Shaobo Han is a Senior Researcher in the Optical Networking and Sensing Department at NEC Laboratories America in Princeton, NJ. He received his Ph.D. in Electrical and Computer Engineering and his M.S. in Statistical Science from Duke University, where his research focused on probabilistic modeling, transfer learning, and structured variational inference. He also earned an M.Eng. degree in Signal and Information Processing from the University of Chinese Academy of Sciences.
At NEC, Dr. Han has been prototyping and delivering advanced algorithmic solutions for real-world applications of sensing AI. By leveraging massive waveform data from NEC’s distributed fiber-optic sensors and cutting-edge machine learning technologies, his work transforms telecom infrastructure into a dense, large-scale network of acoustic sensors capable of real-time situational awareness. His research has led to multiple world-first and industry-first technology field trials and commercial products. He is the recipient of the NECAM Extra Mile Award, and the Outstanding Performance Award from NEC’s Global Innovation Business Unit (GIBU).
He also conducts research on parameter-efficient fine-tuning of large language models and the flexible adaptation of audio-language models. He holds more than 10 U.S. patents and has authored over 50 peer-reviewed papers in top-tier venues, including NeurIPS, ICLR, ICML, AISTATS, ICASSP, OFC, IEEE Transactions on Signal Processing, and the Journal of Lightwave Technology. His innovations advance the learning of structured, interpretable representations of the physical world from raw sensory inputs and enable cost-effective generalization to new environments and deployment scenarios.
NEC Labs America is heading to Denver for CVPR 2026, one of the most prestigious gatherings in computer vision, machine learning, and pattern recognition. The IEEE/CVF Conference on Computer Vision and Pattern Recognition brings innovators from around the world to share breakthroughs.
Real-world deployment requires sound event and acoustic scene classification systems to remain reliable in noisy, diverse environments on resource-constrained devices. Although contrastive language-audio pretraining (CLAP) models with Transformer-based audio encoders achieve strong zero-shot performance, their computational cost hinders deployment. In this paper, we propose Mix-CLAP, a computationally efficient, noise-aware CLAP model with knowledge-distilled audio encoders. Our method includes: (1) a two-stage knowledge distillation from teacher embeddings to two lightweight student encoders?one on clean audio, the other on noisy audio, and (2) adaptive inference that combines their embeddings together with a fusion parameter and minimizes the parameterized entropy at test time. Experiments show that Mix-CLAP with MobileNetV3-based audio encoders greatly improves computational efficiency, while achieving a comparable average accuracy of 52.58% to the Transformer-based CLAP model at 52.83% on the recorded ESC50 datasets with different devices including microphones and fiber-optic distributed acoustic sensors under diverse conditions, making it suitable for real-world, resource-constrained applications.
Knowledge distillation establishes a learning paradigm that leverages both data supervision and teacher guidance. However, determining the optimal balance between learning from data and learning from the teacher is challenging, as some samples may be noisy while others are subject to teacher uncertainty. This motivates the need for adaptively balancing data and teacher supervision. We propose Beta-weighted Knowledge Distillation (Beta-KD), an uncertainty-aware distillation framework that adaptively modulates how much the student relies on teacher guidance. Specifically, we formulate teacher–student learning from a unified Bayesian perspective and interpret teacher supervision as a Gibbs prior over student activations. This yields a closed-form, uncertainty-aware weighting mechanism and supports arbitrary distillation objectives and their combinations. Extensive experiments on multimodal VQA benchmarks demonstrate that distilling student Vision-Language Models from a large teacher VLM consistently improves performance. The results show that Beta-KD outperforms existing knowledge distillation methods.
