Publications (134)
Data Markets to support AI for All: Pricing, Valuation and Governance
Ramesh Raskar, Praneeth Vepakomma, Tristan Swedish +1
We discuss a data market technique based on intrinsic (relevance and uniqueness) as well as extrinsic value (influenced by supply and demand) of data. For intrinsic value, we expla…
On Unlimited Sampling
Ayush Bhandari, Felix Krahmer, Ramesh Raskar
Shannon's sampling theorem provides a link between the continuous and the discrete realms stating that bandlimited signals are uniquely determined by its values on a discrete set.…
Recent Advances in Imaging Around Corners
Tomohiro Maeda, Guy Satat, Tristan Swedish +2
Seeing around corners, also known as non-line-of-sight (NLOS) imaging is a computational method to resolve or recover objects hidden around corners. Recent advances in imaging arou…
NANDA Adaptive Resolver: Architecture for Dynamic Resolution of AI Agent Names
John Zinky, Hema Seshadri, Mahesh Lambe +2
AdaptiveResolver is a dynamic microservice architecture designed to address the limitations of static endpoint resolution for AI agent communication in distributed, heterogeneous e…
Upgrade or Switch: Do We Need a Next-Gen Trusted Architecture for the Internet of AI Agents?
Ramesh Raskar, Pradyumna Chari, Jared James Grogan +11
The emerging Internet of AI Agents challenges existing web infrastructure designed for human-scale, reactive interactions. Unlike traditional web resources, autonomous AI agents in…
No Peek: A Survey of private distributed deep learning
Praneeth Vepakomma, Tristan Swedish, Ramesh Raskar +2
We survey distributed deep learning models for training or inference without accessing raw data from clients. These methods aim to protect confidential patterns in data while still…
Distributed learning of deep neural network over multiple agents
Otkrist Gupta, Ramesh Raskar
In domains such as health care and finance, shortage of labeled data and computational resources is a critical issue while developing machine learning algorithms. To address the is…
SUNDIAL: 3D Satellite Understanding through Direct, Ambient, and Complex Lighting Decomposition
Nikhil Behari, Akshat Dave, Kushagra Tiwary +2
3D modeling from satellite imagery is essential in areas of environmental science, urban planning, agriculture, and disaster response. However, traditional 3D modeling techniques f…
Economic Impact of Discoverability of Localities and Addresses in India
Santanu Bhattacharya, Sai Sri Sathya, Kabir Rustogi +1
Most of the earth's population has a poorly defined addressing system, thus having a poorly discoverable residence, property or business locations on a map. Easily discoverable add…
Resolving Multi-path Interference in Time-of-Flight Imaging via Modulation Frequency Diversity and Sparse Regularization
Ayush Bhandari, Achuta Kadambi, Refael Whyte +4
Time-of-flight (ToF) cameras calculate depth maps by reconstructing phase shifts of amplitude-modulated signals. For broad illumination or transparent objects, reflections from mul…
A Review of Homomorphic Encryption Libraries for Secure Computation
Sai Sri Sathya, Praneeth Vepakomma, Ramesh Raskar +2
In this paper we provide a survey of various libraries for homomorphic encryption. We describe key features and trade-offs that should be considered while choosing the right approa…
AdaSplit: Adaptive Trade-offs for Resource-constrained Distributed Deep Learning
Ayush Chopra, Surya Kant Sahu, Abhishek Singh +4
Distributed deep learning frameworks like federated learning (FL) and its variants are enabling personalized experiences across a wide range of web clients and mobile/IoT devices.…
Verifiable Proof of Health using Public Key Cryptography
Abhishek Singh, Ramesh Raskar
In the current pandemic, testing continues to be the most important tool for monitoring and curbing the disease spread and early identification of the disease to perform health-rel…
Spatial Calibration of Diffuse LiDARs
Nikhil Behari, Ramesh Raskar
Diffuse direct time-of-flight LiDARs report per-pixel depth histograms formed by aggregating photon returns over a wide instantaneous field of view, violating the single-ray assump…
Accelerating Neural Architecture Search using Performance Prediction
Bowen Baker, Otkrist Gupta, Ramesh Raskar +1
Methods for neural network hyperparameter optimization and meta-modeling are computationally expensive due to the need to train a large number of model configurations. In this pape…
