arXiv subjects

Xiaofan Jiang

Publications and source records attributed to Xiaofan Jiang.

At least 19 recordsLinked to original sources

arXiv2026

Pro$^2$Assist: Continuous Step-aware Proactive Assistance with Multi-modal Egocentric Perception for Long-horizon Procedural Tasks

Procedural tasks with multiple ordered steps are ubiquitous in daily life. Recent advances in multimodal large language models (MLLMs) have enabled personal assistants that support daily activities. However, existing systems primarily provide reactive guidance triggered by user queries, or limited proactive assistance for isolated short-term events rather than long-horizon procedural tasks. In this work, we introduce Pro$^2$Assist, a step-aware proactive assistant that continuously tracks fine-grained task progress and reasons over the user's evolving state to provide timely assistance throughout tasks. Pro$^2$Assist leverages multimodal data from augmented reality (AR) glasses to achieve motion-based perception. It then extracts step-oriented procedural context from multi-scale temporal dynamics and task-specific expert knowledge. Based on both sensory input and procedural context, Pro$^2$Assist performs continuous reasoning to infer user needs and display timely assistance on AR glasses. We evaluate Pro$^2$Assist using a dataset curated from public sources and a real-world dataset collected on our testbed with AR glasses. Extensive evaluations show that Pro$^2$Assist outperforms the best-performing baselines by over 21% in procedural action understanding accuracy, and it achieves up to 2.29x the proactive timing accuracy of baselines. A user study with 20 participants further shows that 90% find Pro$^2$Assist useful, indicating its effectiveness for real-world procedural assistance.

cs.AI↗

arXiv2026

RadarTwin: Scene-Specific mmWave Radar Simulation and Learning for Mobile Indoor Perception

Millimeter-wave (mmWave) radar perception is limited by data scarcity: models trained on existing radar datasets fail to generalize to new objects, environments, and sensing trajectories. We present RadarTwin, a framework for generating deployment-specific radar training data before real data collection. Given a 3D reconstruction of a target space (phone LiDAR, robot-mounted sensing, or RGB-to-3D), RadarTwin uses a vision-language model to infer radar-relevant surface materials and a physics-based ray tracer to synthesize raw frequency-modulated continuous-wave (FMCW) radar measurements with multi-bounce propagation. To study what transfers from simulation to reality, we collect a paired real-simulated dataset spanning household objects, material classes, distances, rotations, translations, and mobile sensing trajectories. We show that simulated and real radar share the same object-discriminative shape and material features, and that modeling the environment's multipath is essential to matching real measurements. A representation trained on simulation alone recognizes real objects at 2.5 times chance with no real radar labels, and a few labeled examples raise this to 95.3% on a 12-way recognition task. RadarTwin enables training radar perception for a new space before any real radar data is collected there.

cs.CV↗

arXiv2026

TimeSRL: Generalizable Time-Series Behavioral Modeling via Semantic RL-Tuned LLMs -- A Case Study in Mental Health

Longitudinal passive sensing enables continuous health prediction, yet models often fail under cross-dataset distribution shifts. Traditional ML overfits cohort-specific artifacts, while Large Language Models (LLMs) struggle to reason reliably over long, heterogeneous time-series. We introduce TimeSRL, a two-stage LLM framework that routes predictions through an explicit semantic bottleneck. The model first abstracts raw signals into high-level natural language, then predicts behavioral outcomes from these abstractions alone. This forces the model to reason over semantic concepts that we argue generalize better than raw numbers. We optimize this process end-to-end using Group Relative Policy Optimization (GRPO) with Reinforcement Learning from Verifiable Rewards (RLVR), learning outcome-aligned abstractions without gold intermediate annotations. Instantiated on mental-health prediction, TimeSRL achieves state-of-the-art performance on a benchmark designed to stress-test cross-cohort generalization under a rigorous leave-one-dataset-out (LOSO) protocol, reducing mean absolute error (MAE) over strong non-LLM ML and LLM baselines by 3.1--10.1% and 9.5--44.1% for anxiety, and 3.2--9.6% and 27.4--57.6% for depression (all $p$s<0.05). TimeSRL significantly outperforms prior methods in cross-benchmark transfer across different sensing pipelines, rivaling its own within-domain performance without target-domain fine-tuning. These results demonstrate that semantic abstractions are reusable and point to a new direction for generalizable behavior modeling via RL-tuned LLMs.

