105 citations · 211 across the 16 of their papers we have counts for
20 papers
What CLIP Knows but Cannot Say: Recovering Negation from Frozen Intermediate Features
Chen-Yi Lu, Yueh-Shao Chen, Somali Chaterji
Contrastive vision-language models such as CLIP map semantically opposite phrases (e.g., "a dog" vs. "not a dog") to nearly identical embeddings, rendering them insensitive to nega…
Look Less, Think Faster: Joint Token-Compute Adaptation for Multimodal LLMs
Pengcheng Wang, Zhiquan Wang, Jayoung Lee +5
Multimodal Large Language Models (MLLMs) have recently demonstrated strong performance across vision-language tasks. However, their high inference cost, arising from both the large…
Digital Guardians: The Past and The Future of Cyber-Physical Resilience
Saurabh Bagchi, Hyunseung Kim, Tarek Abdelzaher +20
Resilience in cyber-physical systems (CPS) is the fundamental ability to maintain safety and critical functionality despite adverse "perturbations," which includes security attacks…
Hubs and Spokes Learning: Efficient and Scalable Collaborative Machine Learning
Atul Sharma, Kavindu Herath, Saurabh Bagchi +2
We introduce the Hubs and Spokes Learning (HSL) framework, a novel paradigm for collaborative machine learning that combines the strengths of Federated Learning (FL) and Decentrali…
Learning to Inference Adaptively for Multimodal Large Language Models
Zhuoyan Xu, Khoi Duc Nguyen, Preeti Mukherjee +4
Multimodal Large Language Models (MLLMs) have shown impressive capabilities in visual reasoning, yet come with substantial computational cost, limiting their deployment in resource…
SKALD: Learning-Based Shot Assembly for Coherent Multi-Shot Video Creation
Chen Yi Lu, Md Mehrab Tanjim, Ishita Dasgupta +4
We present SKALD, a multi-shot video assembly method that constructs coherent video sequences from candidate shots with minimal reliance on text. Central to our approach is the Lea…
The Federation Strikes Back: A Survey of Federated Learning Privacy Attacks, Defenses, Applications, and Policy Landscape
Joshua C. Zhao, Saurabh Bagchi, Salman Avestimehr +7
Deep learning has shown incredible potential across a wide array of tasks, and accompanied by this growth has been an insatiable appetite for data. However, a large amount of data…
Virtuoso: Video-based Intelligence for real-time tuning on SOCs
Jayoung Lee, PengCheng Wang, Ran Xu +5
Efficient and adaptive computer vision systems have been proposed to make computer vision tasks, such as image classification and object detection, optimized for embedded or mobile…
Lerna: Transformer Architectures for Configuring Error Correction Tools for Short- and Long-Read Genome Sequencing
Atul Sharma, Pranjal Jain, Ashraf Mahgoub +3
Sequencing technologies are prone to errors, making error correction (EC) necessary for downstream applications. EC tools need to be manually configured for optimal performance. We…
TESSERACT: Gradient Flip Score to Secure Federated Learning Against Model Poisoning Attacks
Atul Sharma, Wei Chen, Joshua Zhao +3
Federated learning---multi-party, distributed learning in a decentralized environment---is vulnerable to model poisoning attacks, even more so than centralized learning approaches.…
ORPHEUS: Living Labs for End-to-End Data Infrastructures for Digital Agriculture
Pengcheng Wang, Edgardo Barsallo Yi, Tomas Ratkus +1
IoT networks are being used to collect, analyze, and utilize sensor data. There are still some key requirements to leverage IoT networks in digital agriculture, e.g., design and de…
Federated Action Recognition on Heterogeneous Embedded Devices
Pranjal Jain, Shreyas Goenka, Saurabh Bagchi +2
Federated learning allows a large number of devices to jointly learn a model without sharing data. In this work, we enable clients with limited computing power to perform action re…
Ambrosia: Reduction in Data Transfer from Sensor to Server for Increased Lifetime of IoT Sensor Nodes
Shikhar Suryavansh, Abu Benna, Chris Guest +1
Data transmission accounts for significant energy consumption in wireless sensor networks where streaming data is generatedby the sensors. This impedes their use in many settings,…
JANUS: Benchmarking Commercial and Open-Source Cloud and Edge Platforms for Object and Anomaly Detection Workloads
Karthick Shankar, Pengcheng Wang, Ran Xu +2
With diverse IoT workloads, placing compute and analytics close to where data is collected is becoming increasingly important. We seek to understand what is the performance and the…
ApproxDet: Content and Contention-Aware Approximate Object Detection for Mobiles
Ran Xu, Chen-lin Zhang, Pengcheng Wang +5
Advanced video analytic systems, including scene classification and object detection, have seen widespread success in various domains such as smart cities and autonomous transporta…
Hybrid Low-Power Wide-Area Mesh Network for IoT Applications
Xiaofan Jiang, Heng zhang, Edgardo Alberto Barsallo Yi +6
The recent advancement of the Internet of Things (IoT) enables the possibility of data collection from diverse environments using IoT devices. However, despite the rapid advancemen…
Artificial Intelligence for Digital Agriculture at Scale: Techniques, Policies, and Challenges
Somali Chaterji, Nathan DeLay, John Evans +4
Digital agriculture has the promise to transform agricultural throughput. It can do this by applying data science and engineering for mapping input factors to crop throughput, whil…
Resilient Cyberphysical Systems and their Application Drivers: A Technology Roadmap
Somali Chaterji, Parinaz Naghizadeh, Muhammad Ashraful Alam +14
Cyberphysical systems (CPS) are ubiquitous in our personal and professional lives, and they promise to dramatically improve micro-communities (e.g., urban farms, hospitals), macro-…
Grand Challenges in Resilience: Autonomous System Resilience through Design and Runtime Measures
Saurabh Bagchi, Vaneet Aggarwal, Somali Chaterji +13
A set of about 80 researchers, practitioners, and federal agency program managers participated in the NSF-sponsored Grand Challenges in Resilience Workshop held on Purdue campus on…
ATHENA: Automated Tuning of Genomic Error Correction Algorithms using Language Models
Mustafa Abdallah, Ashraf Mahgoub, Saurabh Bagchi +1
The performance of most error-correction algorithms that operate on genomic sequencer reads is dependent on the proper choice of its configuration parameters, such as the value of…