Searcharxiv⌕ Search

arXiv subjects

Haitian Wang

Publications and source records attributed to Haitian Wang.

At least 19 recordsLinked to original sources
arXiv2026

MMLongEmbed: Benchmarking Multimodal Embedding Models in Long-Context Scenarios

Recent advancements have significantly expanded the theoretical context windows of Multimodal Embedding Models (MEMs). However, larger context windows do not necessarily translate into effective comprehension and representation of long-context multimodal inputs, which remains a critical bottleneck for real-world deployment. To address the lack of systematic evaluation in this setting, we introduce MMLongEmbed, the first comprehensive benchmark for evaluating MEMs in long-context scenarios. MMLongEmbed comprises four retrieval tasks spanning multiple context-length ranges, covering text, document, and video modalities. Through extensive evaluation of state-of-the-art models, we find that current architectures rely heavily on superficial feature matching and struggle to capture deep semantic and structural dependencies. We further observe that performance degradation varies systematically with context length and key information placement. Moreover, models exhibit substantially different robustness to redundant contextual information across modalities. For reproducibility, the benchmark and code are publicly available.

cs.CV↗
arXiv2026

P2MFDS: A Privacy-Preserving Multimodal Fall Detection System for Elderly People in Bathroom Environments

By 2050, people aged 65 and over are projected to make up 16% of the global population. As aging is closely associated with increased fall risk, particularly in wet and confined environments such as bathrooms where over 80% of falls occur. Although recent research has increasingly focused on non-intrusive, privacy-preserving approaches that do not rely on wearable devices or video-based monitoring, these efforts have not fully overcome the limitations of existing unimodal systems (e.g., WiFi-, infrared-, or mmWave-based), which are prone to reduced accuracy in complex environments. These limitations stem from fundamental constraints in unimodal sensing, including system bias and environmental interference, such as multipath fading in WiFi-based systems and drastic temperature changes in infrared-based methods. To address these challenges, we propose a Privacy-Preserving Multimodal Fall Detection System for Elderly People in Bathroom Environments. First, we develop a sensor evaluation framework to select and fuse millimeter-wave radar with 3D vibration sensing, and use it to construct and preprocess a large-scale, privacy-preserving multimodal dataset in real bathroom settings, which will be released upon publication. Second, we introduce P2MFDS, a dual-stream network combining a CNN-BiLSTM-Attention branch for radar motion dynamics with a multi-scale CNN-SEBlock-Self-Attention branch for vibration impact detection. By uniting macro- and micro-scale features, P2MFDS delivers significant gains in accuracy and recall over state-of-the-art approaches.

cs.CV↗
arXiv2026

Quantization-Aware Neuromorphic Architecture for Skin Lesion Classification on Resource-Constrained Devices

On-device skin lesion analysis is constrained by the compute and energy cost of conventional CNN inference and by the need for lightweight calibration under clinical data shift. Neuromorphic processors provide event-driven sparse computation, but practical deployment is often limited by CNN-to-SNN conversion failures, including unsupported operators, quantization distortion, and accuracy degradation under class imbalance. We propose QANA, a quantization-aware CNN backbone within an end-to-end pipeline for conversion-stable neuromorphic execution. QANA improves conversion robustness by bounding intermediate activations, aligning normalization with low-bit quantization, and replacing conversion-fragile components with spike-compatible transformations. Efficient representation is achieved through Ghost-based feature generation, spatially-aware efficient channel attention, and squeeze-and-excitation modules whose operations can be quantized, folded, or lowered into integer graph operations. The quantized projection head produces SNN-ready logits and supports lightweight readout calibration without full retraining or data offloading. On HAM10000, QANA achieves 91.6% Top-1 accuracy and 91.0% macro F1, improving the strongest converted SNN baseline by 3.5 points in accuracy and 12.1 points in macro F1. On a clinical dataset, QANA achieves 90.8% Top-1 accuracy and 81.7% macro F1, improving the strongest baseline by 3.2 points in accuracy and 3.6 points in macro F1. On BrainChip Akida, QANA runs in 1.5 ms with 1.7 mJ per image, outperforming the strongest size-matched Akida baseline by 4.1 points in accuracy, 10.0 points in macro F1, 21.1% in latency, and 22.7% in energy.

