About

Fujitsu Professor in Electrical Engineering and Computer Science at MIT, Hari Balakrishnan specializes in security and cryptography, systems and networking. His research areas include designing systems that sense, process, and transmit energy and information, leveraging computational, theoretical, and experimental tools to develop groundbreaking sensors, energy transducers, and physical substrates for computation. He has made significant contributions to the fields of electrical engineering and computer science, focusing on addressing shared challenges facing humanity through innovative system development. Hari Balakrishnan has been recognized for his work with the Marconi Prize, the top honor within the field of communications technology, awarded on February 22, 2023.

Research topics

• Computer Science
• Artificial Intelligence
• Computer Security
• Real-time computing
• Information Retrieval
• Operating system
• Computer network
• Computer vision
• Materials science
• Theoretical computer science
• Engineering
• Embedded system
• Mathematics
• World Wide Web
• Distributed computing

Selected publications

• IteRate: Autonomous AI Synthesis of In-Kernel eBPF Wi-Fi Rate Control Algorithms

  ArXiv.org · 2026-05-04

  articleOpen accessSenior author

  Wi-Fi rate adaptation remains a persistent challenge in wireless networking. Deployed algorithms like Minstrel-HT have remained largely stagnant for over a decade, relying on hand-tuned heuristics that fail to generalize to the complexity of modern wireless environments. We present \name, an autonomous research system that closes the loop on rate control development. IteRate uses a multi-agent AI architecture to conduct the full scientific cycle: formulating hypotheses, writing eBPF programs that run inside the Linux kernel, deploying them over-the-air to Wi-Fi devices, collecting fine-grained telemetry for analysis, and iterating based on experimental evidence, all without human intervention. IteRate makes three contributions. (1) a novel kernel module that exposes per-frame hardware telemetry including modulation and coding schemes (MCS) and retry counts to eBPF programs, (2) a structured agentic AI architecture employing specialized agents for algorithm design, experiment execution, and data analysis, coordinated via a hypothesis-driven research protocol with persistent knowledge, and (3) a closed-loop pipeline that automates the cross-compilation, deployment, and evaluation of in-kernel logic onto embedded Wi-Fi targets. On a 58-node testbed running five workloads. relative to the well-known Minstrel algorithm, IteRate achieves 21% faster web-page loads, 7% higher video quality of experience (QoE), and 21% higher peak throughput. Our work demonstrates that AI agents, when equipped with appropriate kernel-level hooks and a disciplined scientific workflow, can effectively automate the research required to design Wi-Fi rate controllers.

  PublisherOA PDF

• Optimizing Unmanned Aerial Vehicle Path finding in Complex Urban Airspaces: A Hybrid Genetic Algorithm with Bidirectional and Greedy Initialization

  Aerotecnica Missili & Spazio · 2026-04-09

  article1st author
  PublisherDOI

• IteRate: Autonomous AI Synthesis of In-Kernel eBPF Wi-Fi Rate Control Algorithms

  arXiv (Cornell University) · 2026-05-04

  preprintOpen accessSenior author

  Wi-Fi rate adaptation remains a persistent challenge in wireless networking. Deployed algorithms like Minstrel-HT have remained largely stagnant for over a decade, relying on hand-tuned heuristics that fail to generalize to the complexity of modern wireless environments. We present \name, an autonomous research system that closes the loop on rate control development. IteRate uses a multi-agent AI architecture to conduct the full scientific cycle: formulating hypotheses, writing eBPF programs that run inside the Linux kernel, deploying them over-the-air to Wi-Fi devices, collecting fine-grained telemetry for analysis, and iterating based on experimental evidence, all without human intervention. IteRate makes three contributions. (1) a novel kernel module that exposes per-frame hardware telemetry including modulation and coding schemes (MCS) and retry counts to eBPF programs, (2) a structured agentic AI architecture employing specialized agents for algorithm design, experiment execution, and data analysis, coordinated via a hypothesis-driven research protocol with persistent knowledge, and (3) a closed-loop pipeline that automates the cross-compilation, deployment, and evaluation of in-kernel logic onto embedded Wi-Fi targets. On a 58-node testbed running five workloads. relative to the well-known Minstrel algorithm, IteRate achieves 21% faster web-page loads, 7% higher video quality of experience (QoE), and 21% higher peak throughput. Our work demonstrates that AI agents, when equipped with appropriate kernel-level hooks and a disciplined scientific workflow, can effectively automate the research required to design Wi-Fi rate controllers.

