arXiv subjects

Jing Hu

Publications and source records attributed to Jing Hu.

At least 19 recordsLinked to original sources

arXiv2026

More Perspectives, Stronger Signals: Multi-Perspective Enhancement and Progressive Fusion for Multimodal Entity Representation Learning

Learning effective multimodal entity representations is fundamental for reasoning tasks such as multimodal knowledge graph completion (MMKGC). However, existing methods often suffer from semantic over-smoothing within modalities and ineffective noise filtration across modalities, particularly under sparse or ambiguous conditions. To overcome these limitations, we propose PrismF, a unified framework that synergizes multi-perspective enhancement with progressive fusion to extract stronger signals from diverse inputs. PrismF enhances fine-grained intra-modal semantics through a multi-perspective mechanism that decomposes each modality into complementary views and constrains them with a decoupling loss to reduce representation collapse. Furthermore, it improves cross-modal integration through a progressive fusion strategy that dynamically calibrates inter-modal interactions, enabling the model to emphasize informative signals while suppressing noisy or unreliable ones. Extensive experiments on three public benchmarks show that PrismF achieves the strongest overall performance, including relative improvements of 4.04% in MRR and 11.17% in Hits@1 on KVC16K. Our code can be found at https://github.com/HubuKG/PrismF.

cs.AI↗

arXiv2026

Singular and nearly singular quadrature in arbitrary dimensions

The accurate numerical evaluation of integrals with singular or nearly singular kernels remains a fundamental challenge in scientific computing, particularly as the spatial dimension increases. While existing approaches, including singularity extraction, adaptive element subdivision, and analytical integration schemes, have achieved considerable success in one and two dimensions, their extension to higher dimensions is often hindered by severe near-singular behaviour and the resulting numerical instabilities. In this work, we propose a systematic approach for the high-accuracy evaluation of singular integrals and nearly singular integrals in arbitrary dimensions, based on variable transformation techniques derived from the Gauss hypergeometric function. We further analyze the structure of singularities and near-singularities in both the Duffy domain and the physical Cartesian domain, and establish a unified treatment via the sinh transformation. A convergence analysis based on the Bernstein ellipse parameter reveals that the sinh transformation ($\beta=1$) consistently outperforms alternative hypergeometric transformations ($\beta=2,3$), which introduce secondary near-singularities despite achieving formal cancellation. Numerical experiments in dimensions two through five, together with an analysis of quadrature-induced consistency errors in variational discretisations, demonstrate that the proposed approach achieves exponential convergence and substantially outperforms direct Gauss--Legendre quadrature. The method offers a practical and theoretically grounded framework for high-dimensional nearly singular integration with broad applicability in scientific computing.

cs.CE↗

arXiv2026

AbICL: In-Context Learning for Antigen-Specific Antibody Affinity Ranking

Accurate ranking of antibody candidates according to their binding affinity is essential for therapeutic antibody discovery. However, existing methods treat affinity comparisons independently and ignore the contextual information encoded in other labeled comparisons, limiting their ability to capture antigen-specific binding landscapes. For many target antigens, a small number of experimentally characterized affinity comparisons are often available. An important question is whether the model can exploit these existing comparisons to infer antigen-specific ranking patterns that facilitate subsequent affinity ranking. This form of learning from labeled demonstrations closely resembles the paradigm of In-Context Learning, motivating us to revisit antibody affinity ranking from an ICL perspective. To this end, we propose AbICL, an ICL framework for antigen-specific antibody affinity ranking. AbICL combines a pretrained structural encoder with a context ranking head and is trained with an episodic meta-training strategy that enables the model to leverage support demonstrations for test-time adaptation without gradient updates. Experiments on the AbRank benchmark demonstrate that AbICL consistently outperforms existing ranking baselines across almost all data splits and evaluation benchmarks. Further analysis shows that the value of contextual demonstrations depends on how well they match the target inference task, and becomes increasingly pronounced under distribution shift and fine-grained affinity discrimination. These findings highlight the potential of ICL as an effective paradigm for antigen-specific antibody affinity ranking, particularly in challenging settings where a single global ranking function is insufficient.

