Our Integrated Systems department innovates, designs, and prototypes high-performance intelligent distributed systems, applications, and services on complex, large-scale communication networks like 5G and beyond. We develop next-generation wireless technologies for sensing the world, localizing critical assets, and improving the capacity, coverage, and scalability of communication networks like 5G and beyond.
New application needs have always sparked human innovation. A decade ago, cloud computing enabled high-value enterprise services with a global reach and scale but with several minutes or seconds of delay. Large-scale services like enterprise resource planning (ERP) were a corner-case scenario, often designed as one-off systems. Today, applications like social networks, automated trading, and video streaming have made large-scale services the norm rather than the exception. In the future, advances in 5G networks and an explosion in smart devices, microservices, databases, networking, and computing tiers will make services so complex that humans cannot tune or manage them.
The sheer scale, dynamic nature, and concurrency in services on 5G slices will require them to be intelligent and autonomic. They will need to continuously self-assess, learn, and automatically adjust for resource needs, data quality, and service reliability. The need for increased efficiency and reduced latency between measurement and action drives our design of real-time distributed systems for feature extraction, computation, and machine learning on multimodal streaming data. We are conducting extensive research on creating end-to-end solutions using multimodal sensing technologies in the retail, public safety, and transportation domains.
Our 5G cellular network research encompasses the development of technologies on the Radio Access Network (RAN), the mobile edge, and the 5G LAN. Within the RAN, we are developing technologies that optimize massive MIMO/MU-MIMO deployments and millimeter-wave access (e.g., transmission at 28 GHz to nomadic/mobile users). At the mobile edge (MEC), we focus on virtualization, scalability, and cloud deployment of appropriate services. Our 5G LAN research extends the benefits of 5G slicing technology to enterprise LANs to position the enterprise as the new MEC.
Read our news and publications from our world-class team of researchers from our Integrated Systems department.
Our exciting internship opportunities for Summer 2027 are now available. We are looking for students pursuing advanced degrees in Computer Science and Electrical Engineering. Internships are typically 3 months long in duration. The benefits of working for us include the opportunity to quickly become part of a project team applying cutting-edge technology to industry-leading concepts.
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. GRASP decouples the planning pipeline across specialized, context-isolated modules: it pre-compiles global macro-guidelines (GenPlan), explores alternative localized strategies within isolated context windows (RevPlan), and independently evaluates trajectories using a multi-criteria discriminator (VerPlan). Empirical evaluations show that GRASP consistently establishes a new state-of-the-art frontier across diverse datasets, yielding substantial accuracy gains over direct LLM planners on Natural Plan Calendar Scheduling (?12.4%?), ZebraLogic (?30.8%?), and SciBench Math. Crucially, under multi-task scaling-where standard planners suffer immediate performance collapse-GRASP completely flattens the multi-task degradation penalty. In interleaved dual-task environments, GRASP achieves an absolute accuracy gain of up to 16.7% over direct LLM planners. Furthermore, by isolating context and enforcing strict macro-regularization, GRASP outperforms frontier reasoning models (such as GPT-5-mini) by a margin of 14.5%.
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 presents Völ, a domain-specific language for expressing AI native tasks, including scientific workflows. Völ separates deterministic control flow from probabilistic model calls and places validation, retry logic, and failure handling next to the task that uses them, so the policy for each model step is visible where it runs. It expresses model calls, structured-output contracts, automatic repair, retry policy, and workflow control in one program rather than across prompts, helper scripts, libraries, and glue code, so end-to-end behavior can be read and reviewed in one place.We use chemical entity recognition in scientific articles from NLM-Chem to evaluate Völ and compare it with Python, LangGraph, Snakemake, and Nextflow implementations. The Völ program is more compact and achieves the lowest mean end-to-end runtime, including about 1.8× and 2.1× speedups over Python and LangGraph at 16 concurrent threads. On a six node SLURM cluster, Nextflow with embedded Völ runs about 1.5× faster than Nextflow with embedded Python and keeps per-job AI logic more compact than embedding Python in Nextflow or Snakemake.
