Chorus: Harmonizing Context and Sensing Signals for Data-Free Model Customization in IoT

• URL: http://arxiv.org/abs/2512.15206v1
• Date: Wed, 17 Dec 2025 08:56:21 GMT
• Title: Chorus: Harmonizing Context and Sensing Signals for Data-Free Model Customization in IoT
• Abstract summary: We propose Chorus, a data-free model customization approach that adapts models to unseen deployment conditions.<n>Chorus learns effective context representations that capture their influence on sensor data patterns.<n>Experiments show that Chorus outperforms state-of-the-art baselines by up to 11.3% in unseen contexts.
• Score: 2.546351849351806
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In real-world IoT applications, sensor data is usually collected under diverse and dynamic contextual conditions where factors such as sensor placements or ambient environments can significantly affect data patterns and downstream performance. Traditional domain adaptation or generalization methods often ignore such context information or use simplistic integration strategies, making them ineffective in handling unseen context shifts after deployment. In this paper, we propose Chorus, a context-aware, data-free model customization approach that adapts models to unseen deployment conditions without requiring target-domain data. The key idea is to learn effective context representations that capture their influence on sensor data patterns and to adaptively integrate them based on the degree of context shift. Specifically, Chorus first performs unsupervised cross-modal reconstruction between unlabeled sensor data and language-based context embeddings, while regularizing the context embedding space to learn robust, generalizable context representations. Then, it trains a lightweight gated head on limited labeled samples to dynamically balance sensor and context contributions-favoring context when sensor evidence is ambiguous and vice versa. To further reduce inference latency, Chorus employs a context-caching mechanism that reuses cached context representations and updates only upon detected context shifts. Experiments on IMU, speech, and WiFi sensing tasks under diverse context shifts show that Chorus outperforms state-of-the-art baselines by up to 11.3% in unseen contexts, while maintaining comparable latency on smartphone and edge devices.