cs.LG↗

arXiv2026

YouZhi: Towards High-Concurrency Financial LLMs via Adaptive GQA-to-MLA Transition

Large language models (LLMs) drive significant financial innovations, yet their high-concurrency deployment is severely bottlenecked by KV cache memory overhead, which inflates infrastructure costs and throttles scalability. To address this, we propose YouZhi-LLM, a highly efficient financial LLM empowered by a comprehensive structural transition and training pipeline natively built on the Huawei Ascend ecosystem. At its algorithmic core, YouZhi-LLM features a layer-adaptive GQA-to-MLA transition framework that dynamically assigns per-layer FreqFold sizes, maximizing KV-cache compression while minimizing perplexity degradation. To recover representation capacity and inject domain expertise, the Ascend-based training pipeline seamlessly integrates generalized knowledge distillation with financial-specific supervised fine-tuning. Evaluations demonstrate the superiority of this systematic approach, with the adaptive transition reducing perplexity degradation by up to 35% over uniform baselines. Crucially, when evaluated on Ascend NPUs via vLLM-Ascend, the massive KV-cache reduction translates directly into deployment efficiency. Compared to their respective base models, YouZhi-7B yields a 12.3% improvement in average financial benchmark score alongside a 2.69$\times$ increase in maximum concurrency; similarly, YouZhi-14B achieves a 7.0% accuracy gain and a 2.43$\times$ concurrency boost, establishing a new paradigm for cost-effective, high-throughput financial inference.

cs.CL↗

arXiv2026

HyFrac.fun: A 3D Hydraulic Fracturing Simulator on Cloud

When multiple hydraulic fractures propagate simultaneously from a horizontal wellbore, elastic stress-shadow interactions generate complex non-planar three-dimensional geometries whose effect on subsequent reservoir drainage has infrequently been quantified, because the propagation and production solvers have historically been incompatible stand-alone tools. This paper presents HyFrac.fun, a cloud-native platform that bridges this gap by exploiting a structural isomorphism between the two SGBEM--FEM governing operator systems. The platform enables automated zero-conversion handoff of the evolved 3D fracture mesh directly to the steady-state Darcy production solver for realizing a fully integrated lifecycle simulation of multi-stage non-planar hydraulic fractures. The lifecycle analysis reveals a double shadow phenomenon: the mechanical stress shadow that suppresses inner-fracture growth during stimulation mirrors a fluid pressure shadow that reduces the inner fracture's drawout rate at small cluster spacing. Critically, switching to a shear-thinning power-law fracturing fluid leaves the fracture trajectories and production rates almost unchanged, demonstrating that stress-shadow-controlled fracture geometry instead of fluid rheology is the primary determinant of long-term production efficiency at equal injection rates. These physics findings are accessible from integrated fracture propagation and production simulations.

cs.CE↗

arXiv2026

High-speed hyperspectral 3D ghost imaging LiDAR

Light detection and ranging (LiDAR) is widely used in autonomous systems and industrial metrology; however, the simultaneous acquisition of three-dimensional (3D) structure and broadband spectral information remains challenging, as conventional hyperspectral LiDAR relies on wavelength-scanning or spectrometer-based detection that limits speed. Here, we demonstrate a hyperspectral 3D ghost imaging LiDAR that eliminates these bottlenecks. By combining a stochastic broadband laser with single-pixel detection, and integrating spatiotemporal encoding with spectral ghost imaging in a time-of-flight framework, the system enables pulse-resolved recovery of spatial and spectral information. Consequently, we achieve a line-scanning rate of 60.5 MHz (point rate 1.8 GHz) and a ranging precision of 0.02 mm within a 10 {\mu}s integration time. Each voxel contains a 1.4 nm resolution spectrum over 1100-1250 nm, enabling simultaneous 3D imaging and chemical identification. This approach provides a route to high-speed hyperspectral LiDAR for environmental monitoring, precision agriculture, and industrial inspection.

