Publications
This section contains publications published by ISI over the past several decades.
2025
HIVTP: A Training-Free Method to Improve VLMs Efficiency via Hierarchical Visual Token Pruning Using Middle-Layer-Based Importance Score
Jingqi Xu, Jingxi Lu, Chenghao Li, Sreetama Sarkar, Peter A Beerel
arXiv preprint arXiv:2509.23663, 2025
LAWCAT: Efficient Distillation from Quadratic to Linear Attention with Convolution across Tokens for Long Context Modeling
Zeyu Liu, Souvik Kundu, Lianghao Jiang, Anni Li, Srikanth Ronanki, Sravan Bodapati, Gourav Datta, Peter A Beerel
arXiv preprint arXiv:2509.18467, 2025
FedDAPL: Toward Client-Private Generalization in Federated Learning
Soroosh Safari Loaliyan, Jose-Luis Ambite, Paul M Thompson, Neda Jahanshad, Greg Ver Steeg
arXiv preprint arXiv:2509.23688, 2025
Demonstration of optical pattern matching between two QPSK data channels using nonlinear wave mixing
Abdulrahman Alhaddad, Wing Ko, Amir Minoofar, Muralekrishnan Ramakrishnan, Huibin Zhou, Hongkun Lian, Zile Jiang, Xinzhou Su, Narek Karapetyan, Yingning Wang, Ruoyu Zeng, Ahmed Almaiman, Moshe Tur, Jonathan L Habif, Alan E Willner
Optics Letters 50 (19), 6125-6128, 2025
Coherent detection for the identification of scattered laser light in a bright incoherent background
J Habif, A RITTENBACH
US Patent App. 19/079,287, 2025
Semantic F1 Scores: Fair Evaluation Under Fuzzy Class Boundaries
Georgios Chochlakis, Jackson Trager, Vedant Jhaveri, Nikhil Ravichandran, Alexandros Potamianos, Shrikanth Narayanan
arXiv preprint arXiv:2509.21633, 2025
Believing without Seeing: Quality Scores for Contextualizing Vision-Language Model Explanations
Keyu He, Tejas Srinivasan, Brihi Joshi, Xiang Ren, Jesse Thomason, Swabha Swayamdipta
arXiv preprint arXiv:2509.25844, 2025
Exploring Opportunities to Support Novice Visual Artists' Inspiration and Ideation with Generative AI
Cindy Peng, Alice Qian, Linghao Jin, Jieneng Chen, Evans Xu Han, Paul Pu Liang, Hong Shen, Haiyi Zhu, Jane Hsieh
arXiv preprint arXiv:2509.24167, 2025
A Point Process Model of Skin Conductance Responses in a Stroop Task for Predicting Depression and Suicidal Ideation
Kleanthis Avramidis, Myzelle Hughes, Idan A Blank, Dani Byrd, Assal Habibi, Takfarinas Medani, Richard M Leahy, Shrikanth Narayanan
arXiv preprint arXiv:2510.00422, 2025
Assessing Visual Privacy Risks in Multimodal AI: A Novel Taxonomy-Grounded Evaluation of Vision-Language Models
Efthymios Tsaprazlis, Tiantian Feng, Anil Ramakrishna, Rahul Gupta, Shrikanth Narayanan
arXiv preprint arXiv:2509.23827, 2025
ARTI-6: Towards Six-dimensional Articulatory Speech Encoding
Jihwan Lee, Sean Foley, Thanathai Lertpetchpun, Kevin Huang, Yoonjeong Lee, Tiantian Feng, Louis Goldstein, Dani Byrd, Shrikanth Narayanan
arXiv preprint arXiv:2509.21447, 2025
Multilingual profiles and their association with cognition and brain structure among older Indian adults
Miguel Arce Renteria, Iris Strangmann, Yingxu Liu, Pranali Khobragade, Sarah Petrosyan, Niranjan Khandelwal, Joyita Banerjee, Emma Nichols, Erik Meijer, Shrikanth Narayanan, Kirsten M Lynch, Leon M Aksman, Jinkook Lee
Alzheimer's Association International Conference, 2025
Evaluation of Speech Foundation Models for ASR on Child-Adult Conversations in Autism Diagnostic Sessions
Aditya Asvin, Rimita Lahiri, Aditya Kommineni, Somer Bishop, Catherine Lord, Sudarsana Kadiri, Shrikanth Narayanan
Proc. WOCCI 2025, 31-35, 2025
PRECOG: Comprehensive Experimental Design and Stimuli Protocol for Investigating Depression and Suicidal Ideation
Myzelle Hughes, Colin McDaniel, Takfarinas Medani, Woojae Jeong, Idan Blank, Dani Byrd, Thomas McGee, Kleanthis Avramidis, Sudarsana Kadiri, Chinmay Chinara, Kristina Lerman, Elsi Kaiser, Richard Leahy, Shrikanth Narayanan, B Cahn
OSF, 2025
Predicting, evaluating, and explaining top misinformation spreaders via archetypal user behavior
Enrico Verdolotti, Luca Luceri, Silvia Giordano
Online Social Networks and Media 50, 100336, 2025
Optimizing Phase-Scheduling with Throughput Trade-offs in AQFP Digital Circuits
Robert S Aviles, Peter A Beerel
arXiv preprint arXiv:2510.03956, 2025
Psychological Steering in LLMs: An Evaluation of Effectiveness and Trustworthiness
Amin Banayeeanzade, Ala N Tak, Fatemeh Bahrani, Anahita Bolourani, Leonardo Blas, Emilio Ferrara, Jonathan Gratch, Sai Praneeth Karimireddy
arXiv preprint arXiv:2510.04484, 2025
Social-LLM: Modeling User Behavior at Scale Using Language Models and Social Network Data
Julie Jiang, Emilio Ferrara
Sci 7 (4), 138, 2025
Context Length Alone Hurts LLM Performance Despite Perfect Retrieval
Yufeng Du, Minyang Tian, Srikanth Ronanki, Subendhu Rongali, Sravan Bodapati, Aram Galstyan, Azton Wells, Roy Schwartz, Eliu A Huerta, Hao Peng
arXiv preprint arXiv:2510.05381, 2025
It’s the Data Stupid
Carl Kesselman, Robert Schuler
2025 IEEE International Conference on eScience (eScience), 377-378, 2025