cs.LG↗

arXiv2026

ProAgent: Harnessing On-Demand Sensory Contexts for Proactive LLM Agent Systems in the Wild

Recent studies have begun to explore proactive large language model (LLM) agents that provide unobtrusive assistance by automatically leveraging contextual information, such as in code editing and in-app suggestions. However, most focus on short, task-specific episodes or on-screen contexts, rather than continuously perceiving and assisting users throughout daily life. Enabling such in-the-wild assistance requires continuous sensing of users' surroundings, which can incur substantial system overhead. In this work, we propose ProAgent, an end-to-end proactive agent system that harnesses on-demand sensory contexts to provide in-the-wild assistance. ProAgent first employs on-demand tiered perception to continuously sense users' surroundings by integrating low-cost contextual cues with richer perception on demand, and uses proactive-oriented context extraction to derive hierarchical contexts integrating both sensory contexts and human preferences. ProAgent then employs a context-aware proactive reasoner to infer user needs and invokes external tools to deliver proactive assistance. We implement ProAgent on AR glasses and evaluate it on a public dataset and a real-world dataset. Results demonstrate that ProAgent achieves up to 27.7% higher proactive prediction accuracy and 20.5% lower false detection than state-of-the-art baselines. A user study with 20 participants shows that 85% were satisfied with ProAgent and willing to use it in daily life.

cs.AI↗

arXiv2026

Investigation on the Robustness of Acoustic Foundation Models on Post Exercise Speech

Automatic speech recognition (ASR) has been extensively studied on neutral and stationary speech, yet its robustness under post-exercise physiological shift remains underexplored. Compared with resting speech, post-exercise speech often contains micro-breaths, non-semantic pauses, unstable phonation, and repetitions caused by reduced breath support, making transcription more difficult. In this work, we benchmark acoustic foundation models on post-exercise speech under a unified evaluation protocol. We compare sequence-to-sequence models (Whisper and FunASR/Paraformer) and self-supervised encoders with CTC decoding (Wav2Vec2, HuBERT, and WavLM), under both off-the-shelf inference and post-exercise in-domain fine-tuning. Across the Static/Post-All benchmark, most models degrade on post-exercise speech, while FunASR shows the strongest baseline robustness at 14.57% WER and 8.21% CER on Post-All. Fine-tuning substantially improves several CTC-based models, whereas Whisper shows unstable adaptation. As an exploratory case study, we further stratify results by fluent and non-fluent speakers; although the non-fluent subset is small, it is consistently more challenging than the fluent subset. Overall, our findings show that post-exercise ASR robustness is strongly model-dependent, that in-domain adaptation can be highly effective but not uniformly stable, and that future post-exercise ASR studies should explicitly separate fluency-related effects from exercise-induced speech variation.

cs.SD↗

arXiv2026

SensorPersona: An LLM-Empowered System for Continual Persona Extraction from Longitudinal Mobile Sensor Streams

Personalization is essential for Large Language Model (LLM)-based agents to adapt to users' preferences and improve response quality and task performance. However, most existing approaches infer personas from chat histories, which capture only self-disclosed information rather than users' everyday behaviors in the physical world, limiting the ability to infer comprehensive user personas. In this work, we introduce SensorPersona, an LLM-empowered system that continuously infers stable user personas from multimodal longitudinal sensor streams unobtrusively collected from users' mobile devices. SensorPersona first performs person-oriented context encoding on continuous sensor streams to enrich the semantics of sensor contexts. It then employs hierarchical persona reasoning that integrates intra- and inter-episode reasoning to infer personas spanning physical patterns, psychosocial traits, and life experiences. Finally, it employs clustering-aware incremental verification and temporal evidence-aware updating to adapt to evolving personas. We evaluate SensorPersona on a self-collected dataset containing 1,580 hours of sensor data from 20 participants, collected over up to 3 months across 17 cities on 3 continents. Results show that SensorPersona achieves up to 31.4% higher recall in persona extraction, an 85.7% win rate in persona-aware agent responses, and notable improvements in user satisfaction compared to state-of-the-art baselines.

