Amir Mohammad Izadi
Research assistant
Publications
-
ACL Findings 2026
Mechanistic Interpretability of Large-Scale Counting in LLMs through a System-2 Strategy
Hosein Hasani, Mohammadali Banayeeanzade, Ali Nafisi, Sadegh Mohammadian, Fatemeh Askari, Mobin Bagherian, Amirmohammad Izadi, Mahdieh Soleymani Baghshah
Reveals how a System-2 strategy decomposes large counting problems, transfers partial counts through dedicated attention heads, and aggregates them reliably.
Findings of the Association for Computational Linguistics: ACL, 2026
-
arXiv 2026
Causal Attribution via Activation Patching
Amirmohammad Izadi, Mohammadali Banayeeanzade, Akbar Mirrokni, Hosein Hasani, Mobin Bagherian, Faridoun Mehri, Mahdieh Soleymani Baghshah
Develops activation-patching methods for tracing causal contributions inside neural networks rather than relying on correlational explanations.
arXiv preprint, 2026
-
TMLR 2025
CAREL: Instruction-Guided Reinforcement Learning with Cross-Modal Auxiliary Objectives
Armin Saghafian, Amirmohammad Izadi, Negin Hashemi Dijujin, Mahdieh Soleymani Baghshah
Uses cross-modal auxiliary objectives and instruction tracking to improve sample efficiency and systematic generalization in language-guided reinforcement learning.
Transactions on Machine Learning Research (TMLR), 2025
-
arXiv 2025
T2I-FineEval: Fine-Grained Compositional Metric for Text-to-Image Evaluation
Seyed Mohammad Hadi Hosseini, Amirmohammad Izadi, Ali Abdollahi, Armin Saghafian, Mahdieh Soleymani Baghshah
Introduces a fine-grained metric for measuring whether generated images satisfy the individual components of complex prompts.
arXiv preprint, 2025
-
arXiv 2025
Fine-Grained Alignment and Noise Refinement for Compositional Text-to-Image Generation
Amirmohammad Izadi, Seyed Mohammad Hadi Hosseini, Soroush Vafaie Tabar, Ali Abdollahi, Armin Saghafian, Mahdieh Soleymani Baghshah
Refines alignment signals and initial noise to improve compositional correctness without retraining the text-to-image model.
arXiv preprint, 2025
-
NeurIPS 2025
Visual Structures Help Visual Reasoning: Addressing the Binding Problem in LVLMs
Amirmohammad Izadi, Mohammadali Banayeeanzade, Fatemeh Askari, Ali Rahimiakbar, Mohammad Mahdi Vahedi, Hosein Hasani, Mahdieh Soleymani Baghshah
Introduces VISER, which adds lightweight spatial structure and sequential-scanning prompts to improve counting, visual search, and spatial reasoning.
Advances in Neural Information Processing Systems (NeurIPS), 2025
-
arXiv 2025
Uncovering Grounding IDs: How External Cues Shape Multimodal Binding
Hosein Hasani, Amirmohammad Izadi, Fatemeh Askari, Mobin Bagherian, Sadegh Mohammadian, Mahdieh Soleymani Baghshah
Studies how external cues create grounding identifiers that help multimodal models bind objects to their properties and locations.
arXiv preprint, 2025
-
arXiv 2025
Understanding Counting Mechanisms in Large Language and Vision-Language Models
Hosein Hasani, Amirmohammad Izadi, Fatemeh Askari, Mobin Bagherian, Sadegh Mohammadian, Mahdieh Soleymani Baghshah
Compares internal counting strategies across language and vision-language models to reveal shared mechanisms and modality-specific failures.
arXiv preprint, 2025