About

Deepak Vasisht is an Assistant Professor at the Siebel School of Computing and Data Science at the University of Illinois Urbana-Champaign. He holds a Ph.D. in Computer Science and Engineering from the Massachusetts Institute of Technology, earned in 2019, along with a Master’s degree in Computer Science from MIT obtained in 2015. His undergraduate degree is a B. Tech. in Computer Science and Engineering from the Indian Institute of Technology-Delhi, completed in 2013. His research areas include sensors, systems, and networking, with a focus on wireless communication, IoT, radar, satellite networks, and in-body communication. Vasisht has contributed to various fields such as radar SLAM, satellite network design, wireless localization, privacy in wireless systems, and IoT self-localization. His work involves developing innovative solutions for bandwidth-efficient clustering, Doppler-based odometry, spectrum-efficient satellite networks, and privacy-preserving wireless communication. He has authored numerous conference articles and has been recognized for his contributions to these domains.

Research topics

• Computer Science
• Real-time computing
• Telecommunications
• Computer network
• Artificial Intelligence
• Engineering
• Computer vision
• Aerospace engineering
• Geology
• Operating system
• Cartography
• Geography
• Remote sensing

Selected publications

• Pinpointing Transmitting LEO Satellites from a Single Passive Array

  Zenodo (CERN European Organization for Nuclear Research) · 2026-03-16

  datasetOpen accessSenior author

  This dataset contains passive RF captures of Starlink Ku-band downlink signals, collected to support research in passive LEO satellite localization. Signals were recorded at a center frequency of 11.325 GHz with a 2 MHz bandwidth using a three-receiver setup. Each observation consists of 15 minutes (900 seconds) of simultaneous IQ data across all three receivers, along with synchronized IMU/GNSS measurements and Starlink Two-Line Element (TLE) data corresponding to the time of capture. Raw IQ data can be processed using the scripts in starlocProcessRawSignal. Due to upload limitations on Zenodo, the full dataset (434.4 GiB, 81 satellites from 11 observations) is hosted on Box.

  PublisherDOI

• StarLoc: Pinpointing Transmitting LEO Satellites from a Single Passive Array

  arXiv (Cornell University) · 2026-04-22

  articleOpen accessSenior author

  This paper focuses on 3D localization of transmitting satellites in low Earth orbits (LEO). 3D localization of transmitters in low orbits is an important emerging problem for many applications such as spectrum management, orbit determination, and backup for GPS failures in orbit. We present StarLoc -- a system to geolocate transmitters in space using a combination of orbital modeling and a new interferometric 3D angle-of-arrival estimation technique. StarLoc's design relies on a unique insight -- the motion of satellites is governed by orbital dynamics and is therefore along a 2D manifold in a 3D space. This reduces the degrees of freedom in satellite motion and allows us to 3D-locate and track a satellite with just three antennas in a 2D plane. We evaluate the system using signal transmissions from 81 Starlink satellites. Our results show that StarLoc can estimate the 3D-angle of a satellite within 0.7 degrees and the orbital range within 5 km. Our dataset and implementation are available at: https://connectedsystemslab.github.io/starloc.

  PublisherOA PDF

• SILC: Lookahead Caching for Short-form Video Delivery Systems

  ArXiv.org · 2026-05-06

  articleOpen access

  Short video platforms like TikTok, Instagram Reels, and YouTube Shorts have gained immense popularity in the last few years and are responsible for a large and growing fraction of Internet traffic. We identify two unique opportunities for improving short video delivery using their existing interactions with content delivery networks (CDNs). First, short videos use a push-based recommendation system, where the user is presented a sequence of videos recommended by the algorithm rather than user explicitly picking content to watch (e.g., in YouTube). Such push-based short video systems offer a unique opportunity for system design by providing visibility into upcoming requests. Second, the popularity of these videos follows a highly skewed Pareto distribution, leading to geographical and temporal overlap amongst videos being served. We leverage these opportunities to build SILC - a lookahead-aware caching system, aimed at (i) reducing CDN cache miss rates, as well as (ii) reducing midgress bandwidth between the CDN and the origin server. Our evaluation of SILC uses traces that we collect from real users, through (i) an in-person user study, and (ii) a data donation program involving 100 TikTok users across the world. Using a combination of these traces, we simulate traffic from 10,000 simultaneous users. Our evaluation shows that, compared to 10 state-of-the-art heuristic and learning-based cache eviction policies, SILC reduces a CDN's midgress costs by 11.1% to 111%.