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 of object locations. As a result, they cannot accumulate negative evidence across time (e.g., “the object is not here”), leading to redundant exploration and repeated manipulation failures. We introduce PRISM, Planning with Belief under Incomplete World Models, a lightweight inference-time framework that augments VLM planners with an explicit probabilistic belief over candidate object locations. PRISM maintains a categorical distribution over locations for each object and updates it online via Bayesian conditioning from visual observations and structured action feedback. To reduce initial uncertainty, the belief is initialized from instruction-aware affordance priors and integrated into the planning loop via prompt conditioning and belief-guided action filtering. We evaluate PRISM on EmbodiedBench across EB-Habitat (Habitat) and EB-ALFRED (AI2-THOR) using InternVL2.5-8B and GPT-4o-mini backbones with 50 episodes per task category. On EB-Habitat, average success improves from 21.6% to 42.8% with InternVL2.5-8B and from 30.4% to 47.2% with GPT-4omini. On EB-ALFRED, the belief pipeline enables InternVL2.5-8B, which achieves near-zero success under ReAct, to reach up to 30% success across multiple task categories. Beyond performance gains, the belief state provides a transparent uncertainty representation that exposes the agent’s location hypotheses at each step, supporting interpretability for human supervisors in shared-space deployments.
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 VLMs into large-scale Earth observation pipelines presents challenges in computational efficiency, data organization, and information retrieval. To address these challenges, we present DamageScope, a retrieval-augmented framework that combines satellite imagery with Vision-Language Models (VLMs) and Large Language Models (LLMs) to automate property damage analysis. Built on a Retrieval-Augmented Generation (RAG) framework, DamageScope extracts structured visual representations from satellite imagery to support interactive natural language queries for damage assessment. To address scalability, we introduce a novel multi-vector embedding-based clustering algorithm that outperforms traditional single-vector embedding approaches while reducing indexing time by up to 14x. Furthermore, a dual-store data architecture minimizes LLM API calls, reducing both operational cost and response latency by up to approximately 3x. By effectively balancing scalability and operational efficiency, DamageScope provides a robust and practical solution for real-world damage assessment tasks.
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 models.
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 objects and concepts. While vision-language models (VLMs) such as CLIP are widely used for text-image retrieval, even fine-tuned variants often struggle to accurately align such queries with satellite imagery. To address this, we propose Open-SAT, a training-free query embedding refinement algorithm that operates at inference time to improve alignment between user queries and satellite image content. Open-SAT uses VLMs to compute embeddings for image tiles, which are stored in a vector database for efficient retrieval. At query time, it leverages Large Language Models (LLMs) to refine the text embeddings by incorporating contextual information about objects of interest and their surroundings. A threshold-free retrieval mechanism further enhances accuracy and efficiency. Experimental results in three public benchmarks demonstrate that Open-SAT improves the F1 score by up to 16.04%, while retrieving a comparable number of image tiles. These results demonstrate the effectiveness of Open-SAT in open-vocabulary satellite image retrieval, leveraging LLM guidance without the need for additional training or supervision.
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 Language Model (LLM)-driven workflow execution that combines a declarative specification language with a runtime that orchestrates tool calls, conditional control flow, and structured LLM reasoning. Using Bellona, we implement an agentic placement workflow that automatically recommends edge or cloud execution. The workflow uses structured prompts and verifiable tool interactions to (i) parse placement and latency-report instructions, (ii) update the latency log, and (iii) select placements based on measured latency improvement thresholds. We evaluate the resulting agent on two representative microservices-based video analytics applications (human-attributes detection and face recognition) over two days of varying workload. Across 1,440 placement decisions per service, the agent achieves accuracies of 94.66%/84.94% (human-attributes detection, Day1/Day2) and 80.91%/96.53% (face recognition, Day1/Day2) with GPT-4o; with GPT-5, accuracy increases to 98.82%/99.45% (human-attributes detection) and 99.31%/99.8% (face recognition). These results demonstrate that Bellona can support practical, self-improving agentic control for placement of microservices on the computing continuum.
As 2025 comes to a close, NEC Laboratories America reflects on a year defined by scientific breakthroughs, global collaboration, and real-world impact. Our researchers advanced the state of the art across AI, optical networking and sensing, system security, and multimodal analytics, while expanding our intellectual property portfolio and presence at the world’s leading conferences.