eess.IV↗
arXiv2026

LiDAR-based 3D Change Detection at City Scale

High-definition 3D city maps enable city planning and change detection, which is essential for municipal compliance, map maintenance, and asset monitoring, including both built structures and urban greenery. Conventional Digital Surface Model (DSM) and image differencing are sensitive to vertical bias and viewpoint mismatch, while original point cloud or voxel models require large memory, assume perfect alignment, and degrade thin structures. We propose an uncertainty-aware, object-centric method for city-scale LiDAR-based change detection. Our method aligns data from different time periods using multi-resolution Normal Distributions Transform (NDT) and a point-to-plane Iterative Closest Point (ICP) method, normalizes elevation, and computes a per-point level of detection from registration covariance and surface roughness to calibrate change decisions. Geometry-based associations are refined by semantic and instance segmentation and optimized using class-constrained bipartite assignment with augmented dummies to handle split-merge cases. Tiled processing bounds memory and preserves narrow ground changes, while instance-level decisions integrate overlap, displacement, and volumetric differences under local detection gating. We perform experiments on the city of Subiaco, Western Australia, using datasets captured in 2023 and 2025. Our method achieves 95.3% accuracy, 90.8% macro F1, and 82.9% macro IoU, improving over the strongest baseline, Triplet KPConv, by 0.3, 0.6, and 1.1 percentage points, respectively.

cs.CV↗
arXiv2026

LoDA: A Level of Detection Aware Method and a Multimodal Sensing Benchmark for Object Level Change Detection

High-definition 3D LiDAR maps are important for autonomous driving and smart-city services, which require reliable detection of object-level changes in multi-temporal urban LiDAR to keep digital maps aligned with the physical world. Existing approaches from raster height differencing to depth image and point-cloud networks often remain tile-based and threshold-driven, yielding per-point scores without explicit detection limits or consistent object-level labels. We propose an object-level 3D change-detection pipeline that integrates detection-limit-aware registration, geometry-driven object proxies with rule-based semantic and instance segmentation, and displacement cues in height, volume, and surface-normal direction to assign five change labels with confidence. By decoupling registration, geometry, and semantics, the pipeline propagates pose uncertainty into spatially varying detection limits, stabilizes cross-epoch correspondences, and suppresses false changes caused by residual misalignment and density variation. We also present LoDA, a level-of-detection (LoD) aware benchmark for the Subiaco district with fused multi-temporal vehicle-LiDAR maps constructed with LiDAR, GNSS, and IMU support, semantic instances, and object-level annotations. On this benchmark, our method achieves 95.0% accuracy, 90.8% macro F1, and 83.0% macro IoU, exceeding the best baseline by 8.7 IoU points and 4.4 F1 points. On the public Urb3DCD-V2 benchmark evaluated under the official point-wise protocol, it reaches 96.81% mean accuracy and 89.52% mean change IoU, improving over the strongest reported baselines by 1.36 points in mAcc and 3.18 points in mIoUch.

cs.CV↗
arXiv2026

Statistical Verification of Medium-Access Parameterization for Power-Grid Edge Ad Hoc Sensor Networks

The widespread deployment of power grid ad hoc sensor networks based on IEEE 802.15.4 raises reliability challenges when nodes selfishly adapt CSMA/CA parameters to maximize individual performance. Such behavior degrades reliability, energy efficiency, and compliance with strict grid constraints. Existing analytical and simulation approaches often fail to rigorously evaluate configurations under asynchronous, event-driven, and resource-limited conditions. We develop a verification framework that integrates stochastic timed hybrid automata with statistical model checking (SMC) with confidence bounds to formally assess CSMA/CA parameterizations under grid workloads. By encoding node- and system-level objectives in temporal logic and automating protocol screening via large-scale statistical evaluation, the method certifies Nash equilibrium strategies that remain robust to unilateral deviations. In a substation-scale scenario, the certified equilibrium improves utility from 0.862 to 0.914 and raises the delivery ratio from 89.5% to 93.2% when compared with an aggressive tuning baseline. Against a delivery-oriented baseline, it reduces mean per-cycle energy from 152.8 mJ to 149.2 mJ while maintaining comparable delivery performance. Certified configurations satisfy latency, reliability, and energy constraints with robustness coefficients above 0.97 and utility above 0.91.