cs.CL↗

arXiv2026

Sim2Radar: Toward Bridging the Radar Sim-to-Real Gap with VLM-Guided Scene Reconstruction

Millimeter-wave (mmWave) radar provides reliable perception in visually degraded indoor environments (e.g., smoke, dust, and low light), but learning-based radar perception is bottlenecked by the scarcity and cost of collecting and annotating large-scale radar datasets. We present Sim2Radar, an end-to-end framework that synthesizes training radar data directly from single-view RGB images, enabling scalable data generation without manual scene modeling. Sim2Radar reconstructs a material-aware 3D scene by combining monocular depth estimation, segmentation, and vision-language reasoning to infer object materials, then simulates mmWave propagation with a configurable physics-based ray tracer using Fresnel reflection models parameterized by ITU-R electromagnetic properties. Evaluated on real-world indoor scenes, Sim2Radar improves downstream 3D radar perception via transfer learning: pre-training a radar point-cloud object detection model on synthetic data and fine-tuning on real radar yields up to +3.7 3D AP (IoU 0.3), with gains driven primarily by improved spatial localization. These results suggest that physics-based, vision-driven radar simulation can provide effective geometric priors for radar learning and measurably improve performance under limited real-data supervision.

cs.CV↗

arXiv2026

ReSPEC: A Framework for Online Multispectral Sensor Reconfiguration in Dynamic Environments

Multi-sensor fusion is central to robust robotic perception, yet most existing systems operate under static sensor configurations, collecting all modalities at fixed rates and fidelity regardless of their situational utility. This rigidity wastes bandwidth, computation, and energy, and prevents systems from prioritizing sensors under challenging conditions such as poor lighting or occlusion. Recent advances in reinforcement learning (RL) and modality-aware fusion suggest the potential for adaptive perception, but prior efforts have largely focused on re-weighting features at inference time, ignoring the physical cost of sensor data collection. We introduce a framework that unifies sensing, learning, and actuation into a closed reconfiguration loop. A task-specific detection backbone extracts multispectral features (e.g. RGB, IR, mmWave, depth) and produces quantitative contribution scores for each modality. These scores are passed to an RL agent, which dynamically adjusts sensor configurations, including sampling frequency, resolution, sensing range, and etc., in real time. Less informative sensors are down-sampled or deactivated, while critical sensors are sampled at higher fidelity as environmental conditions evolve. We implement and evaluate this framework on a mobile rover, showing that adaptive control reduces GPU load by 29.3\% with only a 5.3\% accuracy drop compared to a heuristic baseline. These results highlight the potential of resource-aware adaptive sensing for embedded robotic platforms.

cs.RO↗

arXiv2025

A Large-Scale Multimodal Dataset and Benchmarks for Human Activity Scene Understanding and Reasoning

Multimodal human action recognition (HAR) leverages complementary sensors for activity classification. Beyond recognition, recent advances in large language models (LLMs) enable detailed descriptions and causal reasoning, motivating new tasks: human action understanding (HAU) and human action reasoning (HARn). However, most LLMs, especially large vision language models (LVLMs), struggle with non-RGB modalities such as depth, IMU, and mmWave due to the lack of large-scale data-caption resources. Existing HAR datasets mainly provide coarse data-label annotations, which are insufficient to capture fine-grained action dynamics needed for HAU and HARn. We consider two ground-truth pair types: (1) data label (discrete category) and (2) data caption (textual description). Naively generating captions from labels often lacks logical and spatiotemporal consistency. We introduce CUHK-X, a large-scale multimodal dataset and benchmark suite for HAR, HAU, and HARn. CUHK-X contains 58,445 samples covering 40 actions performed by 30 participants across two indoor environments. To improve caption consistency, we propose a prompt-based scene creation method that leverages LLMs to generate logically connected activity sequences, followed by human validation. CUHK-X includes three benchmarks with six evaluation tasks. Experiments report average accuracies of 76.52% (HAR), 40.76% (HAU), and 70.25% (HARn). CUHK-X aims to enable the community to apply and develop data-intensive learning methods for robust, multimodal human activity analysis. Project page and code: https://openaiotlab.github.io/CUHK-X/ and https://github.com/openaiotlab/CUHK-X.

