arXiv subjects

Bowen Chen

Publications and source records attributed to Bowen Chen.

At least 37 records · Page 2Linked to original sources

arXiv2026

High-Efficiency Acousto-Optic Modulation on Non-Suspended Thin-Film Lithium Tantalate

Acousto-optic (AO) interactions provide a powerful interface between the microwave and optical domains, enabling functionalities such as optical switching, non-reciprocal propagation and efficient microwave-to-optical transduction. Integrated demonstrations to date have largely relied on thin-film lithium niobate (TFLN), which offers strong piezoelectric response and low optical loss performance. Here, we establish lithium tantalate on insulator (LTOI) as a scalable platform for integrated acousto-optics. LTOI combines intrinsically low birefringence, high optical damage threshold, strong electro-optic and Kerr nonlinearities, and superior acoustic quality factors with a mature high-volume manufacturing base. We demonstrate for the first time acousto-optic modulation on the LTOI platform. By exploiting the anisotropy of surface acoustic waves, we reveal a direct correlation between acousto-optic modulation efficiency and the electromechanical coupling coefficient of lithium tantalate. In particular, acoustic excitation along the crystal Z-axis enhances the higher-order R1 mode, yielding the highest modulation efficiency. Our Mach-Zehnder interferometers achieve a modulation efficiency of 0.68 $\mathrm{\mathbf{V \cdot cm}}$, while racetrack resonators reach 0.022 $\mathrm{\mathbf{V \cdot cm}}$ -representing, to the best of our knowledge, the lowest $\mathrm{V_πL}$ demonstrated in non-suspended ferroelectric platforms. This record performance directly enables microwave-to-optical conversion without suspended structures, establishing LTOI as a robust and scalable platform for integrated acousto-optics with broad applications in communications, signal processing, and quantum information technologies.

physics.optics↗

arXiv2026

Evidence-based diagnostic reasoning with multi-agent copilot for human pathology

Pathology is experiencing rapid digital transformation driven by whole-slide imaging and artificial intelligence (AI). While deep learning-based computational pathology has achieved notable success, traditional models primarily focus on image analysis without integrating natural language instruction or rich, text-based context. Current multimodal large language models (MLLMs) in computational pathology face limitations, including insufficient training data, inadequate support and evaluation for multi-image understanding, and a lack of autonomous, diagnostic reasoning capabilities. To address these limitations, we introduce PathChat+, a new MLLM specifically designed for human pathology, trained on over 1 million diverse, pathology-specific instruction samples and nearly 5.5 million question answer turns. Extensive evaluations across diverse pathology benchmarks demonstrated that PathChat+ substantially outperforms the prior PathChat copilot, as well as both state-of-the-art (SOTA) general-purpose and other pathology-specific models. Furthermore, we present SlideSeek, a reasoning-enabled multi-agent AI system leveraging PathChat+ to autonomously evaluate gigapixel whole-slide images (WSIs) through iterative, hierarchical diagnostic reasoning, reaching high accuracy on DDxBench, a challenging open-ended differential diagnosis benchmark, while also capable of generating visually grounded, humanly-interpretable summary reports.

cs.CV↗

arXiv2026

Spectral Scalpel: Amplifying Adjacent Action Discrepancy via Frequency-Selective Filtering for Skeleton-Based Action Segmentation

Skeleton-based Temporal Action Segmentation (STAS) seeks to densely segment and classify diverse actions within long, untrimmed skeletal motion sequences. However, existing STAS methodologies face challenges of limited inter-class discriminability and blurred segmentation boundaries, primarily due to insufficient distinction of spatio-temporal patterns between adjacent actions. To address these limitations, we propose Spectral Scalpel, a frequency-selective filtering framework aimed at suppressing shared frequency components between adjacent distinct actions while amplifying their action-specific frequencies, thereby enhancing inter-action discrepancies and sharpening transition boundaries. Specifically, Spectral Scalpel employs adaptive multi-scale spectral filters as scalpels to edit frequency spectra, coupled with a discrepancy loss between adjacent actions serving as the surgical objective. This design amplifies representational disparities between neighboring actions, effectively mitigating boundary localization ambiguities and inter-class confusion. Furthermore, complementing long-term temporal modeling, we introduce a frequency-aware channel mixer to strengthen channel evolution by aggregating spectra across channels. This work presents a novel paradigm for STAS that extends conventional spatio-temporal modeling by incorporating frequency-domain analysis. Extensive experiments on five public datasets demonstrate that Spectral Scalpel achieves state-of-the-art performance. Code is available at https://github.com/HaoyuJi/SpecScalpel.