cs.NI↗
arXiv2026

Leakage-Safe Empirical Benchmarking of EEG-Based Machine Learning Pipelines for Dementia Classification

Electroencephalography (EEG) is a low-cost and non-invasive signal source for dementia screening, yet existing EEG-based studies remain difficult to compare because preprocessing, EEG segmentation, feature design, classifier choice, and validation protocols vary across studies and are often evaluated in isolation. This variability limits the derivation of robust pipeline recommendations. This paper presents a leakage-safe empirical benchmark for resting-state EEG-based dementia classification and uses it to identify a practical best-practice pipeline. Using the public OpenNeuro ds004504 dataset, the benchmark evaluates artifact correction, fixed-length EEG segmentation, training-only augmentation, multi-domain feature extraction, fold-internal feature selection, classical machine-learning (ML) classifiers, subject-level aggregation, and interpretation under leave-one-subject-out (LOSO) validation. The best-performing pipeline in this benchmark combines Artifact Subspace Reconstruction (ASR) followed by Independent Component Analysis (ICA), 10 s EEG epochs with training-only amplitude scaling and Gaussian-noise augmentation, spectral, complexity, and pairwise connectivity features, mutual-information top-100 selection, linear support vector machine classification, and mean-probability aggregation. It achieves 87.69 percent accuracy, 88.89 percent F1-score, and 91.20 percent AUC on Alzheimer disease (AD) versus cognitively normal controls (CN) classification while retaining 100 features from 1596 raw descriptors. The results support compact multi-domain EEG features as an interpretable and leakage-safe baseline for subject-level dementia classification.

eess.SP↗
arXiv2026

Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference

The quadratic computational complexity of standard attention mechanisms presents a severe scalability bottleneck for LLMs in long-context scenarios. While hybrid attention mechanisms combining Full Attention (FA) and Sparse Attention (SA) offer a potential solution, existing methods typically rely on static allocation ratios that fail to accommodate the variable retrieval demands of different tasks. Furthermore, head-level dynamic sparsity often introduces severe computational load imbalance and synchronization long-tails, which hinder hardware acceleration during autoregressive decoding. To bridge this gap, we introduce Flux Attention, a context-aware framework that dynamically optimizes attention computation at the layer level. By integrating a lightweight Layer Router into frozen pretrained LLMs, the proposed method adaptively routes each layer to FA or SA based on the input context. This layer-wise routing preserves high-fidelity information retrieval while ensuring contiguous memory access, translating theoretical computational reductions into practical wall-clock speedups. As a parameter-efficient approach, our framework requires only 12 hours of training on 8$\times$A800 GPUs. Extensive experiments across multiple long-context and mathematical reasoning benchmarks demonstrate that Flux Attention achieves a superior trade-off between performance and inference speed compared with baseline models, with speed improvements of up to $2.8\times$ and $2.0\times$ in the prefill and decode stages.

cs.LG↗
arXiv2026

Edge-Efficient Two-Stream Multimodal Architecture for Non-Intrusive Bathroom Fall Detection