cs.CV↗

arXiv2025

ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptions

Recent advances in Large Language Models (LLMs) have propelled intelligent agents from reactive responses to proactive support. While promising, existing proactive agents either rely exclusively on observations from enclosed environments (e.g., desktop UIs) with direct LLM inference or employ rule-based proactive notifications, leading to suboptimal user intent understanding and limited functionality for proactive service. In this paper, we introduce ContextAgent, the first context-aware proactive agent that incorporates extensive sensory contexts surrounding humans to enhance the proactivity of LLM agents. ContextAgent first extracts multi-dimensional contexts from massive sensory perceptions on wearables (e.g., video and audio) to understand user intentions. ContextAgent then leverages the sensory contexts and personas from historical data to predict the necessity for proactive services. When proactive assistance is needed, ContextAgent further automatically calls the necessary tools to assist users unobtrusively. To evaluate this new task, we curate ContextAgentBench, the first benchmark for evaluating context-aware proactive LLM agents, covering 1,000 samples across nine daily scenarios and twenty tools. Experiments on ContextAgentBench show that ContextAgent outperforms baselines by achieving up to 8.5% and 6.0% higher accuracy in proactive predictions and tool calling, respectively. We hope our research can inspire the development of more advanced, human-centric, proactive AI assistants. The code and dataset are publicly available at https://github.com/openaiotlab/ContextAgent.

cs.AI↗

arXiv2025

TDBench: A Benchmark for Top-Down Image Understanding with Reliability Analysis of Vision-Language Models

Top-down images play an important role in safety-critical settings such as autonomous navigation and aerial surveillance, where they provide holistic spatial information that front-view images cannot capture. Despite this, Vision Language Models (VLMs) are mostly trained and evaluated on front-view benchmarks, leaving their performance in the top-down setting poorly understood. Existing evaluations also overlook a unique property of top-down images: their physical meaning is preserved under rotation. In addition, conventional accuracy metrics can be misleading, since they are often inflated by hallucinations or "lucky guesses", which obscures a model's true reliability and its grounding in visual evidence. To address these issues, we introduce TDBench, a benchmark for top-down image understanding that includes 2000 curated questions for each rotation. We further propose RotationalEval (RE), which measures whether models provide consistent answers across four rotated views of the same scene, and we develop a reliability framework that separates genuine knowledge from chance. Finally, we conduct four case studies targeting underexplored real-world challenges. By combining rigorous evaluation with reliability metrics, TDBench not only benchmarks VLMs in top-down perception but also provides a new perspective on trustworthiness, guiding the development of more robust and grounded AI systems. Project homepage: https://github.com/Columbia-ICSL/TDBench

cs.LG↗

arXiv2025

An LLM-Empowered Low-Resolution Vision System for On-Device Human Behavior Understanding

