Mohammad Shahab Sepehri

Mohammad Shahab Sepehri

Auto-generated profile, based on publicly available information

Mohammad Shahab Sepehri

Department of Electrical and Computer Engineering University of Southern California Los Angeles CA USA

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
Verified
Journal Article
Closed access
MSMohammad Shahab Sepehri
Mohammad Shahab Sepehri
ZFZalan Fabian
Zalan Fabian
MSMaryam Soltanolkotabi
Maryam Soltanolkotabi
MSMahdi Soltanolkotabi
Mahdi Soltanolkotabi

4 July 2025 in arXiv
Verified
Preprint
Open access
PDF file
AMAsal Mehradfar
Asal Mehradfar
MSMohammad Shahab Sepehri
Mohammad Shahab Sepehri
JHJose Miguel Hernandez-Lobato
Jose Miguel Hernandez-Lobato
GKGlen S. Kwon
Glen S. Kwon
MSMahdi Soltanolkotabi
Mahdi Soltanolkotabi
Morteza RasoulianboroujeniMorteza Rasoulianboroujeni
Morteza Rasoulianboroujeni
The discovery of new ionizable lipids for efficient lipid nanoparticle (LNP)-mediated RNA delivery remains a critical bottleneck for RNA-based therapeutics development. Recent advances have highlighted the potential of machine learning (ML) to predict transfection efficiency from molecular structure, enabling high-throughput virtual screening and accelerating lead identification. However, existing approaches are hindered by inadequate data quality, ineffective feature representations, low predictive accuracy, and poor generalizability. Here, we present LANTERN (Lipid nANoparticle Transfection Efficiency pRedictioN), a robust ML framework for predicting transfection efficiency based on ionizable lipid representation. We benchmarked a diverse set of ML models against AGILE, a previously published model developed for transfection prediction. Our results show that combining simpler models with chemically informative features, particularly count-based Morgan fingerprints, outperforms more complex models that rely on internally learned embeddings, such as AGILE. We also show that a multi-layer perceptron trained on a combination of Morgan fingerprints and Expert descriptors achieved the highest performance ($\text{R}^2$ = 0.8161, r = 0.9053), significantly exceeding AGILE ($\text{R}^2$ = 0.2655, r = 0.5488). We show that the models in LANTERN consistently have strong performance across multiple evaluation metrics. Thus, LANTERN offers a robust benchmarking framework for LNP transfection prediction and serves as a valuable tool for accelerating lipid-based RNA delivery systems design.

1 January 2025 in Advances in neural information processing systems
Verified
Conference Paper
Closed access
MSMohammad Shahab Sepehri
Mohammad Shahab Sepehri
BTBerk Tinaz
Berk Tinaz
ZFZalan Fabian
Zalan Fabian
MSMahdi Soltanolkotabi
Mahdi Soltanolkotabi
Mental visualization, the ability to construct and manipulate visual representations internally, is a core component of human cognition and plays a vital role in tasks involving reasoning, prediction, and abstraction. Despite the rapid progress of Multimodal Large Language Models (MLLMs), current benchmarks primarily assess passive visual perception, offering limited insight into the more active capability of internally constructing visual patterns to support problem solving. Yet mental visualization is a critical cognitive skill in humans, supporting abilities such as spatial navigation, predicting physical trajectories, and solving complex visual problems through imaginative simulation. To bridge this gap, we introduce Hyperphantasia, a synthetic benchmark designed to evaluate the mental visualization abilities of MLLMs through four carefully constructed puzzles. Each puzzle is procedurally generated and presented at three difficulty levels, enabling controlled analysis of model performance across increasing complexity. Our comprehensive evaluation of state-of-the-art models reveals a substantial gap between the performance of humans and MLLMs. Additionally, we explore the potential of reinforcement learning to improve visual simulation capabilities. Our findings suggest that while some models exhibit partial competence in recognizing visual patterns, robust mental visualization remains an open challenge for current MLLMs. Our dataset is publicly available at Huggingface1, and the evaluation code can be found at GitHub2.

4 July 2025 in arXiv
Verified
Preprint
Open access
PDF file
HGHaosheng Gan
Haosheng Gan
BTBerk Tinaz
Berk Tinaz
MSMohammad Shahab Sepehri
Mohammad Shahab Sepehri
ZFZalan Fabian
Zalan Fabian
MSMahdi Soltanolkotabi
Mahdi Soltanolkotabi
Current text-to-image (T2I) benchmarks evaluate models on rigid prompts, potentially underestimating true generative capabilities due to prompt sensitivity and creating biases that favor certain models while disadvantaging others. We introduce ConceptMix++, a framework that disentangles prompt phrasing from visual generation capabilities by applying iterative prompt optimization. Building on ConceptMix, our approach incorporates a multimodal optimization pipeline that leverages vision-language model feedback to refine prompts systematically. Through extensive experiments across multiple diffusion models, we show that optimized prompts significantly improve compositional generation performance, revealing previously hidden model capabilities and enabling fairer comparisons across T2I models. Our analysis reveals that certain visual concepts -- such as spatial relationships and shapes -- benefit more from optimization than others, suggesting that existing benchmarks systematically underestimate model performance in these categories. Additionally, we find strong cross-model transferability of optimized prompts, indicating shared preferences for effective prompt phrasing across models. These findings demonstrate that rigid benchmarking approaches may significantly underrepresent true model capabilities, while our framework provides more accurate assessment and insights for future development.