  PublisherDOI

• Glia: A Human-Inspired AI for Automated Systems Design and Optimization

  2026-05-22

  articleOpen accessSenior author

  Can AI autonomously design mechanisms for computer systems on par with the creativity and reasoning of human experts? We present Glia, an AI architecture for networked systems design that uses large language models (LLMs) in a human-inspired multi-agent workflow. Each agent specializes in reasoning, experimentation, and analysis, collaborating through an evaluation framework that grounds abstract reasoning in empirical feedback. Unlike prior ML-for-systems methods that optimize black-box policies, Glia generates interpretable designs and exposes its reasoning. When applied to a distributed GPU cluster for LLM inference, it produces new algorithms for request routing, scheduling, and auto-scaling that perform at human-expert levels in significantly less time, while yielding novel insights into workload behavior. Our results suggest that by combining reasoning LLMs with structured experimentation, an AI can produce creative and understandable designs for complex systems problems.

  PublisherDOI

• Dossier: Deep Research via Ledger-Driven Branching Search and Query Encoding Learning

  2026-05-22

  articleOpen accessSenior author

  Deep research requires synthesizing information across fragmented sources. Existing ReAct-like agents for such multi-hop retrieval typically rely on long linear search trajectories, where early retrieval failures compound over time. We introduce Dossier, a deep research agent that replaces linear paths with locally parallel, branching search managed by a persistent Research Ledger. The Ledger explicitly tracks claims, contradictions, and information gaps, continuously updating as new evidence is synthesized. To improve the quality of each retrieval step, we introduce Evidence-Aligned Query Learning (EAQL), a training mechanism that fine-tunes query encoders to condition on the Research Ledger. This ensures that generated queries are contextually grounded in the agent’s evolving state rather than isolated prompts. Our evaluation demonstrates that Dossier’s branching architecture improves end-to-end accuracy on BrowseComp-Plus by 23 percentage points and HoVer by 29 percentage points across multiple LLM models.

  PublisherDOI

• Ideas and Requirements for the Global Cosmic-Ray Observatory (GCOS)

  ArXiv.org · 2025-02-08

  preprintOpen access

  After a successful kick-off meeting in 2021. two workshops in 2022 and 2023 on the future Global Cosmic-Ray Observatory (GCOS) focused mainly on a straw man design of the detector and science possibilities for astro- and particle physics. About 100 participants gathered for in-person and hybrid panel discussions. In this report, we summarize these discussions, present a preliminary straw-man design for GCOS and collect short write-ups of the flash talks given during the focus sessions.

  PublisherOA PDFDOI

• Heuristic Evaluation in A-Star Algorithm for Enhanced Urban Uav Path Optimization

  SSRN Electronic Journal · 2025-01-01

  preprintOpen access1st authorCorresponding
  PublisherDOI

• Scalable Routing in a City-Scale Wi-Fi Network for Disaster Recovery

  ArXiv.org · 2025-04-08

  articleOpen accessSenior author

  In this paper, we present a new city-scale decentralized mesh network system suited for disaster recovery and emergencies. When wide-area connectivity is unavailable or significantly degraded, our system, MapMesh, enables static access points and mobile devices equipped with Wi-Fi in a city to route packets via each other for intra-city connectivity and to/from any nodes that might have Internet access, e.g., via satellite. The chief contribution of our work is a new routing protocol that scales to millions of nodes, a significant improvement over prior work on wireless mesh and mobile ad hoc networks. Our approach uses detailed information about buildings from widely available maps--data that was unavailable at scale over a decade ago, but is widely available now--to compute paths in a scalable way.

