INTEGRATED SYSTEMS
PROJECTS
PEOPLE
PUBLICATIONS
PATENTS
Integrated Systems
Large Language Models (LLMs) typically exhibit a performance profile where reliability degrades as task complexity increases. We address the challenge of generating high-quality natural language executable plans for complex tasks by introducing GRASP, a strategy-aware, multi-stage planning framework.
Workflows that use generative AI are error-prone and hard to audit when model calls, validation, retries, and outputs are scattered across prompts, scripts, and configuration. AI native workflows need these elements connected in one place so the pipeline can be audited and reviewed end to end. This paper
Embodied task planning requires reasoning under uncertainty about world states that are partially observed and incrementally revealed through interaction. However, mostvision–language model (VLM) planners operate in a reactive sense–plan–act loop without maintaining a persistent representation
Giuseppe Coviello of NEC Laboratories America presents “Völ: A Domain-Specific Language and Runtime for AI-Native Workflows” at HiPES 2026, held alongside Euro-Par in Pisa, Italy on August 25th. Völ lets developers describe AI workflows declaratively, leaving execution to the runtime.
Timely and accurate assessment of property damage is critical following natural disasters. Traditional on-site inspections are labor-intensive, costly, and often pose safety risks. Advances in satellite imagery and vision-language models (VLMs) enable scalable remote damage assessment; however, integrating
Satellite imagery is vast, high-resolution, and rich with information, but finding specific objects within it using natural language has remained a stubborn challenge. Open-SAT, developed by researchers at NEC Laboratories America and North South University, tackles this problem without retraining any
In satellite applications, user queries often take the form of open-ended natural language, extending beyond a fixed set of predefined categories. This open-vocabulary nature poses significant challenges for retrieving relevant image tiles, as the retrieval system must generalize to a wide range of unseen
Humans solve problems by executing targeted plans, yet large language models (LLMs) remain unreliable for structured workflow execution. We propose RunAgent, a multiagent plan execution platform that interprets natural-language plans while enforcing stepwise execution through constraints and rubrics.
Deploying microservices across the computing continuum (edgecloud) requires placement decisions that adapt to workload variation and heterogeneous infrastructure, yet existing solutions often rely on static policies or opaque heuristics. We present Bellona a system for reliable and auditable Large
Radiology Report Generation (RRG) is a critical step toward automating healthcare workflows, facilitating accurate patient assessments, and reducing the workload of medical professionals. Despite recent progress in Large Medical Vision-Language Models (Med-VLMs), generating radiology reports that are
Large language models (LLMs) are becoming the centerpiece in the design and deployment of Agentic artificial intelligence (AI) systems. AI agents typically have (a) reasoning ability to analyze and think through the given task, (b) context/memory to remember things in the short-term and long-term, and
Identifying subject-matter experts within organizations remains a challenging task due to the scale, heterogeneity, and unstructured nature of enterprise knowledge assets. We present TalentScout, an AI-driven expert identification system that constructs a unified, skill-centric knowledge graph by ingesting
Creating effective slide presentations requires adapting both content and structure to match the communication context e.g. whether the presentation is for summarizing to executives, or reporting progress to research supervisors. In research and enterprise environments, this need for context-sensitive
Murugan Sankaradas (presenting virtually) will present “TalentScout: Multimodal AI-Driven Expert Finding in Organizations” at the IEEE International Conference on Pervasive Intelligence and Computing (PICom2025) on Tuesday, October 21 (10:30am–12pm JST) | Monday, October 20 (9:30–11pm ET) in
Kunal Rao (presenting virtually) will present “SlideCraft: Context-Aware Slides Generation Agent” at the IEEE International Conference on Pervasive Intelligence and Computing hashtag#PICom2025 on Tuesday, Oct 21 (10:30am–12pm JST) | Monday, Oct 20 (9:30–11pm ET) in Hokkaido, Japan. SlideCraft
Agentic AI systems rely on Large Language Models (LLMs) to execute complex tasks by invoking external functions. The efficiency of these systems depends on how well function execution is managed, especially under heterogeneous and high-variance workloads, where function execution times can range from
Roadside LiDAR (Light Detection and Ranging) sensors promise safer and faster traffic management and vehicular operations. However, occlusion and small view angles are significant challenges to widespread use of roadside LiDARs. We consider fusing data from multiple LiDARs at a traffic intersection to
Enterprises are increasingly adopting Generative AI applications to extract insights from large volumes of multimodal documents in domains such as finance, law, healthcare, and industry. These documents contain structured and unstructured data (images, charts, handwritten texts, etc.) requiring robust
In this paper, we propose a novel agentic AI system called XPF, which enables users to create “agents” using just natural language, where each agent is capable of executing complex, real-world business workflows in an accurate and reliable manner. XPF provides an interface to develop and iterate over
Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external knowledge to generate a response within a context with improved accuracy and reduced hallucinations. However, multi-modal RAG systems face unique challenges: (i) the retrieval process may select irrelevant
Scene understanding systems analyze visual contexts by detecting objects, their attributes, and the interactions among them to provide a holistic interpretation. Understanding a scene requires analyzing multiple salient regions within a single video frame. Recently, Vision-Language Models (VLMs) have
Latency-critical applications demand quick responses. Ideally, detailed insights are preferable for the best decision making and response actions. However, in situations when detailed insights cannot be provided quickly, even basic information goes a long way in tackling the situation effectively. For
The advancement of Generative Artificial Intelligence (AI), particularly Large Language Models (LLMs), is reshaping the software industry by automating code generation. Many LLM-driven distributed processing systems rely on serial code generation constrained by predefined libraries, limiting flexibility
LiDAR technology has emerged as a pivotal tool in Intelligent Transportation Systems (ITS), providing unique capabilities that have significantly transformed roadside traffic applications. However, this transformation comes with a distinct challenge: the immense volume of data generated by LiDAR sensors.
In Video Analytics Pipelines (VAP), Analytics Units (AUs) such as object detection and face recognition operating on remote servers rely heavily on surveillance cameras to capture high-quality video streams to achieve high accuracy. Modern network cameras offer an array of parameters that directly influence
With the advancement of 5G, edge-assisted video analytics has become increasingly popular, driven by the technologys ability to support low-latency, high-bandwidth applications. However, in scenarios where multiple clients competing for network resources, network contention poses a significant challenge.
Retrieval-augmented generation (RAG) improves large language models (LLMs) by using external knowledge to guide response generation, reducing hallucinations. However, RAG, particularly multi-modal RAG, can introduce new hallucination sources: (i) the retrieval process may select irrelevant pieces (e.g.,
Edge computing has emerged as a transformative technology that reduces application latency, improves cost efficiency, enhances security, and enables large-scale deployment of applications across various domains. In environmental monitoring, systems such as MegaSense[49], use low-cost sensors to gather
Generative artificial intelligence (GenAI), specifically, Large Language Models (LLMs), have shown tremendous potential in automating several tasks and improving human productivity. Recent works have shown them to be quite useful in writing and summarizing text (articles, blogs, poems, stories, songs,
Retrieval-augmented generation (RAG) systems combine the strengths of language generation and information retrieval to power many real-world applications like chatbots. Use of RAG for understanding of videos is appealing but there are two critical limitations. One-time, upfront conversion of all content
Traffic cameras are essential in urban areas, playing a crucial role in intelligent transportation systems. Multiple cameras at intersections enhance law enforcement capabilities, traffic management, and pedestrian safety. However, efficiently managing and analyzing multi-camera feeds poses challenges
Costs of LLM API usage rise rapidly when proprietary enterprise data is used as context for user queries to generate more accurate responses from LLMs. To reduce costs, we propose LeanContext, which generates query-aware, compact and AI model-friendly summaries of relevant enterprise data context. This
Retrieval-augmented generation (RAG) is used in natural language processing (NLP) to provide query-relevant information in enterprise documents to large language models (LLMs). Such enterprise context enables the LLMs to generate more informed and accurate responses. When enterprise data is primarily
Standardized lossy video coding is at the core of almost all real-world video processing pipelines. Rate control is used to enable standard codecs to adapt to different network bandwidth conditions or storage constraints. However standard video codecs (e.g. H.264) and their rate control modules aim to
Ensuring high-quality video content for wireless users has become increasingly vital. Nevertheless, maintaining a consistent level of video quality faces challenges due to the fluctuating encoded bitrate, primarily caused by dynamic video content, especially in live streaming scenarios. Video compression
AI/ML techniques have been used to solve systems problems, but their applicability to customize solutions on-the-fly has been limited. Traditionally, any customization required manually changing the AI/ML model or modifying the code, configuration parameters, application settings, etc. This incurs too
Extracting real-time insights from multi-modal data streams from various domains such as healthcare, intelligent transportation, and satellite remote sensing remains a challenge. High computational demands and limited knowledge scope restrict the applicability of Multi-Modal Large Language Models (MM-LLMs)
Question-answering (QA) is a significant application of Large Language Models (LLMs), shaping chatbot capabilities across healthcare, education, and customer service. However, widespread LLM integration presents a challenge for small businesses due to the high expenses of LLM API usage. Costs rise rapidly