cs.CV↗

arXiv2026

Toward scalable and bias-stable optical phased arrays on lithium tantalate

Ferroelectric materials are an ideal platform for high-speed reconfigurable photonic integrated circuits (PICs) for classical and quantum photonic computations, communications, and sensing. Most reconfigurable PIC devices achieve their functionalities via interference and are therefore highly sensitive to phase errors. Under static bias, carrier drift in ferroelectric waveguides induces continuous phase drift, creating a severe bottleneck for both PIC functionality and scalability. Here we propose achieving bias-stable and scalable ferroelectric PICs by exploiting the intrinsically low carrier drift of lithium tantalate (LT). Taking one of the PIC devices that is most sensitive to phase drift, the optical phased array (OPA), as an example, we designed and fabricated an integrated LT OPA that can keep the far-field main lobe 8 dB higher than side lobes for over 4 hours, representing at least a two-order-of-magnitude improvement over the state of the art. We demonstrated our device's capability in generating arbitrary spatiotemporal waveforms with a modulation frequency as low as 0.1 Hz, leading to practical applications in optical tweezers, trapped-ion quantum computers, adaptive optics for astronomy, AR, 3D printers, LiDAR, and free-space optical communications. Beyond OPA, our work establishes LT as a bias-stable, scalable, and high-speed PIC platform for large-scale classical and quantum photonic systems.

physics.optics↗

arXiv2026

A Comparative Analysis of LLM Memorization at Statistical and Internal Levels: Cross-Model Commonalities and Model-Specific Signatures

Memorization is a fundamental component of intelligence for both humans and LLMs. However, while LLM performance scales rapidly, our understanding of memorization lags. Due to limited access to the pre-training data of LLMs, most previous studies focus on a single model series, leading to isolated observations among series, making it unclear which findings are general or specific. In this study, we collect multiple model series (Pythia, OpenLLaMa, StarCoder, OLMo1/2/3) and analyze their shared or unique memorization behavior at both the statistical and internal levels, connecting individual observations while showing new findings. At the statistical level, we reveal that the memorization rate scales log-linearly with model size, and memorized sequences can be further compressed. Further analysis demonstrated a shared frequency and domain distribution pattern for memorized sequences. However, different models also show individual features under the above observations. At the internal level, we find that LLMs can remove certain injected perturbations, while memorized sequences are more sensitive. By decoding middle layers and attention head ablation, we revealed the general decoding process and shared important heads for memorization. However, the distribution of those important heads differs between families, showing a unique family-level feature. Through bridging various experiments and revealing new findings, this study paves the way for a universal and fundamental understanding of memorization in LLM.

cs.CL↗

arXiv2026

DynamicVis: Dynamic Visual Perception for Efficient Remote Sensing Foundation Models

The advancement of RS technology has enabled high-resolution Earth observation; however, interpreting these images using modern VFMs remains a significant challenge. Unlike object-centric natural images, RS imagery is fundamentally characterized by extreme target sparsity and massive spatial redundancy. Key objects of interest (e.g., ships, vehicles) often occupy less than 1% of the spatial extent, surrounded by vast, target-free backgrounds. Existing VFMs predominantly rely on uniform dense processing (e.g., ViTs) and pixel-reconstruction pre-training paradigms (e.g., MAE). These approaches inherently waste substantial computational capacity on modeling redundant backgrounds and inadvertently dilute the feature representations of small, sparse targets. To bridge this structural misalignment, we propose DynamicVis, a visual foundation model explicitly tailored to the sparse nature of RS imagery. Architecturally, DynamicVis introduces a Dynamic Region-Aware SSM that bypasses uniform computation. It adaptively routes and incrementally models only task-relevant, high-salience tokens while employing a parameter-free integration for background context, drastically reducing the complexity of processing ultra-long 2D token sequences ($\sim$100,000). Crucially, to equip the network with robust spatial-selection capabilities, we propose a novel Region-Level Meta-Embedding Multi-Instance Learning (MIL) pre-training paradigm. Trained on a million-scale dataset, this paradigm explicitly disentangles sparse foreground instances from dense backgrounds in the latent semantic space, overcoming the semantic ambiguity of conventional pixel-reconstruction methods. Extensive evaluations across nine diverse downstream tasks reveal that DynamicVis exhibits exceptional efficacy, particularly dominating in sparse-target and instance-level perception tasks (e.g., small object detection, and change detection).

