DiscussLLM: Teaching Large Language Models When to Speak

/in /by

Large Language Models (LLMs) have demonstrated remarkable capabilities in understanding and generating human-like text, yet they largely operate as reactive agents, responding only when directly prompted. This passivity creates an “awareness gap,” limiting their potential as truly collaborative partners in dynamic human discussions. We introduce , a framework designed to bridge this gap by training models to proactively decide not just to say, but critically, to speak. Our primary contribution is a scalable two-stage data generation pipeline that synthesizes a large-scale dataset of realistic multi-turn human discussions. Each discussion is annotated with one of five intervention types (e.g., Factual Correction, Concept Definition) and contains an explicit conversational trigger where an AI intervention adds value. By training models to predict a special silent token when no intervention is needed, they learn to remain quiet until a helpful contribution can be made. We explore two architectural baselines: an integrated end-to-end model and a decoupled classifier-generator system optimized for low-latency inference. We evaluate these models on their ability to accurately time interventions and generate helpful responses, paving the way for more situationally aware and proactive conversational AI.

Read more

Bifröst: Peer-to-peer Load-balancing for Function Execution in Agentic AI Systems

/in /by

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 milliseconds to several seconds. Traditional load-balancing techniques, such as round-robin, least-loaded, and Peak-EWMA (used in Linkerd), struggle in such settings: round-robin ignores load imbalance, least-loaded reacts slowly to rapid workload shifts, and Peak-EWMA relies on latency tracking, which is ineffective for workloads with high execution time variability. In this paper, we introduce Bifröst, a peer-to-peer load-balancing mechanism that distributes function requests based on real-time active request count rather than latency estimates. Instead of relying on centralized load-balancers or client-side decisions, Bifröst enables function-serving pods to dynamically distribute load by comparing queue lengths and offloading requests accordingly. This avoids unnecessary overhead while ensuring better responsiveness under high-variance workloads. Our evaluation on open-vocabulary object detection, multi-modal understanding, and code generation workloads shows that Bifröst improves function completion time by up to 20% when processing 13,700 requests from 137 AI agents on a 32-node Kubernetes cluster, outperforming both OpenFaaS and OpenFaaS with Linkerd. In an AI-driven insurance claims processing workflow, Bifröst achieves up to 25% faster execution.

Read more

Summer Highlights at NEC Labs America: Teamwork, Innovation, and Fun

/in /by

This summer at NEC Laboratories America was full of energy, teamwork, and connection. From volleyball games in San Jose and TopGolf with colleagues from Princeton to kayaking adventures, a campus picnic, and celebrating our incredible interns, our teams came together to learn, laugh, and grow. Here’s a look back at the highlights that made Summer 2025 so memorable.

Read more

Harnessing Vision Models for Time Series Analysis: A Survey

/in /by

Time series analysis has witnessed the inspiring development from traditional autoregressive models, deep learning models, to recent Transformers and Large Language Models (LLMs). Efforts in leveraging vision models for time series analysis have also been made along the way but are less visible to the community due to the predominant research on sequence modeling in this domain. However, the discrepancy between continuous time series and the discrete token space of LLMs, and the challenges in explicitly modeling the correlations of variates in multivariate time series have shifted some research attentions to the equally successful Large Vision Models (LVMs) and Vision Language Models (VLMs). To fill the blank in the existing literature, this survey discusses the advantages of vision models over LLMs in time series analysis. It provides a comprehensive and in-depth overview of the existing methods, with dual views of detailed taxonomy that answer the key research questions including how to encode time series as images and how to model the imaged time series for various tasks. Additionally, we address the challenges in the pre- and post-processing steps involved in this framework and outline future directions to further advance time series analysis with vision models.

Read more

Multi-modal Time Series Analysis: A Tutorial and Survey

/in /by

Multi-modal time series analysis has recently emerged as a prominent research area, driven by the increasing availability of diverse data modalities, such as text, images, and structured tabular data from real-world sources. However, effective analysis of multi-modal time series is hindered by data heterogeneity, modality gap, misalignment, and inherent noise. Recent advancements in multi-modal time series methods have exploited the multi-modal context via cross-modal interactions based on deep learning methods, significantly enhancing various downstream tasks. In this tutorial and survey, we present a systematic and up-to-date overview of multi-modal time series datasets and methods. We first state the existing challenges of multi-modal time series analysis and our motivations, with a brief introduction of preliminaries. Then, we summarize the general pipeline and categorize existing methods through a unified cross-modal interaction framework encompassing fusion, alignment, and transference at different levels (i.e., input, intermediate, output), where key concepts and ideas are highlighted. We also discuss the real-world applications of multi-modal analysis for both standard and spatial time series, tailored to general and specific domains. Finally, we discuss future research directions to help practitioners explore and exploit multi-modal time series. The up-to-date resources are provided in the GitHub repository. https://github.com/UConn-DSIS/Multi-modal-Time-Series-Analysis.