Providing wireless users with high-quality video content has become increasingly important. However, ensuring consistent video quality poses challenges due to variable encodedbitrate caused by dynamic video content and fluctuating channel bitrate caused by wireless fading effects. Suboptimal selection
For microservices-based real-time stream processing applications, computing at the edge delivers fast responses for low workloads, but as workload increases, the response time starts to slow down due to limited compute capacity. Abundant compute capacity in the cloud delivers fast responses even for
Retrieval augmented generation (RAG) systems combine the strengths of language generation and information retrieval to power many real-world applications like chatbots. Use of RAG for combined understanding of multimodal data such as text, images and videos is appealing but two critical limitations exist:
One of the key metrics of interest for stream processing applications is latency, which indicates the total time it takes for the application to process and generate insights from streaming input data. For mission-critical video analytics applications like surveillance and monitoring, it is of paramount
JPEG remains one of the most widespread lossy image coding methods. However, the non-differentiable nature of JPEG restricts the application in deep learning pipelines. Several differentiable approximations of JPEG have recently been proposed to address this issue. This paper conducts a comprehensive
Modern video analytics applications comprise multiple microservices chained together as pipelines and executed on container orchestration platforms like Kubernetes. Kubernetes automatically handles the scaling of these microservices for efficient application execution. There are two popular choices for
Deep learning based joint source-channel coding (JSCC) has demonstrated significant advancements in data reconstruction compared to separate source-channel coding (SSCC). This superiority arises from the suboptimality of SSCC when dealing with finite block-length data. Moreover, SSCC falls short in reconstructing
Deep Video Codec Control Lossy video compression is commonly used when transmitting and storing video data. Unified video codecs (e.g., H.264 or H.265) remain the emph(Unknown sysvar: (de facto)) standard, despite the availability of advanced (neural) compression approaches. Transmitting videos in the
In 2008, parallel computing posed significant challenges due to the complexities of parallel programming and the bottlenecks associated with efficient parallel execution. Inspired by the remarkable scalability achieved by networking and storage systems in handling extensive packet traffic and persistent
We present Application in a Box (AnB) product concept aimed at simplifying the deployment and operation of remote 5G applications. AnB comes pre-configured with all necessary hardware and software components, including sensors like cameras, hardware and software components for a local 5G wireless network,
IoT sensors, especially video cameras, are ubiquitously deployed around the world to perform a variety of computer vision tasks in several verticals including retail, health- care, safety and security, transportation, manufacturing, etc. To amortize their high deployment effort and cost, it is desirable
Edge Intelligence has received attention in the recent times for its potential towards improving responsiveness, reducing the cost of data transmission, enhancing security and privacy, and enabling autonomous decisions by edge devices. However, edge devices lack the power and compute resources necessary
Access to high-quality data is an important barrier in the digital analysis of urban settings, including applications within computer vision and urban design. Diverse forms of data collected from sensors in areas of high activity in the urban environment, particularly at street intersections, are valuable
Modern applications are designed as an interacting set of microservices, and these applications are typically deployed on container orchestration platforms like Kubernetes. Several attractive features in Kubernetes make it a popular choice for deploying applications, and automatic scaling is one such
Devices with limited computing resources use smaller AI models to achieve low-latency inferencing. However, model accuracy is typically much lower than the accuracy of a bigger model that is trained and deployed in places where the computing resources are relatively abundant. We describe DyCo, a novel
Cameras are increasingly being deployed in cities, enterprises and roads world-wide to enable many applications in public safety, intelligent transportation, retail, healthcare and manufacturing. Often, after initial deployment of the cameras, the environmental conditions and the scenes around these
Serverless edge computing aims to deploy and manage applications so that developers are unaware of challenges associated with dynamic management, sharing, and maintenance of the edge infrastructure. However, this is a non-trivial task because the resource usage by various edge applications varies based
In Video Analytics Pipelines (VAP), Analytics Units (AUs) such as object detection and face recognition running on remote servers critically rely on surveillance cameras to capture high-quality video streams in order to achieve high accuracy. Modern IP cameras come with a large number of camera parameters