Falls in wet bathroom environments are a major safety risk for seniors living alone. Recent work has shown that mmWave-only, vibration-only, and existing multimodal schemes, such as vibration-triggered radar activation, early feature concatenation, and decision-level score fusion, can support privacy-preserving, non-intrusive fall detection. However, these designs still treat motion and impact as loosely coupled streams, depending on coarse temporal alignment and amplitude thresholds, and do not explicitly encode the causal link between radar-observed collapse and floor impact or address timing drift, object drop confounders, and latency and energy constraints on low-power edge devices. To this end, we propose a two-stream architecture that encodes radar signals with a Motion--Mamba branch for long-range motion patterns and processes floor vibration with an Impact--Griffin branch that emphasizes impact transients and cross-axis coupling. Cross-conditioned fusion uses low-rank bilinear interaction and a Switch--MoE head to align motion and impact tokens and suppress object-drop confounders. The model keeps inference cost suitable for real-time execution on a Raspberry Pi 4B gateway. We construct a bathroom fall detection benchmark dataset with frame-level annotations, comprising more than 3~h of synchronized mmWave radar and triaxial vibration recordings across eight scenarios under running water, together with subject-independent training, validation, and test splits. On the test split, our model attains 96.1% accuracy, 94.8% precision, 88.0% recall, a 91.1% macro F1 score, and an AUC of 0.968. Compared with the strongest baseline, it improves accuracy by 2.0 percentage points and fall recall by 1.3 percentage points, while reducing latency from 35.9 ms to 15.8 ms and lowering energy per 2.56 s window from 14200 mJ to 10750 mJ on the Raspberry Pi 4B gateway.

cs.CV↗
arXiv2026

BAWSeg: A UAV Multispectral Benchmark for Barley Weed Segmentation

Accurate weed mapping in cereal fields requires pixel-level segmentation from UAV imagery that remains reliable across fields, seasons, and illumination. Existing multispectral pipelines often depend on thresholded vegetation indices, which are brittle under radiometric drift and mixed crop--weed pixels, or on single-stream CNN and Transformer backbones that ingest stacked bands and indices, where radiance cues and normalized index cues interfere and reduce sensitivity to small weed clusters embedded in crop canopy. We propose VISA, a two-stream segmentation network that decouples these cues and fuses them at native resolution. The radiance stream learns from calibrated five-band reflectance using local residual convolutions, channel recalibration, spatial gating, and skip-connected decoding, which preserve fine textures, row boundaries, and small weed structures that are often weakened after ratio-based index compression. The index stream operates on vegetation-index maps with windowed self-attention to model local structure efficiently, state-space layers to propagate field-scale context without quadratic attention cost, and Slot Attention to form stable region descriptors that improve discrimination of sparse weeds under canopy mixing. To support supervised training and deployment-oriented evaluation, we introduce BAWSeg, a four-year UAV multispectral dataset collected over commercial barley paddocks in Western Australia, providing radiometrically calibrated blue, green, red, red edge, and near-infrared orthomosaics, derived vegetation indices, and dense crop, weed, and other labels with leakage-free block splits. On BAWSeg, VISA achieves 75.6% mIoU and 63.5% weed IoU with 22.8 M parameters, outperforming a multispectral SegFormer-B1 baseline by 1.2 mIoU and 1.9 weed IoU. Under cross-plot and cross-year protocols, VISA maintains 71.2% and 69.2% mIoU, respectively.

cs.CV↗
arXiv2026

LiDAR, GNSS and IMU Sensor Fine Alignment through Dynamic Time Warping to Construct 3D City Maps

LiDAR-based 3D mapping suffers from cumulative drift causing global misalignment, particularly in GNSS-constrained environments. To address this, we propose a unified framework that fuses LiDAR, GNSS, and IMU data for high-resolution city-scale mapping. The method performs velocity-based temporal alignment using Dynamic Time Warping and refines GNSS and IMU signals via extended Kalman filtering. Local maps are built using Normal Distributions Transform-based registration and pose graph optimization with loop closure detection, while global consistency is enforced using GNSS-constrained anchors followed by fine registration of overlapping segments. We also introduce a large-scale multimodal dataset captured in Perth, Western Australia to facilitate future research in this direction. Our dataset comprises 144,000 frames acquired with a 128-channel Ouster LiDAR, synchronized RTK-GNSS trajectories, and MEMS-IMU measurements across 21 urban loops. To assess geometric consistency, we evaluated our method using alignment metrics based on road centerlines and intersections to capture both global and local accuracy. The proposed framework reduces the average global alignment error from 3.32m to 1.24m, achieving a 61.4% improvement, and significantly decreases the intersection centroid offset from 13.22m to 2.01m, corresponding to an 84.8% enhancement. The constructed high-fidelity map and raw dataset are publicly available through https://ieee-dataport.org/documents/perth-cbd-high-resolution-lidar-map-gnss-and-imu-calibration, and its visualization can be viewed at https://www.youtube.com/watch?v=-ZUgs1KyMks. The source code is available at https://github.com/HaitianWang/LiDAR-GNSS-and-IMU-Sensor-Fine-Alignment-through-Dynamic-Time-Warping-to-Construct-3D-City-Maps. This dataset and method together establish a new benchmark for evaluating 3D city mapping in GNSS-constrained environments.