The rapid advancements in Large Vision Language Models (LVLMs) offer the potential to surpass conventional labeling by generating richer, more detailed descriptions of on-device human behavior understanding (HBU) in low-resolution vision systems, such as depth, thermal, and infrared. However, existing large vision language model (LVLM) approaches are unable to understand low-resolution data well as they are primarily designed for high-resolution data, such as RGB images. A quick fixing approach is to caption a large amount of low-resolution data, but it requires a significant amount of labor-intensive annotation efforts. In this paper, we propose a novel, labor-saving system, Llambda, designed to support low-resolution HBU. The core idea is to leverage limited labeled data and a large amount of unlabeled data to guide LLMs in generating informative captions, which can be combined with raw data to effectively fine-tune LVLM models for understanding low-resolution videos in HBU. First, we propose a Contrastive-Oriented Data Labeler, which can capture behavior-relevant information from long, low-resolution videos and generate high-quality pseudo labels for unlabeled data via contrastive learning. Second, we propose a Physical-Knowledge Guided Captioner, which utilizes spatial and temporal consistency checks to mitigate errors in pseudo labels. Therefore, it can improve LLMs' understanding of sequential data and then generate high-quality video captions. Finally, to ensure on-device deployability, we employ LoRA-based efficient fine-tuning to adapt LVLMs for low-resolution data. We evaluate Llambda using a region-scale real-world testbed and three distinct low-resolution datasets, and the experiments show that Llambda outperforms several state-of-the-art LVLM systems up to $40.03\%$ on average Bert-Score.

cs.CV↗

arXiv2025

Exploring the Capabilities of LLMs for IMU-based Fine-grained Human Activity Understanding

Human activity recognition (HAR) using inertial measurement units (IMUs) increasingly leverages large language models (LLMs), yet existing approaches focus on coarse activities like walking or running. Our preliminary study indicates that pretrained LLMs fail catastrophically on fine-grained HAR tasks such as air-written letter recognition, achieving only near-random guessing accuracy. In this work, we first bridge this gap for flat-surface writing scenarios: by fine-tuning LLMs with a self-collected dataset and few-shot learning, we achieved up to a 129x improvement on 2D data. To extend this to 3D scenarios, we designed an encoder-based pipeline that maps 3D data into 2D equivalents, preserving the spatiotemporal information for robust letter prediction. Our end-to-end pipeline achieves 78% accuracy on word recognition with up to 5 letters in mid-air writing scenarios, establishing LLMs as viable tools for fine-grained HAR.

cs.CV↗

arXiv2025

Visualizing the Invisible: A Generative AR System for Intuitive Multi-Modal Sensor Data Presentation

Understanding sensor data can be difficult for non-experts because of the complexity and different semantic meanings of sensor modalities. This leads to a need for intuitive and effective methods to present sensor information. However, creating intuitive sensor data visualizations presents three key challenges: the variability of sensor readings, gaps in domain comprehension, and the dynamic nature of sensor data. To address these issues, we propose Vivar, a novel system that integrates multi-modal sensor data and presents 3D volumetric content for AR visualization. In particular, we introduce a cross-modal embedding approach that maps sensor data into a pre-trained visual embedding space through barycentric interpolation. This approach accurately reflects value changes in multi-modal sensor information, ensuring that sensor variations are properly shown in visualization outcomes. Vivar also incorporates sensor-aware AR scene generation using foundation models and 3D Gaussian Splatting (3DGS) without requiring domain expertise. In addition, Vivar leverages latent reuse and caching strategies to accelerate 2D and AR content generation, demonstrating 11x latency reduction without compromising quality. A user study involving over 503 participants, including domain experts, demonstrates Vivar's effectiveness in accuracy, consistency, and real-world applicability, paving the way for more intuitive sensor data visualization.

cs.HC↗

arXiv2025

FlexiFly: Interfacing the Physical World with Foundation Models Empowered by Reconfigurable Drone Systems

Foundation models (FM) have shown immense human-like capabilities for generating digital media. However, foundation models that can freely sense, interact, and actuate the physical domain is far from being realized. This is due to 1) requiring dense deployments of sensors to fully cover and analyze large spaces, while 2) events often being localized to small areas, making it difficult for FMs to pinpoint relevant areas of interest relevant to the current task. We propose FlexiFly, a platform that enables FMs to ``zoom in'' and analyze relevant areas with higher granularity to better understand the physical environment and carry out tasks. FlexiFly accomplishes by introducing 1) a novel image segmentation technique that aids in identifying relevant locations and 2) a modular and reconfigurable sensing and actuation drone platform that FMs can actuate to ``zoom in'' with relevant sensors and actuators. We demonstrate through real smart home deployments that FlexiFly enables FMs and LLMs to complete diverse tasks up to $85\%$ more successfully. FlexiFly is critical step towards FMs and LLMs that can naturally interface with the physical world.