Proximity Inference with Wifi-Colocation during the COVID-19 Pandemic
Mikhail Dmitrienko, Abhishek Singh, Patrick Erichsen +1
In this work we propose a WiFi colocation methodology for digital contact tracing. The approach works by having a device scan and store nearby access point information to perform p…
Differentiable Agent-based Epidemiology
Ayush Chopra, Alexander RodrÃguez, Jayakumar Subramanian +4
Mechanistic simulators are an indispensable tool for epidemiology to explore the behavior of complex, dynamic infections under varying conditions and navigate uncertain environment…
Augmenting Light Field to model Wave Optics effects
Se Baek Oh, George Barbastathis, Ramesh Raskar
The ray-based 4D light field representation cannot be directly used to analyze diffractive or phase--sensitive optical elements. In this paper, we exploit tools from wave optics an…
Digital Landscape of COVID-19 Testing: Challenges and Opportunities
Darshan Gandhi, Rohan Sukumaran, Priyanshi Katiyar +23
The COVID-19 Pandemic has left a devastating trail all over the world, in terms of loss of lives, economic decline, travel restrictions, trade deficit, and collapsing economy inclu…
What is the right addressing scheme for India?
Kabir Rustogi, Santanu Bhattacharya, Margaret Church +1
Computer generated addresses are coming to your neighborhood because most places in the world do not have an assigned meaningful street address. In India, 80% of the addresses are…
A Roadmap for Greater Public Use of Privacy-Sensitive Government Data: Workshop Report
Chris Clifton, Bradley Malin, Anna Oganian +2
Government agencies collect and manage a wide range of ever-growing datasets. While such data has the potential to support research and evidence-based policy making, there are conc…
Using the NANDA Index Architecture in Practice: An Enterprise Perspective
Sichao Wang, Ramesh Raskar, Mahesh Lambe +5
The proliferation of autonomous AI agents represents a paradigmatic shift from traditional web architectures toward collaborative intelligent systems requiring sophisticated mechan…
Measurement of Snowpack Density, Grain Size, and Black Carbon Concentration Using Time-domain Diffuse Optics
Connor Henley, Joseph Hollmann, Colin Meyer +1
Diffuse optical spectroscopy (DOS) techniques aim to characterize scattering media by examining their optical response to laser illumination. Time-domain DOS methods involve illumi…
Adding Location and Global Context to the Google/Apple Exposure Notification Bluetooth API
Ramesh Raskar, Abhishek Singh, Sam Zimmerman +1
Contact tracing requires a strong understanding of the context of a user, and location with other sensory data could provide a context for any infection encounter. Although Bluetoo…
Domain Generalization In Robust Invariant Representation
Gauri Gupta, Ritvik Kapila, Keshav Gupta +1
Unsupervised approaches for learning representations invariant to common transformations are used quite often for object recognition. Learning invariances makes models more robust…
Split Learning for collaborative deep learning in healthcare
Maarten G. Poirot, Praneeth Vepakomma, Ken Chang +3
Shortage of labeled data has been holding the surge of deep learning in healthcare back, as sample sizes are often small, patient information cannot be shared openly, and multi-cen…
Ripple Effect Protocol: Coordinating Agent Populations
Ayush Chopra, Aman Sharma, Feroz Ahmad +3
Modern AI agents can exchange messages using protocols such as A2A and ACP, yet these mechanisms emphasize communication over coordination. As agent populations grow, this limitati…
Shoot-Bounce-3D: Single-Shot Occlusion-Aware 3D from Lidar by Decomposing Two-Bounce Light
Tzofi Klinghoffer, Siddharth Somasundaram, Xiaoyu Xiang +5
3D scene reconstruction from a single measurement is challenging, especially in the presence of occluded regions and specular materials, such as mirrors. We address these challenge…
DENALI: A Dataset Enabling Non-Line-of-Sight Spatial Reasoning with Low-Cost LiDARs
Nikhil Behari, Diego Rivero, Luke Apostolides +3
Consumer LiDARs in mobile devices and robots typically output a single depth value per pixel. Yet internally, they record full time-resolved histograms containing direct and multi-…
Multi-velocity neural networks for gesture recognition in videos
Otkrist Gupta, Dan Raviv, Ramesh Raskar
We present a new action recognition deep neural network which adaptively learns the best action velocities in addition to the classification. While deep neural networks have reache…