physics.optics↗

arXiv2026

The Eleventh NTIRE 2026 Efficient Super-Resolution Challenge Report

This paper reviews the NTIRE 2026 challenge on efficient single-image super-resolution with a focus on the proposed solutions and results. The aim of this challenge is to devise a network that reduces one or several aspects, such as runtime, parameters, and FLOPs, while maintaining PSNR of around 26.90 dB on the DIV2K_LSDIR_valid dataset, and 26.99 dB on the DIV2K_LSDIR_test dataset. The challenge had 95 registered participants, and 15 teams made valid submissions. They gauge the state-of-the-art results for efficient single-image super-resolution.

cs.CV↗

arXiv2026

VADMamba++: Efficient Video Anomaly Detection via Hybrid Modeling in Grayscale Space

VADMamba pioneered the introduction of Mamba to Video Anomaly Detection (VAD), achieving high accuracy and fast inference through hybrid proxy tasks. Nevertheless, its heavy reliance on optical flow as auxiliary input and inter-task fusion scoring constrains its applicability to a single proxy task. In this paper, we introduce VADMamba++, an efficient VAD method based on the Gray-to-RGB paradigm that enforces a Single-Channel to Three-Channel reconstruction mapping, designed for a single proxy task and operating without auxiliary inputs. This paradigm compels inferring color appearances from grayscale structures, allowing anomalies to be more effectively revealed through dual inconsistencies between structure and chromatic cues. Specifically, VADMamba++ reconstructs grayscale frames into the RGB space to simultaneously discriminate structural geometry and chromatic fidelity, thereby enhancing sensitivity to explicit visual anomalies. We further design a hybrid modeling backbone that integrates Mamba, CNN, and Transformer modules to capture diverse normal patterns while suppressing the appearance of anomalies. Furthermore, an intra-task fusion scoring strategy integrates explicit future-frame prediction errors with implicit quantized feature errors, further improving accuracy under a single task setting. Extensive experiments on three benchmark datasets demonstrate that VADMamba++ outperforms state-of-the-art methods while meeting performance and efficiency, especially under a strict single-task setting with only frame-level inputs.

cs.CV↗

arXiv2026

Eureka-Audio: Triggering Audio Intelligence in Compact Language Models

We present Eureka-Audio, a compact yet high-performance audio language model that achieves competitive performance against models that are 4 to 18 times larger across a broad range of audio understanding benchmarks. Despite containing only 1.7B parameters, Eureka-Audio demonstrates strong performance on automatic speech recognition (ASR), audio understanding, and dense audio captioning, matching or surpassing multiple 7B to 30B audio and omni-modal baselines. The model adopts a unified end-to-end architecture composed of a lightweight language backbone, a Whisper-based audio encoder, and a sparsely activated Mixture-of-Experts (MoE) adapter that explicitly accounts for audio heterogeneity and alleviates cross-modal optimization conflicts under limited capacity. To further enhance paralinguistic reasoning, we introduce DataFlux, a closed loop audio instruction data synthesis and verification pipeline that constructs high quality, logically consistent supervision from raw audio. Extensive evaluations across ASR, knowledge reasoning, safety, instruction following, and paralinguistic benchmarks, demonstrate that Eureka-Audio achieves an efficient balance between computational cost and performance. These results establish Eureka Audio as a strong and practical baseline for lightweight audio understanding models.

cs.SD↗

arXiv2026

Forward Consistency Learning with Gated Context Aggregation for Video Anomaly Detection