cs.RO↗

arXiv2025

Exploring Finetuned Audio-LLM on Heart Murmur Features

Large language models (LLMs) for audio have excelled in recognizing and analyzing human speech, music, and environmental sounds. However, their potential for understanding other types of sounds, particularly biomedical sounds, remains largely underexplored despite significant scientific interest. In this study, we focus on diagnosing cardiovascular diseases using phonocardiograms, i.e., heart sounds. Most existing deep neural network (DNN) paradigms are restricted to heart murmur classification (healthy vs unhealthy) and do not predict other acoustic features of the murmur such as timing, grading, harshness, pitch, and quality, which are important in helping physicians diagnose the underlying heart conditions. We propose to finetune an audio LLM, Qwen2-Audio, on the PhysioNet CirCor DigiScope phonocardiogram (PCG) dataset and evaluate its performance in classifying 11 expert-labeled murmur features. Additionally, we aim to achieve more noise-robust and generalizable system by exploring a preprocessing segmentation algorithm using an audio representation model, SSAMBA. Our results indicate that the LLM-based model outperforms state-of-the-art methods in 8 of the 11 features and performs comparably in the remaining 3. Moreover, the LLM successfully classifies long-tail murmur features with limited training data, a task that all previous methods have failed to classify. These findings underscore the potential of audio LLMs as assistants to human cardiologists in enhancing heart disease diagnosis.

eess.AS↗

arXiv2024

SocialMind: LLM-based Proactive AR Social Assistive System with Human-like Perception for In-situ Live Interactions

Social interactions are fundamental to human life. The recent emergence of large language models (LLMs)-based virtual assistants has demonstrated their potential to revolutionize human interactions and lifestyles. However, existing assistive systems mainly provide reactive services to individual users, rather than offering in-situ assistance during live social interactions with conversational partners. In this study, we introduce SocialMind, the first LLM-based proactive AR social assistive system that provides users with in-situ social assistance. SocialMind employs human-like perception leveraging multi-modal sensors to extract both verbal and nonverbal cues, social factors, and implicit personas, incorporating these social cues into LLM reasoning for social suggestion generation. Additionally, SocialMind employs a multi-tier collaborative generation strategy and proactive update mechanism to display social suggestions on Augmented Reality (AR) glasses, ensuring that suggestions are timely provided to users without disrupting the natural flow of conversation. Evaluations on three public datasets and a user study with 20 participants show that SocialMind achieves 38.3% higher engagement compared to baselines, and 95% of participants are willing to use SocialMind in their live social interactions.

cs.AI↗

arXiv2024

AIRA: A Low-cost IR-based Approach Towards Autonomous Precision Drone Landing and NLOS Indoor Navigation

Automatic drone landing is an important step for achieving fully autonomous drones. Although there are many works that leverage GPS, video, wireless signals, and active acoustic sensing to perform precise landing, autonomous drone landing remains an unsolved challenge for palm-sized microdrones that may not be able to support the high computational requirements of vision, wireless, or active audio sensing. We propose AIRA, a low-cost infrared light-based platform that targets precise and efficient landing of low-resource microdrones. AIRA consists of an infrared light bulb at the landing station along with an energy efficient hardware photodiode (PD) sensing platform at the bottom of the drone. AIRA costs under 83 USD, while achieving comparable performance to existing vision-based methods at a fraction of the energy cost. AIRA requires only three PDs without any complex pattern recognition models to accurately land the drone, under $10$cm of error, from up to $11.1$ meters away, compared to camera-based methods that require recognizing complex markers using high resolution images with a range of only up to $1.2$ meters from the same height. Moreover, we demonstrate that AIRA can accurately guide drones in low light and partial non line of sight scenarios, which are difficult for traditional vision-based approaches.

cs.RO↗