Deep video gesture recognition using illumination invariants
Otkrist Gupta, Dan Raviv, Ramesh Raskar
In this paper we present architectures based on deep neural nets for gesture recognition in videos, which are invariant to local scaling. We amalgamate autoencoder and predictor ar…
FedML: A Research Library and Benchmark for Federated Machine Learning
Chaoyang He, Songze Li, Jinhyun So +17
Federated learning (FL) is a rapidly growing research field in machine learning. However, existing FL libraries cannot adequately support diverse algorithmic development; inconsist…
Beyond DNS: Unlocking the Internet of AI Agents via the NANDA Index and Verified AgentFacts
Ramesh Raskar, Pradyumna Chari, John Zinky +15
The Internet is poised to host billions to trillions of autonomous AI agents that negotiate, delegate, and migrate in milliseconds and workloads that will strain DNS-centred identi…
Scalable Collaborative Learning via Representation Sharing
Frédéric Berdoz, Abhishek Singh, Martin Jaggi +1
Privacy-preserving machine learning has become a key conundrum for multi-party artificial intelligence. Federated learning (FL) and Split Learning (SL) are two frameworks that enab…
A Compressive Multi-Mode Superresolution Display
Felix Heide, James Gregson, Gordon Wetzstein +2
Compressive displays are an emerging technology exploring the co-design of new optical device configurations and compressive computation. Previously, research has shown how to impr…
DAVED: Data Acquisition via Experimental Design for Data Markets
Charles Lu, Baihe Huang, Sai Praneeth Karimireddy +3
The acquisition of training data is crucial for machine learning applications. Data markets can increase the supply of data, particularly in data-scarce domains such as healthcare,…
Safepaths: Vaccine Diary Protocol and Decentralized Vaccine Coordination System using a Privacy Preserving User Centric Experience
Abhishek Singh, Ramesh Raskar, Anna Lysyanskaya
In this early draft, we present an end-to-end decentralized protocol for the secure and privacy preserving workflow of vaccination, vaccination status verification, and adverse rea…
Blurred LiDAR for Sharper 3D: Robust Handheld 3D Scanning with Diffuse LiDAR and RGB
Nikhil Behari, Aaron Young, Siddharth Somasundaram +3
3D surface reconstruction is essential across applications of virtual reality, robotics, and mobile scanning. However, RGB-based reconstruction often fails in low-texture, low-ligh…
Evolution of AI Agent Registry Solutions: Centralized, Enterprise, and Distributed Approaches
Aditi Singh, Abul Ehtesham, Mahesh Lambe +8
Autonomous AI agents now operate across cloud, enterprise, and decentralized domains, creating demand for registry infrastructures that enable trustworthy discovery, capability neg…
Towards Viewpoint Robustness in Bird's Eye View Segmentation
Tzofi Klinghoffer, Jonah Philion, Wenzheng Chen +6
Autonomous vehicles (AV) require that neural networks used for perception be robust to different viewpoints if they are to be deployed across many types of vehicles without the rep…
The Trust Fabric: Decentralized Interoperability and Economic Coordination for the Agentic Web
Sree Bhargavi Balija, Rekha Singal, Ramesh Raskar +4
The fragmentation of AI agent ecosystems has created urgent demands for interoperability, trust, and economic coordination that current protocols -- including MCP (Hou et al., 2025…
DeepABM: Scalable, efficient and differentiable agent-based simulations via graph neural networks
Ayush Chopra, Esma Gel, Jayakumar Subramanian +5
We introduce DeepABM, a framework for agent-based modeling that leverages geometric message passing of graph neural networks for simulating action and interactions over large agent…
Position: Collaborative Agentic AI Needs Interoperability Across Ecosystems
Rishi Sharma, Martijn de Vos, Pradyumna Chari +2
Collaborative agentic AI is projected to transform entire industries by enabling AI-powered agents to autonomously perceive, plan, and act within digital environments. Yet, current…
Sampling Without Time: Recovering Echoes of Light via Temporal Phase Retrieval
Ayush Bhandari, Aurelien Bourquard, Ramesh Raskar
This paper considers the problem of sampling and reconstruction of a continuous-time sparse signal without assuming the knowledge of the sampling instants or the sampling rate. Thi…
Private independence testing across two parties