cs.RO↗
arXiv2026

Universal Bound States with Bose-Fermi Duality in Microwave-Shielded Polar Molecules

We report universal bound states of microwave-shielded ultracold molecules that solely depend on the strengths of long-range dipolar interaction and microwave coupling. Under a highly elliptic microwave field, few-molecule scatterings in three dimension are shown to be governed by effective one-dimensional (1D) models, which well reproduce the tetratomic bound state and the Born-Oppenheimer potential in three-molecule sector. For hexatomic systems comprising three identical molecules, we find much deeper bound state than the tetratomic one, with binding energy exceeding twice of the latter. Strikingly, these bound states display Bose-Fermi duality as facilitated by the effective 1D scattering with a large repulsive core from angular fluctuations. For large molecule ensembles, our results suggest the formation of elongated self-bound droplets with crystalline patterns in both bosonic and fermionic molecules.

cond-mat.quant-gas↗
arXiv2026

MemoryRewardBench: Benchmarking Reward Models for Long-Term Memory Management in Large Language Models

Existing works increasingly adopt memory-centric mechanisms to process long contexts in a segment manner, and effective memory management is one of the key capabilities that enables large language models to effectively propagate information across the entire sequence. Therefore, leveraging reward models (RMs) to automatically and reliably evaluate memory quality is critical. In this work, we introduce MemoryRewardBench, the first benchmark to systematically study the ability of RMs to evaluate long-term memory management processes. MemoryRewardBench covers both long-context comprehension and long-form generation tasks, featuring 10 distinct settings with different memory management patterns, with context length ranging from 8K to 128K tokens. Evaluations on 13 cutting-edge RMs indicate a diminishing performance gap between open-source and proprietary models, with newer-generation models consistently outperforming their predecessors regardless of parameter count. We further expose the capabilities and fundamental limitations of current RMs in evaluating LLM memory management across diverse settings.

cs.CL↗
arXiv2026

Geo-Registration of Terrestrial LiDAR Point Clouds with Satellite Images without GNSS

Accurate geo-registration of LiDAR point clouds remains a significant challenge in urban environments where Global Navigation Satellite System (GNSS) signals are denied or degraded. Existing methods typically rely on real-time GNSS and Inertial Measurement Unit (IMU) data, which require pre-calibration and assume stable signals. However, this assumption often fails in dense cities, resulting in localization errors. To address this, we propose a structured post-hoc geo-registration method that accurately aligns LiDAR point clouds with satellite images. The proposed approach targets point cloud datasets where reliable GNSS information is unavailable or degraded, enabling city-scale geo-registration as a post-processing solution. Our method uses a pre-trained Point Transformer to segment road points, then extracts road skeletons and intersections from the point cloud and the satellite image. Global alignment is achieved through rigid transformation using corresponding intersection points, followed by local non-rigid refinement with radial basis function (RBF) interpolation. Elevation discrepancies are corrected using terrain data from the Shuttle Radar Topography Mission (SRTM). To evaluate geo-registration accuracy, we measure the absolute distances between the roads extracted from the two modalities. Our method is validated on the KITTI benchmark and a newly collected dataset of Perth, Western Australia. On KITTI, our method achieves a mean planimetric alignment error of 0.69m, corresponding to a 50% reduction in global geo-registration bias compared to the raw KITTI annotations. On Perth dataset, it achieves a mean planimetric error of 2.17m from GNSS values extracted from Google Maps, corresponding to 57.4% improvement over rigid alignment. Elevation correlation factor improved by 30.5% (KITTI) and 55.8% (Perth).