As a crucial element of public security, video anomaly detection (VAD) aims to measure deviations from normal patterns for various events in real-time surveillance systems. However, most existing VAD methods rely on large-scale models to pursue extreme accuracy, limiting their feasibility on resource-limited edge devices. Moreover, mainstream prediction-based VAD detects anomalies using only single-frame future prediction errors, overlooking the richer constraints from longer-term temporal forward information. In this paper, we introduce FoGA, a lightweight VAD model that performs Forward consistency learning with Gated context Aggregation, containing about 2M parameters and tailored for potential edge devices. Specifically, we propose a Unet-based method that performs feature extraction on consecutive frames to generate both immediate and forward predictions. Then, we introduce a gated context aggregation module into the skip connections to dynamically fuse encoder and decoder features at the same spatial scale. Finally, the model is jointly optimized with a novel forward consistency loss, and a hybrid anomaly measurement strategy is adopted to integrate errors from both immediate and forward frames for more accurate detection. Extensive experiments demonstrate the effectiveness of the proposed method, which substantially outperforms state-of-the-art competing methods, running up to 155 FPS. Hence, our FoGA achieves an excellent trade-off between performance and the efficiency metric.

cs.CV↗

arXiv2026

CORD: Bridging the Audio-Text Reasoning Gap via Weighted On-policy Cross-modal Distillation

Large Audio Language Models (LALMs) have garnered significant research interest. Despite being built upon text-based large language models (LLMs), LALMs frequently exhibit a degradation in knowledge and reasoning capabilities. We hypothesize that this limitation stems from the failure of current training paradigms to effectively bridge the acoustic-semantic gap within the feature representation space. To address this challenge, we propose CORD, a unified alignment framework that performs online cross-modal self-distillation. Specifically, it aligns audio-conditioned reasoning with its text-conditioned counterpart within a unified model. Leveraging the text modality as an internal teacher, CORD performs multi-granularity alignment throughout the audio rollout process. At the token level, it employs on-policy reverse KL divergence with importance-aware weighting to prioritize early and semantically critical tokens. At the sequence level, CORD introduces a judge-based global reward to optimize complete reasoning trajectories via Group Relative Policy Optimization (GRPO). Empirical results across multiple benchmarks demonstrate that CORD consistently enhances audio-conditioned reasoning and substantially bridges the audio-text performance gap with only 80k synthetic training samples, validating the efficacy and data efficiency of our on-policy, multi-level cross-modal alignment approach.

cs.SD↗

arXiv2026

MoE Adapter for Large Audio Language Models: Sparsity, Disentanglement, and Gradient-Conflict-Free

Extending the input modality of Large Language Models~(LLMs) to the audio domain is essential for achieving comprehensive multimodal perception. However, it is well-known that acoustic information is intrinsically \textit{heterogeneous}, entangling attributes such as speech, music, and environmental context. Existing research is limited to a dense, parameter-shared adapter to model these diverse patterns, which induces \textit{gradient conflict} during optimization, as parameter updates required for distinct attributes contradict each other. To address this limitation, we introduce the \textit{\textbf{MoE-Adapter}}, a sparse Mixture-of-Experts~(MoE) architecture designed to decouple acoustic information. Specifically, it employs a dynamic gating mechanism that routes audio tokens to specialized experts capturing complementary feature subspaces while retaining shared experts for global context, thereby mitigating gradient conflicts and enabling fine-grained feature learning. Comprehensive experiments show that the MoE-Adapter achieves superior performance on both audio semantic and paralinguistic tasks, consistently outperforming dense linear baselines with comparable computational costs. Furthermore, we will release the related code and models to facilitate future research.

cs.SD↗

arXiv2025

Exploring the changes in brain network SC-FC coupling patterns of partial sleep deprivation based on DTI-fMRI fusion analysis

