activity
20242026
collaborators

7 papers

cs.CL2026

When Weak LLMs Speak with Confidence, Preference Alignment Gets Stronger

Amirabbas Afzali, Myeongho Jeon, Maria Brbic

Preference alignment is an essential step in adapting large language models (LLMs) to human values, but existing approaches typically depend on costly human annotations or large-sc…

cs.CV2026

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

Hesam Hosseini, Ghazal Hosseini Mighan, Amirabbas Afzali +2

Transformers have revolutionized Computer Vision (CV) through self-attention mechanisms. However, their complexity makes latent token representations difficult to interpret. We int…

cs.LG2025

LORE: Lagrangian-Optimized Robust Embeddings for Visual Encoders

Borna Khodabandeh, Amirabbas Afzali, Amirhossein Afsharrad +4

Visual encoders have become fundamental components in modern computer vision pipelines. However, ensuring robustness against adversarial perturbations remains a critical challenge.…

cs.IR2025

Controlling Gender Bias in Retrieval via a Backpack Architecture

Amirabbas Afzali, Amirreza Velae, Iman Ahmadi +1

The presence of social biases in large language models (LLMs) has become a significant concern in AI research. These biases, often embedded in training data, can perpetuate harmful…

cs.LG2025

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

Amirabbas Afzali, Amirhossein Afsharrad, Seyed Shahabeddin Mousavi +1

Large Language Models (LLMs) have made significant strides in generating human-like responses, largely due to preference alignment techniques. However, these methods often assume u…

cs.CV2025

Aligning Visual Contrastive learning models via Preference Optimization

Amirabbas Afzali, Borna Khodabandeh, Ali Rasekh +3

Contrastive learning models have demonstrated impressive abilities to capture semantic similarities by aligning representations in the embedding space. However, their performance c…