It is a common practice to think of a video as a sequence of images (frames), and re-use deep neural network models that are trained only on images for similar analytics tasks on videos. In this paper, we show that this “leap of faith” that deep learning models that work well on images will also
Roadside LiDAR (Light Detection and Ranging) sensors are recently being explored for intelligent transportation systems aiming at safer and faster traffic management and vehicular operations. A key challenge in such systems is to efficiently transfer massive point-cloud data from the roadside LiDAR devices
5G-LAN is an enterprise local area network (LAN) that leverages 5G technology for wireless connectivity instead of WiFi. 5G technology is unique: it uses network slicing to distinguish customers in the same traffic class using new QoS technologies in the RF domain. This unique ability is not supported
A big challenge in changing a monolithic application into a performant microservices-based application is the design of efficient mechanisms for microservices to communicate with each other. Prior proposals range from custom point-to-point communication among microservices using protocols like gRPC to
Meta learning algorithms for few-shot video recognition use complex, episodic training but they often fail to learn effective feature representations. In contrast, we propose a new and simpler few-shot video recognition method that does not use meta-learning, but its performance compares well with the
5G services and applications explicitly reserve compute and network resources in today’s complex and dynamic infrastructure of multi-tiered computing and cellular networking to ensure application-specific service quality metrics, and the infrastructure providers charge the 5G services for the resources
Design of multitasking deep learning models has mostly focused on improving the accuracy of the constituent tasks, but the challenges of efficiently deploying such models in a device-edge collaborative setup (that is common in 5G deployments) has not been investigated. Towards this end, in this paper,
With the growth of 5G, Internet of Things (IoT), edge computing and cloud computing technologies, the infrastructure (compute and network) available to emerging applications (AR/VR, autonomous driving, industry 4.0, etc.) has become quite complex. There are multiple tiers of computing (IoT devices, near
A key barrier to building performant, remotely managed and self-optimizing multi-sensor, distributed stream processing edge applications is high programming complexity. We recently proposed DataX [1], a novel platform that improves programmer productivity by enabling easy exchange, transformations, and
Millions of cameras at edge are being deployed to power a variety of different deep learning applications. However, the frames captured by these cameras are not always pristine – they can be distorted due to lighting issues, sensor noise, compression etc. Such distortions not only deteriorate visual
Edge computing and 5G have made it possible to perform analytics closer to the source of data and achieve super-low latency response times, which isn’t possible with centralized cloud deployment. In this paper, we present a novel fever screening system, which uses edge machine learning techniques and
Microservices-based video analytics pipelines routinely use multiple deep convolutional neural networks. We observe that the best allocation of resources to deep learning engines (or microservices) in a pipeline, and the best configuration of parameters for each engine vary over time, often at a timescale
Applications can tailor a network slice by specifying a variety of QoS attributes related to application-specific performance, function or operation. However, some QoS attributes like guaranteed bandwidth required by the application do vary over time. For example, network bandwidth needs of video streams
Video analytics systems critically rely on video cameras, which capture high quality video frames, to achieve high analytics accuracy. Although modern video cameras often expose tens of configurable parameter settings that can be set by end users, deployment of surveillance cameras today often uses a
We investigate ways to leverage uncertainty in face images to improve the quality of the face clusters. We observe that popular clustering algorithms do not produce better quality clusters when clustering probabilistic face representations that implicitly model uncertainty – these algorithms predict
Applications that use edge computing and 5G to improve response times consume both compute and network resources. However, 5G networks manage only network resources without considering the application’s compute requirements, and container orchestration frameworks manage only compute resources without
The exponential growth in smart sensors and rapid progress in 5G networks is creating a world awash with data streams. However, a key barrier to building performant multi-sensor, distributed stream processing applications is high programming complexity. We propose DataX, a novel platform that improves
Identification of people with elevated body temperature can reduce or dramatically slow down the spread of infectious diseases like COVID-19. We present a novel fever-screening system, F 3 S, that uses edge machine learning techniques to accurately measure core body temperatures of multiple individuals
Centralized cloud computing with 100+ milliseconds network latencies cannot meet the tens of milliseconds to sub-millisecond response times required for emerging 5G applications like autonomous driving, smart manufacturing, tactile internet, and augmented or virtual reality. We describe a new, dynamic