cs.CV↗

arXiv2026

Computational Pathology in the Era of Emerging Foundation and Agentic AI -- International Expert Perspectives on Clinical Integration and Translational Readiness

Recent breakthroughs in artificial intelligence through foundation models and agents have accelerated the evolution of computational pathology. Demonstrated performance gains reported across academia in benchmarking datasets in predictive tasks such as diagnosis, prognosis, and treatment response have ignited substantial enthusiasm for clinical application. Despite this development momentum, real world adoption has lagged, as implementation faces economic, technical, and administrative challenges. Beyond existing discussions of technical architectures and comparative performance, this review considers how these emerging AI systems can be responsibly integrated into medical practice by connecting deployable clinical relevance with downstream analytical capabilities and their technical maturity, operational readiness, and economic and regulatory context. Drawing on perspectives from an international group, we provide a practical assessment of current capabilities and barriers to adoption in patient care settings.

cs.CE↗

arXiv2026

ResearchEnvBench: Benchmarking Agents on Environment Synthesis for Research Code Execution

Autonomous agents are increasingly expected to support scientific research, and recent benchmarks report progress in code repair and autonomous experimentation. However, these evaluations typically assume a pre-configured execution environment, which requires resolving complex software dependencies, aligning hardware and framework versions, and configuring distributed execution, yet this capability remains largely unbenchmarked. We introduce ResearchEnvBench, a benchmark for environment synthesis in research code execution. Given a research repository, documentation, and a target execution setting, agents must construct an environment that successfully executes at runtime. Evaluations on diverse research repositories reveal a substantial gap in current SOTA agents, with failures dominated by incomplete dependency resolution and brittle version coupling. ResearchEnvBench provides a realistic testbed for advancing autonomous agents toward reproducible scientific research.

cs.SE↗

arXiv2026

Shifting Adaptation from Weight Space to Memory Space: A Memory-Augmented Agent for Medical Image Segmentation

Medical image segmentation is fundamental to clinical workflows, yet models trained on a single dataset often fail to generalize across institutions, scanners, or patient populations. While vision foundation models have shown great promise in addressing this challenge, their deployment typically requires task-specific fine-tuning, which introduces substantial communication overhead in federated learning and prevents continuous knowledge evolution during deployment. In this work, we propose a memory-augmented segmentation agent (MemSeg-Agent) that shifts adaptation from weight space to memory space, enabling few-shot learning, federated supervised learning, and test-time adaptation within a unified architecture. MemSeg-Agent conditions a fixed backbone with lightweight static, few-shot, and test-time working memories, which are dynamically composed by an agentic controller. In federated settings, we update compact memory units instead of model parameters, substantially reducing communication overhead. Experiments on four public datasets demonstrate strong performance and robustness to domain shift: Static memory alone matches or surpasses strong supervised baselines with high parameter efficiency, and test-time working memory further improves in-domain and cross-domain performance without fine-tuning. Overall, MemSeg-Agent introduces a new paradigm for scalable and adaptive medical image segmentation in the era of agentic AI.

cs.CV↗

arXiv2026

Multi-Domain Supervised Contrastive Learning for UAV Radio-Frequency Open-Set Recognition

5G-Advanced (5G-A) has enabled the vibrant development of low altitude integrated sensing and communication (LA-ISAC) networks. As a core component of these networks, unmanned aerial vehicles (UAVs) have witnessed rapid growth in recent years. However, due to the lag in traditional industry regulatory norms, unauthorized flight incidents occur frequently, posing a severe security threat to LA-ISAC networks. To surveil the non-cooperative UAVs, in this paper, we propose a multi-domain supervised contrastive learning (MD-SupContrast) framework for UAV radio frequency (RF) open-set recognition. Specifically, first, the texture features and the time-frequency position features from the ResNet and the TransformerEncoder are fused, and then the supervised contrastive learning is applied to optimize the feature representation of the closed-set samples. Next, to surveil the invasive UAVs that appear in real life, we propose an improved generative OpenMax (IG-OpenMax) algorithm and construct an open-set recognition model, namely Open-RFNet. According to the unknown samples, we first freeze the feature extraction layers and then only retrain the classification layer, which achieves excellent recognition performance both in closed-set and open-set recognitions. We analyze the computational complexity of the proposed model. Experiments are conducted with a large-scale UAV open dataset. The results show that the proposed Open-RFNet outperforms the existing benchmark methods in terms of recognition accuracy between the known and the unknown UAVs, as it achieves 95.12% in closed-set and 96.08% in open-set under 25 UAV types, respectively.