  PublisherOA PDFDOI

• Savaal: Scalable Concept-Driven Question Generation to Enhance Human Learning

  ArXiv.org · 2025-02-18 · 1 citations

  preprintOpen accessSenior author

  Assessing and enhancing human learning through question-answering is vital, yet automating this process remains challenging. While large language models (LLMs) excel at summarization and query responses, their ability to generate meaningful questions for learners is underexplored. We propose Savaal, a scalable question-generation system with three objectives: (i) scalability, enabling question generation from hundreds of pages of text (ii) depth of understanding, producing questions beyond factual recall to test conceptual reasoning, and (iii) domain-independence, automatically generating questions across diverse knowledge areas. Instead of providing an LLM with large documents as context, Savaal improves results with a three-stage processing pipeline. Our evaluation with 76 human experts on 71 papers and PhD dissertations shows that Savaal generates questions that better test depth of understanding by 6.5X for dissertations and 1.5X for papers compared to a direct-prompting LLM baseline. Notably, as document length increases, Savaal's advantages in higher question quality and lower cost become more pronounced.

  PublisherOA PDFDOI

• DriveTrack: A Benchmark for Long-Range Point Tracking in Real-World Videos

  2024-06-16 · 6 citations

  articleSenior author

  This paper presents DriveTrack, a new benchmark and data generation framework for long-range keypoint tracking in real-world videos. DriveTrack is motivated by the observation that the accuracy of state-of-the-art trackers depends strongly on visual attributes around the selected keypoints, such as texture and lighting. The problem is that these artifacts are especially pronounced in real-world videos, but these trackers are unable to train on such scenes due to a dearth of annotations. DriveTrack bridges this gap by building a framework to auto- matically annotate point tracks on autonomous driving datasets. We release a dataset consisting of 1 billion point tracks across 24 hours of video, which is seven orders of magnitude greater than prior real-world benchmarks and on par with the scale of synthetic benchmarks. DriveTrack unlocks new use cases for point tracking in real-world videos. First, we show that fine- tuning keypoint trackers on DriveTrack improves accuracy on real-world scenes by up to 7%. Second, we analyze the sensitiv- ity of trackers to visual artifacts in real scenes and motivate the idea of running assistive keypoint selectors alongside trackers.

  PublisherDOI

Recent grants

• Collaborative Research: CT-T: Towards a More Accountable Internet

  NSF · $300k · 2007–2011

• FIA: Collaborative Research: Architecting for Innovation

  NSF · $200k · 2010–2013

• CPS: Medium: Vehicular Cyber-Physical Systems

  NSF · $1.5M · 2009–2014

• NeTS: Medium: Collaborative Research: An App-Centric Transport Architecture for the Internet

  NSF · $800k · 2014–2020

• NeTS: Medium: Collaborative Research: Language and Hardware Primitives for Programming the Data Plane in High-Speed Networks

  NSF · $898k · 2016–2022

Frequent coauthors

• Samuel Madden

  47 shared

• Scott Shenker

  University of California, Berkeley

  34 shared

• Nick Feamster

  University of Chicago

  32 shared

• Mohammad Alizadeh

  Amirkabir University of Technology

  25 shared

• David G. Andersen

  Carnegie Mellon University

  21 shared

• Srinivasan Seshan

  Universidad del Noreste

  20 shared

• Mohammad Reza Alizadeh

  20 shared

• Randy H. Katz

  19 shared

Education

• Ph.D., Computer Science

  Massachusetts Institute of Technology

  1989

• M.S., Electrical Engineering and Computer Science

  Massachusetts Institute of Technology

  1985

• B.S., Electrical Engineering

  Indian Institute of Technology, Madras

  1981

Awards & honors

• Marconi Prize