Related papers

• An Adversarial Zero-Shot Learning Approach for Anomaly Detection in Multivariate IoT Traffic Data [7.858819231575403]
  Anomaly detection in Internet of Things networks presents unique challenges due to diversity of devices, lack of labeled data, and domain variability across environments.<n>We propose a novel framework for multivariate time-series anomaly detection that leverages adversarial learning and contrastive loss within a sequence-based Variational Autoencoder architecture.
  arXiv  Detail & Related papers  (2026-09-03T08:07:06Z)
• The Universal Language of CSI:Unifying Wireless Sensing Across Devices and Environments [18.372157907342817]
  WiFi sensing based on Channel State Information promises ubiquitous, device-free perception.<n>Current research remains trapped in a Tower of Babel, fragmented into isolated silos.<n>We propose a foundation-model framework that treats CSI as a structured language with a learnable universal grammar.
  arXiv  Detail & Related papers  (2026-06-30T04:30:04Z)
• Still Between Us? Evaluating and Improving Voice Assistant Robustness to Third-Party Interruptions [52.45054413627452]
  TPI-Train is a dataset of 88K instances designed with speaker-aware hard negatives to enforce acoustic cue prioritization for interruption handling.<n>TPI-Bench is a comprehensive evaluation framework designed to rigorously measure the interruption-handling strategy.
  arXiv  Detail & Related papers  (2026-04-19T10:03:42Z)
• ConInfer: Context-Aware Inference for Training-Free Open-Vocabulary Remote Sensing Segmentation [12.428190609914594]
  Training-free open-vocabulary remote sensing segmentation (OVRSS) has emerged as a promising paradigm for achieving category-agnostic semantic understanding in remote sensing imagery.<n>We propose ConInfer, a context-aware inference framework for OVRSS that performs joint prediction across multiple spatial units.<n>Our method significantly enhances segmentation consistency, robustness, and generalization in complex remote sensing environments.
  arXiv  Detail & Related papers  (2026-03-31T05:12:02Z)
• When Does Context Help? Error Dynamics of Contextual Information in Large Language Models [64.88201012057822]
  We present a unified theoretical framework for analyzing the effect of arbitrary contextual information in large language models.<n>Our analysis characterizes contextual influence through output error dynamics.<n> Experiments across ICL, retrieval-augmented generation, and memory evolution validate our theory and motivate a principled context selection strategy.
  arXiv  Detail & Related papers  (2026-02-09T05:58:41Z)
• Deep Learning for Contextualized NetFlow-Based Network Intrusion Detection: Methods, Data, Evaluation and Deployment [5.402853794565817]
  This paper synthesizes recent research on context-aware deep learning for flow-based intrusion detection.<n>We organize existing methods into a four-dimensional taxonomy covering temporal context, graph or relational context, multimodal context, and multi-resolution context.<n>We review common failure modes that can inflate reported results, including temporal leakage, data splitting, dataset design flaws, limited dataset diversity, and weak cross-dataset generalization.
  arXiv  Detail & Related papers  (2026-02-05T12:25:18Z)
• Spatial Context Improves the Integration of Text with Remote Sensing for Mapping Environmental Variables [19.670023742796136]
  We propose an attention-based approach that combines aerial imagery and geolocated text within a spatial neighbourhood.<n>Our model is evaluated on the task of predicting 103 environmental variables from the SWECO25 data cube.
  arXiv  Detail & Related papers  (2026-01-13T17:27:16Z)
• MobiDiary: Autoregressive Action Captioning with Wearable Devices and Wireless Signals [20.30554810750095]
  Human Activity Recognition (HAR) in smart homes is critical for health monitoring and assistive living.<n>We present MobiDiary, a framework that generates natural language descriptions of daily activities directly from heterogeneous physical signals.
  arXiv  Detail & Related papers  (2026-01-13T04:16:17Z)
• From Indoor to Open World: Revealing the Spatial Reasoning Gap in MLLMs [65.04549036809557]
  We introduce a benchmark built from pedestrian-perspective videos captured with synchronized stereo cameras, LiDAR, and IMU/GPS sensors.<n>This dataset provides metrically precise 3D information, enabling the automatic generation of spatial reasoning questions.<n> Evaluations reveal that the performance gains observed in structured indoor benchmarks vanish in open-world settings.
  arXiv  Detail & Related papers  (2025-12-22T18:58:12Z)
• Grounding Long-Context Reasoning with Contextual Normalization for Retrieval-Augmented Generation [57.97548022208733]
  We show that seemingly superficial choices in key-value extraction can induce shifts in accuracy and stability.<n>We introduce Contextual Normalization, a strategy that adaptively standardizes context representations before generation.
  arXiv  Detail & Related papers  (2025-10-15T06:28:25Z)
• Context-Informed Grounding Supervision [102.11698329887226]
  Context-INformed Grounding Supervision (CINGS) is a post-training supervision in which the model is trained with relevant context prepended to the response.<n>Our experiments demonstrate that models trained with CINGS exhibit stronger grounding in both textual and visual domains.
  arXiv  Detail & Related papers  (2025-06-18T14:13:56Z)
• Spatial-Temporal-Spectral Unified Modeling for Remote Sensing Dense Prediction [20.1863553357121]
  Current deep learning architectures for remote sensing are fundamentally rigid.<n>We introduce the Spatial-Temporal-Spectral Unified Network (STSUN) for unified modeling.<n> STSUN can adapt to input and output data with arbitrary spatial sizes, temporal lengths, and spectral bands.<n>It unifies various dense prediction tasks and diverse semantic class predictions.
  arXiv  Detail & Related papers  (2025-05-18T07:39:17Z)
• Adaptive State-Space Mamba for Real-Time Sensor Data Anomaly Detection [2.922256022514318]
  We propose an emphAdaptive State-Space Mamba framework for real-time sensor data anomaly detection.<n>Our approach is easily to other time-series tasks that demand rapid and reliable detection capabilities.
  arXiv  Detail & Related papers  (2025-03-26T21:37:48Z)
• A Reality Check on Context Utilisation for Retrieval-Augmented Generation [44.54803681476863]
  We introduce DRUID (Dataset of Retrieved Unreliable, Insufficient and Difficult-to-understand contexts) with real-world queries and contexts manually annotated for stance.<n>The dataset is based on the task of automated claim verification, for which automated retrieval of real-world evidence is crucial.<n>We show that synthetic datasets exaggerate context characteristics rare in real retrieved data, which leads to inflated context utilisation results.
  arXiv  Detail & Related papers  (2024-12-22T14:16:38Z)
• DynST: Dynamic Sparse Training for Resource-Constrained Spatio-Temporal Forecasting [31.398965880415492]
  Earth science systems rely heavily on the extensive deployment of sensors.<n>Traditional approaches to sensor deployment utilize specific algorithms to design and deploy sensors.<n>We introduce for the first time the concept of sparse-temporal data dynamic sparse training and are committed to adaptively, dynamically filtering important distributions sensor.
  arXiv  Detail & Related papers  (2024-03-05T12:31:24Z)
• Text2Data: Low-Resource Data Generation with Textual Control [100.5970757736845]
  Text2Data is a novel approach that utilizes unlabeled data to understand the underlying data distribution.<n>It undergoes finetuning via a novel constraint optimization-based learning objective that ensures controllability and effectively counteracts catastrophic forgetting.
  arXiv  Detail & Related papers  (2024-02-08T03:41:39Z)
• Bridging the Gap Between Clean Data Training and Real-World Inference for Spoken Language Understanding [76.89426311082927]
  Existing models are trained on clean data, which causes a textitgap between clean data training and real-world inference. We propose a method from the perspective of domain adaptation, by which both high- and low-quality samples are embedding into similar vector space. Experiments on the widely-used dataset, Snips, and large scale in-house dataset (10 million training examples) demonstrate that this method not only outperforms the baseline models on real-world (noisy) corpus but also enhances the robustness, that is, it produces high-quality results under a noisy environment.
  arXiv  Detail & Related papers  (2021-04-13T17:54:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.