cs.CV↗
arXiv2025

Comparing State-Representations for DEL Model Checking

Model checking with the standard Kripke models used in (Dynamic) Epistemic Logic leads to scalability issues. Hence alternative representations have been developed, in particular symbolic structures based on Binary Decision Diagrams (BDDs) and succinct models based on mental programs. While symbolic structures have been shown to perform well in practice, their theoretical complexity was not known so far. On the other hand, for succinct models model checking is known to be PSPACE-complete, but no implementations are available. We close this gap and directly relate the two representations. We show that model checking DEL on symbolic structures encoded with BDDs is also PSPACE-complete. In fact, already model checking Epistemic Logic without dynamics is PSPACE-complete on symbolic structures. We also provide direct translations between BDDs and mental programs. Both translations yield exponential outputs. For the translation from mental programs to BDDs we show that no small translation exists. For the other direction we conjecture the same.

cs.LO↗
arXiv2025

Interaction-induced Dimension Reduction for Bound States in Microwave-Shielded Ultracold Molecules

We investigate tetratomic and hexatomic bound states of ultracold molecules dressed by an elliptic microwave field. We show that these bound states can be accurately described by effective one-dimensional (1D) models incorporating high-order angular fluctuations, despite the physical system is in three-dimensional (3D) free space. By comparing with exact solutions of the full 3D system, we identify the validity region of such 1D description in the parameter plane of ellipticity and coupling strength of microwave field. The hard-core character of these effective models enables a duality between bosonic and fermionic molecules in real and spectral space, while their momentum distributions remain distinct. Our results have demonstrated an effective dimension reduction in microwave-shielded molecular systems, which is purely due to the intrinsic interaction anisotropy rather than any external confinement. Extending to large systems, our results suggest a self-bound single-molecule array as the ground state of both bosonic and fermionic molecular gases.

cond-mat.quant-gas↗
arXiv2025

LongRM: Revealing and Unlocking the Context Boundary of Reward Modeling

Reward model (RM) plays a pivotal role in aligning large language model (LLM) with human preferences. As real-world applications increasingly involve long history trajectories, e.g., LLM agent, it becomes indispensable to evaluate whether a model's responses are not only high-quality but also grounded in and consistent with the provided context. Yet, current RMs remain confined to short-context settings and primarily focus on response-level attributes (e.g., safety or helpfulness), while largely neglecting the critical dimension of long context-response consistency. In this work, we introduce Long-RewardBench, a benchmark specifically designed for long-context RM evaluation, featuring both Pairwise Comparison and Best-of-N tasks. Our preliminary study reveals that even state-of-the-art generative RMs exhibit significant fragility in long-context scenarios, failing to maintain context-aware preference judgments. Motivated by the analysis of failure patterns observed in model outputs, we propose a general multi-stage training strategy that effectively scales arbitrary models into robust Long-context RMs (LongRMs). Experiments show that our approach not only substantially improves performance on long-context evaluation but also preserves strong short-context capability. Notably, our 8B LongRM outperforms much larger 70B-scale baselines and matches the performance of the proprietary Gemini 2.5 Pro model.

cs.CL↗
arXiv2025

High-Performance Parallel Optimization of the Fish School Behaviour on the Setonix Platform Using OpenMP

This paper presents an in-depth investigation into the high-performance parallel optimization of the Fish School Behaviour (FSB) algorithm on the Setonix supercomputing platform using the OpenMP framework. Given the increasing demand for enhanced computational capabilities for complex, large-scale calculations across diverse domains, there's an imperative need for optimized parallel algorithms and computing structures. The FSB algorithm, inspired by nature's social behavior patterns, provides an ideal platform for parallelization due to its iterative and computationally intensive nature. This study leverages the capabilities of the Setonix platform and the OpenMP framework to analyze various aspects of multi-threading, such as thread counts, scheduling strategies, and OpenMP constructs, aiming to discern patterns and strategies that can elevate program performance. Experiments were designed to rigorously test different configurations, and our results not only offer insights for parallel optimization of FSB on Setonix but also provide valuable references for other parallel computational research using OpenMP. Looking forward, other factors, such as cache behavior and thread scheduling strategies at micro and macro levels, hold potential for further exploration and optimization.

cs.DC↗