicts

Coauthor

2024 – Present

Expertise

Deep Learning

2023 – Present

Reinforce Learning

2023 – Present

Publications

When Weak LLMs Speak with Confidence, Preference Alignment Gets Stronger
Amirabbas Afzali, Myeongho Jeon, Maria Brbic
- ICLR 2026 Poster
- Readers: Everyone
ULTra: Unveiling Latent Token Interpretability in Transformer-Based Understanding and Segmentation
Hesam Hosseini, Ghazal Hosseini Mighan, Amirabbas Afzali, Sajjad Amini, Amir Houmansadr
- Accepted by TMLR
- Readers: Everyone
LORE: Lagrangian-Optimized Robust Embeddings for Visual Encoders
Borna khodabandeh, Amirabbas Afzali, Amirhossein Afsharrad, Seyed Shahabeddin Mousavi, Sanjay Lall, Sajjad Amini, Seyed-Mohsen Moosavi-Dezfooli
- NeurIPS 2025 poster
- Readers: Everyone
One Goal, Many Challenges: Robust Preference Optimization Amid Content-Aware and Multi-Source Noise
Amirabbas Afzali, Amirhossein Afsharrad, Seyed Shahabeddin Mousavi, Sanjay Lall
- CoRR 2025
- Readers: Everyone
One Goal, Many Challenges: Robust Preference Optimization Amid Content-Aware, Multi-Source Noise
Amirabbas Afzali, Amirhossein Afsharrad, Seyed Shahabeddin Mousavi, Sanjay Lall
- RLC 2025
- Readers: Everyone
One Goal, Many Challenges: Robust Preference Optimization Amid Content-Aware and Multi-Source Noise
Amirabbas Afzali, Amirhossein Afsharrad, Seyed Shahabeddin Mousavi, Sanjay Lall
- SCSL @ ICLR 2025
- Readers: Everyone
ULTra: Unveiling Latent Token Interpretability in Transformer-Based Understanding
Hesam Hosseini, Ghazal Hosseini Mighan, Amirabbas Afzali, Sajjad Amini, Amir Houmansadr
- ICLR 2025 Workshop XAI4Science
- Readers: Everyone
Aligning Visual Contrastive learning models via Preference Optimization
Amirabbas Afzali, Borna Khodabandeh, Ali Rasekh, Mahyar JafariNodeh, Sepehr Kazemi Ranjbar, Simon Gottschalk
- ICLR 2025
- Readers: Everyone
Clustering Time Series Data with Gaussian Mixture Embeddings in a Graph Autoencoder Framework
Amirabbas Afzali, Hesam Hosseini, Mohamad Amin Mirzai, Arash Amini
- AI4Research @ AAAI 2025 Poster
- Readers: Everyone
Aligning Visual Contrastive learning models via Preference Optimization
Amirabbas Afzali, Borna khodabandeh, Ali Rasekh, Mahyar JafariNodeh, Sepehr Kazemi Ranjbar, Simon Gottschalk
- ICLR 2025 Poster
- Readers: Everyone

View all 13 publications

Co-Authors