Read more

ICeTEA: Mixture of Detectors for Metric-Log Anomaly Detection

/in /by

Anomaly detection is essential for identifying unusual system behaviors and has wide-ranging applications, from fraud detection to system monitoring. In web servers, anomalies are typically detected using two types of data: metrics (numerical indicators of performance) and logs (records of system events). While correlations between metrics and logs in real-world scenarios highlight the need for joint analysis, which is termed the “metric-log anomaly detection” problem, it has not been fully explored yet due to inherent differences between metrics and logs. In this paper, we propose ICeTEA, a novel system for metric-log anomaly detection that integrates three detectors: a metric-log detector based on a multimodal Variational Autoencoder (VAE), and two individual metric and log detectors. By leveraging the ensemble technique to combine outputs of these detectors, ICeTEA enhances the effectiveness and robustness of metric-log anomaly detection. Case studies demonstrate two key functionalities of ICeTEA: data visualization and rankings of contributions to anomaly scores. Experiments demonstrate that our proposed ICeTEA accurately detects true anomalies while significantly reducing false positives.

Read more

Roadside Multi-LiDAR Data Fusion for Enhanced Traffic Safety

/in /by

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 better estimate traffic parameters than one can estimate from a single LiDAR. The key challenge is to calibrate multiple LiDARs both in time and space. The problem is more complex when heterogeneous sensors differ in resolution and are positioned arbitrarily on a traffic intersection.We propose a calibration technique to fuse multiple LiDARs. We show that our technique works on various data granularity and enables real-time analytics for roadside traffic monitoring. We evaluate on a large number of simulated traffic scenarios and show that fusion improves accuracy of vehicle counting and near-collision detection. We apply our algorithm on real traffic data and demonstrate utility in classifying vehicles and detecting occluded traffic participants.

Read more

Identifying Combinatorial Regulatory Genes for Cell Fate Decision via Reparameterizable Subset Explanations

/in /by

Cell fate decisions are highly coordinated processes governed bycomplex interactions among numerous regulatory genes, whiledisruptions in these mechanisms can lead to developmental abnormalitiesand disease. Traditional methods often fail to capture suchcombinatorial interactions, limiting their ability to fully model cellfate dynamics. Here, we introduce MetaVelo, a global feature explanationframework for identifying key regulatory gene sets influencingcell fate transitions. MetaVelo models these transitions as ablack-box function and employs a differentiable neural ordinary differentialequation (ODE) surrogate to enable efficient optimization.By reparameterizing the problem as a controllable data generationprocess, MetaVelo overcomes the challenges posed by the nondifferentiablenature of cell fate dynamics. Benchmarking acrossdiverse stand-alone and longitudinal single-cell RNA-seq datasetsand three black-box cell fate models demonstrates its superiorityover 12 baseline methods in predicting developmental trajectoriesand identifying combinatorial regulatory gene sets. MetaVelo furtherdistinguishes independent from synergistic regulatory genes,offering novel insights into the gene interactions governing cellfate. With the growing availability of high-resolution single-celldata, MetaVelo provides a scalable and effective framework fo

Read more

On Synthesizing Data for Context Attribution in Question Answering

/in /by

Question Answering (QA) accounts for a significantportion of LLM usage “in the wild”.However, LLMs sometimes produce false ormisleading responses, also known as hallucinations.Therefore, grounding the generatedanswers in contextually provided information—i.e., providing evidence for the generated text—is paramount for LLMs’ trustworthiness. Providingthis information is the task of context attribution.In this paper, we systematically studyLLM-based approaches for this task, namelywe investigate (i) zero-shot inference, (ii) LLMensembling, and (iii) fine-tuning of small LMson synthetic data generated by larger LLMs.Our key contribution is SYNQA: a novel generativestrategy for synthesizing context attributiondata. Given selected context sentences, anLLM generates QA pairs that are supported bythese sentences. This leverages LLMs’ naturalstrengths in text generation while ensuring clearattribution paths in the synthetic training data.We show that the attribution data synthesizedvia SYNQA is highly effective for fine-tuningsmall LMs for context attribution in differentQA tasks and domains. Finally, with a userstudy, we validate the usefulness of small, efficientLMs (fine-tuned on synthetic data fromSYNQA) in context attribution for QA.

Read more

Feasibility study on scour monitoring for subsea cables of offshore wind turbines using distributed fiber optic sensors

/in /by

Subsea cables are critical components of offshore wind turbines and are subjected to scour. Monitoring the scour conditions of subsea cables plays significant roles in improving safety and operation efficiency and reducing the levelized cost of electricity. This paper presents a feasibility study on monitoring subsea cables using distributed fiber optic sensors (DFOS), aiming to evaluate the technical and economic performance of utilizing DFOS to detect, locate, and quantify scour conditions. Laboratory experiments were conducted to test the response ofDFOS measurements to the change of support conditions which were used to simulate scour effects, and a finite element model was developed to investigate the impact of scour on the mechanical responses of subsea cables in different scour scenarios. Economic analysis of three methods, involving the use of DFOS, discrete sensors, and underwater robots, is performed via a case study. The results showed that the proposed method has technical and economic benefits for monitoring subsea cables. This research offers insights into monitoring subsea structuresfor offshore wind turbines.

Read more