Praneeth Vepakomma, Mohammad Mohammadi Amiri, Clément L. Canonne +2
We introduce -test, a privacy-preserving algorithm for testing statistical independence between data distributed across multiple parties. Our algorithm relies on privately esti…
Splintering with distributions: A stochastic decoy scheme for private computation
Praneeth Vepakomma, Julia Balla, Ramesh Raskar
Performing computations while maintaining privacy is an important problem in todays distributed machine learning solutions. Consider the following two set ups between a client and…
COVID-19 Outbreak Prediction and Analysis using Self Reported Symptoms
Rohan Sukumaran, Parth Patwa, T V Sethuraman +9
It is crucial for policymakers to understand the community prevalence of COVID-19 so combative resources can be effectively allocated and prioritized during the COVID-19 pandemic.…
On the limits of agency in agent-based models
Ayush Chopra, Shashank Kumar, Nurullah Giray-Kuru +2
Agent-based modeling (ABM) offers powerful insights into complex systems, but its practical utility has been limited by computational constraints and simplistic agent behaviors, es…
Addressing the Invisible: Street Address Generation for Developing Countries with Deep Learning
Ilke Demir, Ramesh Raskar
More than half of the world's roads lack adequate street addressing systems. Lack of addresses is even more visible in daily lives of people in developing countries. We would like…
Flash Photography for Data-Driven Hidden Scene Recovery
Matthew Tancik, Guy Satat, Ramesh Raskar
Vehicles, search and rescue personnel, and endoscopes use flash lights to locate, identify, and view objects in their surroundings. Here we show the first steps of how all these ta…
Designing Neural Network Architectures using Reinforcement Learning
Bowen Baker, Otkrist Gupta, Nikhil Naik +1
At present, designing convolutional neural network (CNN) architectures requires both human expertise and labor. New architectures are handcrafted by careful experimentation or modi…
Privacy in Deep Learning: A Survey
Fatemehsadat Mireshghallah, Mohammadkazem Taram, Praneeth Vepakomma +3
The ever-growing advances of deep learning in many areas including vision, recommendation systems, natural language processing, etc., have led to the adoption of Deep Neural Networ…
Challenges of Equitable Vaccine Distribution in the COVID-19 Pandemic
Joseph Bae, Darshan Gandhi, Jil Kothari +25
The COVID-19 pandemic has led to a need for widespread and rapid vaccine development. As several vaccines have recently been approved for human use or are in different stages of de…
PrivateMail: Supervised Manifold Learning of Deep Features With Differential Privacy for Image Retrieval
Praneeth Vepakomma, Julia Balla, Ramesh Raskar
Differential Privacy offers strong guarantees such as immutable privacy under post processing. Thus it is often looked to as a solution to learning on scattered and isolated data.…
Data Measurements for Decentralized Data Markets
Charles Lu, Mohammad Mohammadi Amiri, Ramesh Raskar
Decentralized data markets can provide more equitable forms of data acquisition for machine learning. However, to realize practical marketplaces, efficient techniques for seller se…
Conformal Prediction with Large Language Models for Multi-Choice Question Answering
Bhawesh Kumar, Charlie Lu, Gauri Gupta +4
As large language models continue to be widely developed, robust uncertainty quantification techniques will become crucial for their safe deployment in high-stakes scenarios. In th…
Split learning for health: Distributed deep learning without sharing raw patient data
Praneeth Vepakomma, Otkrist Gupta, Tristan Swedish +1
Can health entities collaboratively train deep learning models without sharing sensitive raw data? This paper proposes several configurations of a distributed deep learning method…
Pairwise Confusion for Fine-Grained Visual Classification
Abhimanyu Dubey, Otkrist Gupta, Pei Guo +3
Fine-Grained Visual Classification (FGVC) datasets contain small sample sizes, along with significant intra-class variation and inter-class similarity. While prior work has address…
SplitNN-driven Vertical Partitioning
Iker Ceballos, Vivek Sharma, Eduardo Mugica +4
In this work, we introduce SplitNN-driven Vertical Partitioning, a configuration of a distributed deep learning method called SplitNN to facilitate learning from vertically distrib…
On Unlimited Sampling and Reconstruction
Ayush Bhandari, Felix Krahmer, Ramesh Raskar