Sleep disorder is a serious global public health issue, with cognitive-emotional dysfunction being a core symptom. The analysis of multimodal MRI data provides an effective method for detecting sleep deprivation-induced neural network abnormalities. The structure-function coupling (SC-FC) integrates functional connectivity with white matter structural information, which can enable comprehensive detection of brain network abnormalities and offer quantitative measures of sleep deprivation-induced neural damage. This study integrates diffusion tensor imaging (DTI) and resting-state fMRI (rs-fMRI) to systematically investigate brain network reorganization and their relationship with emotional functions in partial sleep deprivation (PSD). Our methodology employed DTI to construct structural connectivity (SC) networks and rs-fMRI to establish functional connectivity (FC) networks, then construct SC-FC coupling model . The experiment included 16 healthy controls (HC) and 20 PSD patients, with comprehensive whole-brain and nodal-level SC-FC analyses performed. The results show that (1) severe FC disruptions in PSD patients involving the limbic system, default mode network, sensorimotor network, and visual networks; (2) altered SC in default mode, sensorimotor, visual, language, and auditory networks; (3) significant SC-FC decoupling in these networks; and (4) strong correlations between these neural changes and clinical measures (KSQ and HADS scores). The SC-FC coupling approach achieved comprehensive detection of PSD-related network abnormalities. Compared to single-modal approaches, this integrated SC-FC analysis provides more comprehensive biomarkers for sleep-related emotional dysregulation. This innovative multimodal neuroimaging approach elucidates the neural mechanisms of SC-FC imbalance induced by PSD, establishing novel biomarkers for sleep-mediated emotional dysregulation.

q-bio.NC↗

arXiv2025

DAGLFNet: Deep Feature Attention Guided Global and Local Feature Fusion for Pseudo-Image Point Cloud Segmentation

Environmental perception systems are crucial for high-precision mapping and autonomous navigation, with LiDAR serving as a core sensor providing accurate 3D point cloud data. Efficiently processing unstructured point clouds while extracting structured semantic information remains a significant challenge. In recent years, numerous pseudo-image-based representation methods have emerged to balance efficiency and performance by fusing 3D point clouds with 2D grids. However, the fundamental inconsistency between the pseudo-image representation and the original 3D information critically undermines 2D-3D feature fusion, posing a primary obstacle for coherent information fusion and leading to poor feature discriminability. This work proposes DAGLFNet, a pseudo-image-based semantic segmentation framework designed to extract discriminative features. It incorporates three key components: first, a Global-Local Feature Fusion Encoding (GL-FFE) module to enhance intra-set local feature correlation and capture global contextual information; second, a Multi-Branch Feature Extraction (MB-FE) network to capture richer neighborhood information and improve the discriminability of contour features; and third, a Feature Fusion via Deep Feature-guided Attention (FFDFA) mechanism to refine cross-channel feature fusion precision. Experimental evaluations demonstrate that DAGLFNet achieves mean Intersection-over-Union (mIoU) scores of 69.9% and 78.7% on the validation sets of SemanticKITTI and nuScenes, respectively. The method achieves an excellent balance between accuracy and efficiency.

cs.CV↗

arXiv2025

Self-Enhanced Image Clustering with Cross-Modal Semantic Consistency

While large language-image pre-trained models like CLIP offer powerful generic features for image clustering, existing methods typically freeze the encoder. This creates a fundamental mismatch between the model's task-agnostic representations and the demands of a specific clustering task, imposing a ceiling on performance. To break this ceiling, we propose a self-enhanced framework based on cross-modal semantic consistency for efficient image clustering. Our framework first builds a strong foundation via Cross-Modal Semantic Consistency and then specializes the encoder through Self-Enhancement. In the first stage, we focus on Cross-Modal Semantic Consistency. By mining consistency between generated image-text pairs at the instance, cluster assignment, and cluster center levels, we train lightweight clustering heads to align with the rich semantics of the pre-trained model. This alignment process is bolstered by a novel method for generating higher-quality cluster centers and a dynamic balancing regularizer to ensure well-distributed assignments. In the second stage, we introduce a Self-Enhanced fine-tuning strategy. The well-aligned model from the first stage acts as a reliable pseudo-label generator. These self-generated supervisory signals are then used to feed back the efficient, joint optimization of the vision encoder and clustering heads, unlocking their full potential. Extensive experiments on six mainstream datasets show that our method outperforms existing deep clustering methods by significant margins. Notably, our ViT-B/32 model already matches or even surpasses the accuracy of state-of-the-art methods built upon the far larger ViT-L/14.

