activity
20242026
collaborators

49 papers

cs.CV2026

VISTA: Test-Time Compositional Alignment for Visual Autoregressive Generation

Hossein Shahabadi, Niki Sepasian, Mahdieh Soleymani Baghshah

Visual autoregressive (VAR) models have emerged as a fast, high-quality alternative to diffusion for text-to-image generation, but like diffusion models they exhibit persistent com…

cs.LG2026

Efficient Adversarial Attacks on High-dimensional Offline Bandits

Seyed Mohammad Hadi Hosseini, Amir Najafi, Mahdieh Soleymani Baghshah

Bandit algorithms have recently emerged as a powerful tool for evaluating machine learning models, including generative image models and large language models, by efficiently ident…

cs.LG2026

SUSD: Structured Unsupervised Skill Discovery through State Factorization

Seyed Mohammad Hadi Hosseini, Mahdieh Soleymani Baghshah

Unsupervised Skill Discovery (USD) aims to autonomously learn a diverse set of skills without relying on extrinsic rewards. One of the most common USD approaches is to maximize the…

cs.CV2026

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…

cs.SD2026

Persian MusicGen: A Large-Scale Dataset and Culturally-Aware Generative Model for Persian Music

Mohammad Hossein Sameti, Diba Hadi Esfangereh, Sepehr Harfi Moridani +2

Persian music, with its unique tonalities, modal systems (Dastgah), and rhythmic structures, presents significant challenges for music generation models trained primarily on Wester…

cs.CL2026

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…