Shannon's sampling theorem is one of the cornerstone topics that is well understood and explored, both mathematically and algorithmically. That said, practical realization of this…
A High-Resolution, US-scale Digital Similar of Interacting Livestock, Wild Birds, and Human Ecosystems with Applications to Multi-host Epidemic Spread
Abhijin Adiga, Ayush Chopra, Mandy L. Wilson +8
One Health issues, such as the spread of highly pathogenic avian influenza~(HPAI), present significant challenges at the human-animal-environmental interface. Recent H5N1 outbreaks…
Task-Driven Implicit Representations for Automated Design of LiDAR Systems
Nikhil Behari, Aaron Young, Tzofi Klinghoffer +2
Imaging system design is a complex, time-consuming, and largely manual process; LiDAR design, ubiquitous in mobile devices, autonomous vehicles, and aerial imaging platforms, adds…
CoDream: Exchanging dreams instead of models for federated aggregation with heterogeneous models
Abhishek Singh, Gauri Gupta, Ritvik Kapila +5
Federated Learning (FL) enables collaborative optimization of machine learning models across decentralized data by aggregating model parameters. Our approach extends this concept b…
View-Dependent Displays and the Space of Light Fields
Roarke Horstmeyer, Se Baek Oh, Ramesh Raskar
In this paper we explore how light propagates from thin elements into a volume for viewing. In particular, devices that are typically connected with geometric optics, like parallax…
Super-Resolution in Phase Space
Ayush Bhandari, Yonina Eldar, Ramesh Raskar
This work considers the problem of super-resolution. The goal is to resolve a Dirac distribution from knowledge of its discrete, low-pass, Fourier measurements. Classically, such p…
Private Agent-Based Modeling
Ayush Chopra, Arnau Quera-Bofarull, Nurullah Giray-Kuru +2
The practical utility of agent-based models in decision-making relies on their capacity to accurately replicate populations while seamlessly integrating real-world data streams. Ye…
Sweep Distortion Removal from THz Images via Blind Demodulation
Alireza Aghasi, Barmak Heshmat, Albert Redo-Sanchez +2
Heavy sweep distortion induced by alignments and inter-reflections of layers of a sample is a major burden in recovering 2D and 3D information in time resolved spectral imaging. Th…
Physically Disentangled Representations
Tzofi Klinghoffer, Kushagra Tiwary, Arkadiusz Balata +2
State-of-the-art methods in generative representation learning yield semantic disentanglement, but typically do not consider physical scene parameters, such as geometry, albedo, li…
Decouple-and-Sample: Protecting sensitive information in task agnostic data release
Abhishek Singh, Ethan Garza, Ayush Chopra +3
We propose sanitizer, a framework for secure and task-agnostic data release. While releasing datasets continues to make a big impact in various applications of computer vision, its…
What if Eye...? Computationally Recreating Vision Evolution
Kushagra Tiwary, Aaron Young, Zaid Tasneem +6
Vision systems in nature show remarkable diversity, from simple light-sensitive patches to complex camera eyes with lenses. While natural selection has produced these eyes through…
Target Privacy Threat Modeling for COVID-19 Exposure Notification Systems
Ananya Gangavarapu, Ellie Daw, Abhishek Singh +4
The adoption of digital contact tracing (DCT) technology during the COVID-19pandemic has shown multiple benefits, including helping to slow the spread of infectious disease and to…
Federated Conformal Predictors for Distributed Uncertainty Quantification
Charles Lu, Yaodong Yu, Sai Praneeth Karimireddy +2
Conformal prediction is emerging as a popular paradigm for providing rigorous uncertainty quantification in machine learning since it can be easily applied as a post-processing ste…
Privacy-Preserving Split Learning with Vision Transformers using Patch-Wise Random and Noisy CutMix
Seungeun Oh, Sihun Baek, Jihong Park +5
In computer vision, the vision transformer (ViT) has increasingly superseded the convolutional neural network (CNN) for improved accuracy and robustness. However, ViT's large model…
DecentNeRFs: Decentralized Neural Radiance Fields from Crowdsourced Images
Zaid Tasneem, Akshat Dave, Abhishek Singh +4
Neural radiance fields (NeRFs) show potential for transforming images captured worldwide into immersive 3D visual experiences. However, most of this captured visual data remains si…
Can Self Reported Symptoms Predict Daily COVID-19 Cases?