  PublisherOA PDF

• SILC: Lookahead Caching for Short-form Video Delivery Systems

  arXiv (Cornell University) · 2026-05-06

  preprintOpen access

  Short video platforms like TikTok, Instagram Reels, and YouTube Shorts have gained immense popularity in the last few years and are responsible for a large and growing fraction of Internet traffic. We identify two unique opportunities for improving short video delivery using their existing interactions with content delivery networks (CDNs). First, short videos use a push-based recommendation system, where the user is presented a sequence of videos recommended by the algorithm rather than user explicitly picking content to watch (e.g., in YouTube). Such push-based short video systems offer a unique opportunity for system design by providing visibility into upcoming requests. Second, the popularity of these videos follows a highly skewed Pareto distribution, leading to geographical and temporal overlap amongst videos being served. We leverage these opportunities to build SILC - a lookahead-aware caching system, aimed at (i) reducing CDN cache miss rates, as well as (ii) reducing midgress bandwidth between the CDN and the origin server. Our evaluation of SILC uses traces that we collect from real users, through (i) an in-person user study, and (ii) a data donation program involving 100 TikTok users across the world. Using a combination of these traces, we simulate traffic from 10,000 simultaneous users. Our evaluation shows that, compared to 10 state-of-the-art heuristic and learning-based cache eviction policies, SILC reduces a CDN's midgress costs by 11.1% to 111%.

  PublisherDOI

• Counting How the Seconds Count: Understanding TikTok Behavior via ML-driven Analysis of Video Content

  2026-04-13 · 2 citations

  articleOpen access

  Short video streaming systems such as TikTok, YouTube Shorts, Instagram Reels, etc., have reached billions of active users worldwide. At the core of such systems are (proprietary) recommendation algorithms which recommend a sequence of videos to each user, in a personalized way. We aim to understand the temporal evolution of recommendations made by such algorithms, as well as the interplay between the recommendations and user experience. While past work has studied recommendation algorithms using textual data (e.g., titles, hashtags, etc.) as well as user studies and interviews, we add a third modality of analysis—we perform automated analysis of the videos themselves. To perform such multimodal analysis, we develop a new HCI measurement approach that starts with our new tool called VCA (Video Content Analysis) that leverages recent advances in Vision Language Models (VLMs). We apply VCA on a trifecta of HCI methodologies—real user studies, interviews, and data donation. This allows us to understand temporal aspects of how well TikTok’s recommendation algorithm is perceived by users, is affected by user interactions, and aligns with user history; how users are sensitive to the order of videos recommended; and how the algorithm’s effectiveness itself may be predictable in the future. While it is not our goal to reverse-engineer TikTok’s recommendation algorithm, our new findings indicate behavioral aspects that the TikTok user community can benefit from.

  PublisherDOI

• StarLoc: Pinpointing Transmitting LEO Satellites from a Single Passive Array

  arXiv (Cornell University) · 2026-04-22

  preprintOpen accessSenior author

  This paper focuses on 3D localization of transmitting satellites in low Earth orbits (LEO). 3D localization of transmitters in low orbits is an important emerging problem for many applications such as spectrum management, orbit determination, and backup for GPS failures in orbit. We present StarLoc -- a system to geolocate transmitters in space using a combination of orbital modeling and a new interferometric 3D angle-of-arrival estimation technique. StarLoc's design relies on a unique insight -- the motion of satellites is governed by orbital dynamics and is therefore along a 2D manifold in a 3D space. This reduces the degrees of freedom in satellite motion and allows us to 3D-locate and track a satellite with just three antennas in a 2D plane. We evaluate the system using signal transmissions from 81 Starlink satellites. Our results show that StarLoc can estimate the 3D-angle of a satellite within 0.7 degrees and the orbital range within 5 km. Our dataset and implementation are available at: https://connectedsystemslab.github.io/starloc.

  PublisherDOI

• EcoCell: Energy Conservation Through Traffic Shaping in Cellular Radio Access Networks

  Open MIND · 2026-01-01

  articleOpen accessSenior author

  Cellular networks contribute significantly to global energy demands and carbon emissions due to the millions of base stations deployed worldwide. We characterize the energy consumption of production base stations by performing fine-grained power and network telemetry measurements using off-the-shelf base stations. Our measurements reveal unique insights about how variations in temporal-usage patterns affect base station energy consumption. Based on these insights, we design EcoCell, a software-only solution that introduces energy-efficient traffic patterns in network flows. EcoCell can be implemented either as a traffic scheduler in the radio access network or as an independent middlebox. We evaluate EcoCell with five popular networked applications on a production basestation. We demonstrate savings up to 32% in dynamic energy consumption of a base station, without drops in application-level quality of experience.