Distributed fiber optic sensing (DFOS) has emerged as a promising technology for wide-area monitoring by utilizing existing telecom cables as large-scale sensing media. This paper explores three sensing modalities, backscattering-based sensing, forward-transmission-based sensing, and hybrid sensing, and discusses their respective benefits, challenges, and application domains. Backscattering sensing demonstrates strong potential for applications such as road traffic monitoring, pavement condition assessment, intrusion detection, and cabledamage prevention but is constrained in amplified dense wavelength division multiplexing (DWDM) networks. Forward-transmission sensing enables sensing over operational telecom links with in-line amplification, extending sensing reach, although it involves trade-offs in spatial resolution and localization accuracy. To address these challenges, a hybrid sensing architecture that integrates backscattering and forward-transmission techniques is introduced, achieving enhanced sensing distance while maintaining high sensitivity and localization performance.In addition, this work incorporates artificial intelligence (AI) through a locally adaptive anomaly detection (LAAD) framework based on self-supervised representation learning. By leveraging location-based pretext tasks and unlabeled data, the proposed AI approach enables efficient adaptation across heterogeneous fiber routes and operational environments, significantly reducing reliance on labeled data while improving cross-domain generalization. Field trials over deployed telecom networks validate the feasibility and effectiveness of the proposedsensing and AI framework, demonstrating scalable, telecom-compatible DFOS for real-world infrastructure monitoring and intelligent network operations.
We present methods and field trial results demonstrating an integrated distributed acoustic sensing (DAS) and distributed temperature sensing (DTS) system for manhole localization, condition diagnostics, and anomaly detection in pre-deployed telecommunication fiber networks. The proposed system leverages ambient environmental signals, such as vibrational patterns from traffic and day-night temperature fluctuations, and machine learning techniques for automated detection. By combining DAS waterfall traces with temperature measurements from DTS, we achieve improved classification accuracy. Experimental results from three real-world testbeds in Texas and New Jersey show a significant improvement in classification accuracyfrom 78.9% and 89.5% using DAS and DTS alone, respectively, to 94.7% via cross-referenced analysis. We propose a structured prediction formulation for manhole localization based on a U-Net architecture with a gated attention mechanism, where the label of each fiber location in the waterfall image is predicted using both its neighboring context and within-patch discriminative features. The method also supports cross-route generalization for manhole localization and enables condition diagnostics, identifying issues such as cable exposure and water ingress. These results highlight the potential for scalable deployment of fiber sensing solutions for real-time, continuous monitoring of telecom infrastructure.
Low-Rank Adaptation (LoRA) has become the de facto parameter-efficient fine-tuning (PEFT) method for large language models (LLMs) by constraining weight updates to low-rank matrices. Recent works such as Tied-LoRA, VeRA, and VB-LoRA push efficiency further by introducing additional constraints to reduce the trainable parameter space. In this paper, we show that the parameter space reduction strategies employed by these LoRA variants can be formulated within a unified framework, Uni-LoRA, where the LoRA parameter space, flattened as a high-dimensional vector space R^D, can be reconstructed through a projection from a subspace R^d, with d ll D. We demonstrate that the fundamental difference among various LoRA methods lies in the choice of the projection matrix, P in R^(Unknown sysvar: (D times d)).Most existing LoRA variants rely on layer-wise or structure-specific projections that limit cross-layer parameter sharing, thereby compromising parameter efficiency. In light of this, we introduce an efficient and theoretically grounded projection matrix that is isometric, enabling global parameter sharing and reducing computation overhead. Furthermore, under the unified view of Uni-LoRA, this design requires only a single trainable vector to reconstruct LoRA parameters for the entire LLM – making Uni-LoRA both a unified framework and a “one-vector-only” solution. Extensive experiments on GLUE, mathematical reasoning, and instruction tuning benchmarks demonstrate that Uni-LoRA achieves state-of-the-art parameter efficiency while outperforming or matching prior approaches in predictive performance.
NEC Laboratories America is heading to San Diego for NeurIPS 2025, where our researchers will present cutting-edge work spanning optimization, AI systems, language modeling, and trustworthy machine learning. multi-agent coordination, scalable training, efficient inference, and techniques for detecting LLM-generated text.
Eric Blow of NEC Labs will address how machine-learning methods applied to distributed acoustic-sensing data can monitor facility perimeters and detect intrusion via walk, dig, or drive events over buried optical fibre—for example achieving ~90% classification accuracy.
Distributed fiber-optic sensing combined with machine learning enables continuous monitoring of telecom infrastructure. We employ generative modeling for event classification, supporting semi supervised learning, uncertainty calibration, and noise resilience. Our approach offers a scalable, data-efficient solution for real-world deployment in complex environments.
We introduce anchor vectors to monitor Rayleigh-backscattering variability in a fiber-optic computing system that performs nonlinear random projection for image classification. With a ~0.4-s calibration interval, system stability can be maintained with a linear decoder, achieving an average accuracy of 80%-90%.