Parth Patwa, Viswanatha Reddy, Rohan Sukumaran +6
The COVID-19 pandemic has impacted lives and economies across the globe, leading to many deaths. While vaccination is an important intervention, its roll-out is slow and unequal ac…
Progressive versus Random Projections for Compressive Capture of Images, Lightfields and Higher Dimensional Visual Signals
Rohit Pandharkar, Ashok Veeraraghavan, Ramesh Raskar
Computational photography involves sophisticated capture methods. A new trend is to capture projection of higher dimensional visual signals such as videos, multi-spectral data and…
Reconstruction of hidden 3D shapes using diffuse reflections
Otkrist Gupta, Andreas Velten, Thomas Willwacher +2
We analyze multi-bounce propagation of light in an unknown hidden volume and demonstrate that the reflected light contains sufficient information to recover the 3D structure of the…
NoPeek: Information leakage reduction to share activations in distributed deep learning
Praneeth Vepakomma, Abhishek Singh, Otkrist Gupta +1
For distributed machine learning with sensitive data, we demonstrate how minimizing distance correlation between raw data and intermediary representations reduces leakage of sensit…
PlatoNeRF: 3D Reconstruction in Plato's Cave via Single-View Two-Bounce Lidar
Tzofi Klinghoffer, Xiaoyu Xiang, Siddharth Somasundaram +4
3D reconstruction from a single-view is challenging because of the ambiguity from monocular cues and lack of information about occluded regions. Neural radiance fields (NeRF), whil…
Lensless Imaging with Compressive Ultrafast Sensing
Guy Satat, Matthew Tancik, Ramesh Raskar
Lensless imaging is an important and challenging problem. One notable solution to lensless imaging is a single pixel camera which benefits from ideas central to compressive samplin…
Detection and Mapping of Specular Surfaces Using Multibounce Lidar Returns
Connor Henley, Siddharth Somasundaram, Joseph Hollmann +1
We propose methods that use specular, multibounce lidar returns to detect and map specular surfaces that might be invisible to conventional lidar systems that rely on direct, singl…
Advances and Open Problems in Federated Learning
Peter Kairouz, H. Brendan McMahan, Brendan Avent +56
Federated learning (FL) is a machine learning setting where many clients (e.g. mobile devices or whole organizations) collaboratively train a model under the orchestration of a cen…
Comparing manual contact tracing and digital contact advice
Ramesh Raskar, Ranu Dhillon, Suraj Kapa +8
Manual contact tracing is a top-down solution that starts with contact tracers at the public health level, who identify the contacts of infected individuals, interview them to get…
Towards Learning Neural Representations from Shadows
Kushagra Tiwary, Tzofi Klinghoffer, Ramesh Raskar
We present a method that learns neural shadow fields which are neural scene representations that are only learnt from the shadows present in the scene. While traditional shape-from…
Enhancing Autonomous Navigation by Imaging Hidden Objects using Single-Photon LiDAR
Aaron Young, Nevindu M. Batagoda, Harry Zhang +4
Robust autonomous navigation in environments with limited visibility remains a critical challenge in robotics. We present a novel approach that leverages Non-Line-of-Sight (NLOS) s…
Differentially Private CutMix for Split Learning with Vision Transformer
Seungeun Oh, Jihong Park, Sihun Baek +5
Recently, vision transformer (ViT) has started to outpace the conventional CNN in computer vision tasks. Considering privacy-preserving distributed learning with ViT, federated lea…
Private measurement of nonlinear correlations between data hosted across multiple parties
Praneeth Vepakomma, Subha Nawer Pushpita, Ramesh Raskar
We introduce a differentially private method to measure nonlinear correlations between sensitive data hosted across two entities. We provide utility guarantees of our private estim…