  PublisherOA PDFDOI

• Pinpointing Transmitting LEO Satellites from a Single Passive Array

  Zenodo (CERN European Organization for Nuclear Research) · 2026-03-16

  datasetOpen accessSenior author

  This dataset contains passive RF captures of Starlink Ku-band downlink signals, collected to support research in passive LEO satellite localization. Signals were recorded at a center frequency of 11.325 GHz with a 2 MHz bandwidth using a three-receiver setup. Each observation consists of 15 minutes (900 seconds) of simultaneous IQ data across all three receivers, along with synchronized IMU/GNSS measurements and Starlink Two-Line Element (TLE) data corresponding to the time of capture. Raw IQ data can be processed using the scripts in starlocProcessRawSignal. Due to upload limitations on Zenodo, the full dataset (434.4 GiB, 81 satellites from 11 observations) is hosted on Box.

  PublisherDOI

• Counting How the Seconds Count: Understanding Algorithm-User Interplay in TikTok via ML-driven Analysis of Video Content

  arXiv (Cornell University) · 2025-03-25

  preprintOpen access

  Short video streaming systems such as TikTok, YouTube Shorts, Instagram Reels, etc., have reached billions of active users worldwide. At the core of such systems are (proprietary) recommendation algorithms which recommend a sequence of videos to each user, in a personalized way. We aim to understand the temporal evolution of recommendations made by such algorithms, as well as the interplay between the recommendations and user experience. While past work has studied recommendation algorithms using textual data (e.g., titles, hashtags, etc.) as well as user studies and interviews, we add a third modality of analysis - we perform automated analysis of the videos themselves. To perform such multimodal analysis, we develop a new HCI measurement approach that starts with our new tool called VCA (Video Content Analysis) that leverages recent advances in Vision Language Models (VLMs). We apply VCA on a trifecta of HCI methodologies - real user studies, interviews, and data donation. This allows us to understand temporal aspects of how well TikTok's recommendation algorithm is perceived by users, is affected by user interactions, and aligns with user history; how users are sensitive to the order of videos recommended; and how the algorithm's effectiveness itself may be predictable in the future. While it is not our goal to reverse-engineer TikTok's recommendation algorithm, our new findings indicate behavioral aspects that the TikTok user community can benefit from.

  PublisherOA PDFDOI

• SkyLink: Scalable and Resilient Link Management in LEO Satellite Networks

  IEEE Transactions on Communications · 2025-11-21

  articleOpen access

  The rapid growth of space-based services has established Low Earth Orbit (LEO) satellite networks as a promising option for global broadband connectivity. Next-generation LEO networks leverage inter-satellite links (ISLs) to provide faster and more reliable communications compared to traditional bent-pipe architectures, even in remote regions. However, the high mobility of satellites, dynamic traffic patterns, and potential link failures pose significant challenges for efficient and resilient routing. To address these challenges, we model the LEO satellite network as a time-varying graph comprising a constellation of satellites and ground stations. Our objective is to minimize a weighted sum of average delay and packet drop rate. Each satellite independently decides how to distribute its incoming traffic to neighboring nodes in real time. Given the infeasibility of finding optimal solutions at scale, due to the exponential growth of routing options and uncertainties in link capacities, we propose SKYLINK, a novel fully distributed learning strategy for link management in LEO satellite networks. SKYLINK enables each satellite to adapt to the time-varying network conditions, ensuring real-time responsiveness, scalability to millions of users, and resilience to network failures, while maintaining low communication overhead and computational complexity. To support the evaluation of SKYLINK at global scale, we develop a new simulator for large-scale LEO satellite networks. For 25.4 million users, SKYLINK reduces the weighted sum of average delay and drop rate by 29% compared to the bent-pipe approach, and by 92% compared to Dijkstra. It lowers drop rates by 95% relative to k-shortest paths, 99% relative to Dijkstra, and 74% compared to the bent-pipe baseline, while achieving up to 46% higher throughput. At the same time, SKYLINK maintains constant computational complexity with respect to constellation size.

  PublisherOA PDFDOI

Recent grants

• CAREER: Networking and Compute for Next Generation Low-Earth Orbit Satellites

  NSF · $648k · 2023–2028

• RINGS: Provably Robust Machine Learning for Next Generation Cellular Networks

  NSF · $794k · 2022–2025

Frequent coauthors

• Dina Katabi

  Massachusetts Institute of Technology

  15 shared

• Ranveer Chandra

  11 shared

• Swarun Kumar

  Carnegie Mellon University

  9 shared

• Zerina Kapetanovic

  Stanford University

  7 shared

• Emerson Sie

  University of Illinois Urbana-Champaign

  7 shared

• Jayanth Shenoy

  University of Illinois Urbana-Champaign

  7 shared

• Yu Tao

  King University

  6 shared

• Zikun Liu

  University of Illinois Urbana-Champaign

  6 shared

Education

• Ph.D., Computer Science

  University of Illinois at Urbana-Champaign

  2000

• M.S., Computer Science

  University of Illinois at Urbana-Champaign

  1996

• B.S., Computer Science

  University of Illinois at Urbana-Champaign

  1994