1 citations · 3 across the 11 of their papers we have counts for
11 papers
Causal Attribution via Activation Patching
Amirmohammad Izadi, Mohammadali Banayeeanzade, Alireza Mirrokni +4
Attribution methods for Vision Transformers (ViTs) aim to identify image regions that influence model predictions, but producing faithful and well-localized attributions remains ch…
Mechanistic Interpretability of Large-Scale Counting in LLMs through a System-2 Strategy
Hosein Hasani, Mohammadali Banayeeanzade, Ali Nafisi +5
Large language models (LLMs), despite strong performance on complex mathematical problems, exhibit systematic limitations in counting tasks. This issue arises from the architectura…
Limits and Gains of Test-Time Scaling in Vision-Language Reasoning
Mohammadjavad Ahmadpour, Amirmahdi Meighani, Payam Taebi +3
Test-time scaling (TTS) has emerged as a powerful paradigm for improving the reasoning ability of Large Language Models (LLMs) by allocating additional computation at inference, ye…
Understanding Counting Mechanisms in Large Language and Vision-Language Models
Hosein Hasani, Amirmohammad Izadi, Fatemeh Askari +4
Counting is one of the fundamental abilities of large language models (LLMs) and large vision-language models (LVLMs). This paper examines how these foundation models represent and…
Uncovering Grounding IDs: How External Cues Shape Multi-Modal Binding
Hosein Hasani, Amirmohammad Izadi, Fatemeh Askari +4
Large vision-language models (LVLMs) perform well on multimodal tasks, but their ability to reason and precisely align visual and textual information still has room for improvement…
Visual Structures Helps Visual Reasoning: Addressing the Binding Problem in VLMs
Amirmohammad Izadi, Mohammad Ali Banayeeanzade, Fatemeh Askari +4
Despite progress in Large Vision-Language Models (LVLMs), their capacity for visual reasoning is often limited by the binding problem: the failure to reliably associate perceptual…
T2I-FineEval: Fine-Grained Compositional Metric for Text-to-Image Evaluation
Seyed Mohammad Hadi Hosseini, Amir Mohammad Izadi, Ali Abdollahi +2
Although recent text-to-image generative models have achieved impressive performance, they still often struggle with capturing the compositional complexities of prompts including a…
Fine-Grained Alignment and Noise Refinement for Compositional Text-to-Image Generation
Amir Mohammad Izadi, Seyed Mohammad Hadi Hosseini, Soroush Vafaie Tabar +3
Text-to-image generative models have made significant advancements in recent years; however, accurately capturing intricate details in textual prompts-such as entity missing, attri…
CAREL: Instruction-guided reinforcement learning with cross-modal auxiliary objectives
Armin Saghafian, Amirmohammad Izadi, Negin Hashemi Dijujin +1
Grounding the instruction in the environment is a key step in solving language-guided goal-reaching reinforcement learning problems. In automated reinforcement learning, a key conc…
Detecting Popular Social Events through Limited Observation with Deep Survival Analysis
Maryam Ramezani, Hossein Goli, AmirMohammad Izadi +1
Users increasing activity across various social networks made it the most widely used platform for exchanging and propagating information among individuals. To spread information w…
ComAlign: Compositional Alignment in Vision-Language Models
Ali Abdollah, Amirmohammad Izadi, Armin Saghafian +5
Vision-language models (VLMs) like CLIP have showcased a remarkable ability to extract transferable features for downstream tasks. Nonetheless, the training process of these models…