PPContactTracing: A Privacy-Preserving Contact Tracing Protocol for COVID-19 Pandemic
Priyanka Singh, Abhishek Singh, Gabriel Cojocaru +2
Several contact tracing solutions have been proposed and implemented all around the globe to combat the spread of COVID-19 pandemic. But, most of these solutions endanger the priva…
Server-Side Local Gradient Averaging and Learning Rate Acceleration for Scalable Split Learning
Shraman Pal, Mansi Uniyal, Jihong Park +5
In recent years, there have been great advances in the field of decentralized learning with private data. Federated learning (FL) and split learning (SL) are two spearheads possess…
DISCO: Dynamic and Invariant Sensitive Channel Obfuscation for deep neural networks
Abhishek Singh, Ayush Chopra, Vivek Sharma +4
Recent deep learning models have shown remarkable performance in image classification. While these deep learning systems are getting closer to practical deployment, the common assu…
Role of Transients in Two-Bounce Non-Line-of-Sight Imaging
Siddharth Somasundaram, Akshat Dave, Connor Henley +2
The goal of non-line-of-sight (NLOS) imaging is to image objects occluded from the camera's field of view using multiply scattered light. Recent works have demonstrated the feasibi…
Shape from Mixed Polarization
Vage Taamazyan, Achuta Kadambi, Ramesh Raskar
Shape from Polarization (SfP) estimates surface normals using photos captured at different polarizer rotations. Fundamentally, the SfP model assumes that light is reflected either…
Data Facts: A Metadata Schema for Structured Data Exchange in the NANDini Multi-Agent Ecosystem
Jin Gao, Maria Gorskikh, Pradyumna Chari +5
NANDini (Networked Agents Natural Distillation of Interconnected Nodal Intelligence) envisions an automated ecosystem where intelligent agents independently create, process, and ex…
Bluetooth based Proximity, Multi-hop Analysis and Bi-directional Trust: Epidemics and More
Ramesh Raskar, Sai Sri Sathya
In this paper, we propose a trust layer on top of Bluetooth and similar wireless communication technologies that can form mesh networks. This layer as a protocol enables computing…
ORCa: Glossy Objects as Radiance Field Cameras
Kushagra Tiwary, Akshat Dave, Nikhil Behari +3
Reflections on glossy objects contain valuable and hidden information about the surrounding environment. By converting these objects into cameras, we can unlock exciting applicatio…
ExpertMatcher: Automating ML Model Selection for Users in Resource Constrained Countries
Vivek Sharma, Praneeth Vepakomma, Tristan Swedish +3
In this work we introduce ExpertMatcher, a method for automating deep learning model selection using autoencoders. Specifically, we are interested in performing inference on data s…
First 100 days of pandemic; an interplay of pharmaceutical, behavioral and digital interventions -- A study using agent based modeling
Gauri Gupta, Ritvik Kapila, Ayush Chopra +1
Pandemics, notably the recent COVID-19 outbreak, have impacted both public health and the global economy. A profound understanding of disease progression and efficient response str…
Fundamentals of Task-Agnostic Data Valuation
Mohammad Mohammadi Amiri, Frederic Berdoz, Ramesh Raskar
We study valuing the data of a data owner/seller for a data seeker/buyer. Data valuation is often carried out for a specific task assuming a particular utility metric, such as test…
Detailed comparison of communication efficiency of split learning and federated learning
Abhishek Singh, Praneeth Vepakomma, Otkrist Gupta +1
We compare communication efficiencies of two compelling distributed machine learning approaches of split learning and federated learning. We show useful settings under which each m…
Clinical Landscape of COVID-19 Testing: Difficult Choices
Darshan Gandhi, Sanskruti Landage, Joseph Bae +12
The coronavirus disease 2019 (COVID-19) pandemic has spread rapidly across the world, leading to enormous amounts of human death and economic loss. Until definitive preventive or c…