cs.CV↗

arXiv2025

SRMambaV2: Biomimetic Attention for Sparse Point Cloud Upsampling in Autonomous Driving

Upsampling LiDAR point clouds in autonomous driving scenarios remains a significant challenge due to the inherent sparsity and complex 3D structures of the data. Recent studies have attempted to address this problem by converting the complex 3D spatial scenes into 2D image super-resolution tasks. However, due to the sparse and blurry feature representation of range images, accurately reconstructing detailed and complex spatial topologies remains a major difficulty. To tackle this, we propose a novel sparse point cloud upsampling method named SRMambaV2, which enhances the upsampling accuracy in long-range sparse regions while preserving the overall geometric reconstruction quality. Specifically, inspired by human driver visual perception, we design a biomimetic 2D selective scanning self-attention (2DSSA) mechanism to model the feature distribution in distant sparse areas. Meanwhile, we introduce a dual-branch network architecture to enhance the representation of sparse features. In addition, we introduce a progressive adaptive loss (PAL) function to further refine the reconstruction of fine-grained details during the upsampling process. Experimental results demonstrate that SRMambaV2 achieves superior performance in both qualitative and quantitative evaluations, highlighting its effectiveness and practical value in automotive sparse point cloud upsampling tasks.

cs.CV↗

arXiv2025

Broadband coherent Raman spectroscopy based on single-pulse spectral-domain ghost imaging

Broadband coherent anti-Stokes Raman scattering (CARS) spectroscopy plays a vital role in chemical sensing and label-free vibrational imaging, yet conventional methods suffer from limited acquisition speeds and complex detection schemes. Here, we demonstrate high-speed broadband CARS enabled by nonlinear spectral ghost imaging combined with time-stretch dispersive Fourier-transform spectroscopy (TS-DFT). We exploit modulation instability to generate a stochastic supercontinuum as the Stokes source and a synchronized narrowband pulse as the pump. Reference Stokes spectra are captured at 60.5 MHz via TS-DFT, while anti-Stokes signals are detected using a single non-spectrally resolving photodetector. Correlating these signals enables broadband CARS spectral reconstruction across the fingerprint (600-1600 cm-1) and C-H stretching (2600-3400 cm-1) regions with 13 cm-1 resolution and microsecond-scale acquisition times. Our method enables robust signal recovery without the need for spectral resolution in the detection path, facilitating measurements in complex biological and chemical environments.

physics.optics↗

arXiv2025

HelixDesign-Antibody: A Scalable Production-Grade Platform for Antibody Design Built on HelixFold3

Antibody engineering is essential for developing therapeutics and advancing biomedical research. Traditional discovery methods often rely on time-consuming and resource-intensive experimental screening. To enhance and streamline this process, we introduce a production-grade, high-throughput platform built on HelixFold3, HelixDesign-Antibody, which utilizes the high-accuracy structure prediction model, HelixFold3. The platform facilitates the large-scale generation of antibody candidate sequences and evaluates their interaction with antigens. Integrated high-performance computing (HPC) support enables high-throughput screening, addressing challenges such as fragmented toolchains and high computational demands. Validation on multiple antigens showcases the platform's ability to generate diverse and high-quality antibodies, confirming a scaling law where exploring larger sequence spaces increases the likelihood of identifying optimal binders. This platform provides a seamless, accessible solution for large-scale antibody design and is available via the antibody design page of PaddleHelix platform.

q-bio.BM↗