eess.SP↗

arXiv2026

Seeing Beyond 8bits: Subjective and Objective Quality Assessment of HDR-UGC Videos

High Dynamic Range (HDR) user-generated (UGC) videos are rapidly proliferating across social platforms, yet most perceptual video quality assessment (VQA) systems remain tailored to Standard Dynamic Range (SDR). HDR has a higher bit depth, wide color gamut, and elevated luminance range, exposing distortions such as near-black crushing, highlight clipping, banding, and exposure flicker that amplify UGC artifacts and challenge SDR models. To catalyze progress, we curate Beyond8Bits, a large-scale subjective dataset of 44K videos from 6.5K sources with over 1.5M crowd ratings, spanning diverse scenes, capture conditions, and compression settings. We further introduce HDR-Q, the first Multimodal Large Language Model (MLLM) for HDR-UGC VQA. We propose (i) a novel HDR-aware vision encoder to produce HDR-sensitive embeddings, and (ii) HDR-Aware Policy Optimization (HAPO), an RL finetuning framework that anchors reasoning to HDR cues. HAPO augments GRPO via an HDR-SDR contrastive KL that encourages token reliance on HDR inputs and a Gaussian weighted regression reward for fine-grained MOS calibration. Across Beyond8Bits and public HDR-VQA benchmarks, HDR-Q delivers state-of-the-art performance.

cs.CV↗

arXiv2026

RegionRoute: Regional Style Transfer with Diffusion Model

Precise spatial control in diffusion-based style transfer remains challenging. This challenge arises because diffusion models treat style as a global feature and lack explicit spatial grounding of style representations, making it difficult to restrict style application to specific objects or regions. To our knowledge, existing diffusion models are unable to perform true localized style transfer, typically relying on handcrafted masks or multi-stage post-processing that introduce boundary artifacts and limit generalization. To address this, we propose an attention-supervised diffusion framework that explicitly teaches the model where to apply a given style by aligning the attention scores of style tokens with object masks during training. Two complementary objectives, a Focus loss based on KL divergence and a Cover loss using binary cross-entropy, jointly encourage accurate localization and dense coverage. A modular LoRA-MoE design further enables efficient and scalable multi-style adaptation. To evaluate localized stylization, we introduce the Regional Style Editing Score, which measures Regional Style Matching through CLIP-based similarity within the target region and Identity Preservation via masked LPIPS and pixel-level consistency on unedited areas. Experiments show that our method achieves mask-free, single-object style transfer at inference, producing regionally accurate and visually coherent results that outperform existing diffusion-based editing approaches.

cs.CV↗

arXiv2025

TaCo: Capturing Spatio-Temporal Semantic Consistency in Remote Sensing Change Detection

Remote sensing change detection (RSCD) aims to identify surface changes across bi-temporal satellite images. Most previous methods rely solely on mask supervision, which effectively guides spatial localization but provides limited constraints on the temporal semantic transitions. Consequently, they often produce spatially coherent predictions while still suffering from unresolved semantic inconsistencies. To address this limitation, we propose TaCo, a spatio-temporal semantic consistent network, which enriches the existing mask-supervised framework with a spatio-temporal semantic joint constraint. TaCo conceptualizes change as a semantic transition between bi-temporal states, in which one temporal feature representation can be derived from the other via dedicated transition features. To realize this, we introduce a Text-guided Transition Generator that integrates textual semantics with bi-temporal visual features to construct the cross-temporal transition features. In addition, we propose a spatio-temporal semantic joint constraint consisting of bi-temporal reconstruct constraints and a transition constraint: the former enforces alignment between reconstructed and original features, while the latter enhances discrimination for changes. This design can yield substantial performance gains without introducing any additional computational overhead during inference. Extensive experiments on six public datasets, spanning both binary and semantic change detection tasks, demonstrate that TaCo consistently achieves SOTA performance.

cs.CV↗

arXiv2025

OceanAI: A Conversational Platform for Accurate, Transparent, Near-Real-Time Oceanographic Insights

Artificial intelligence is transforming the sciences, yet general conversational AI systems often generate unverified "hallucinations" undermining scientific rigor. We present OceanAI, a conversational platform that integrates the natural-language fluency of open-source large language models (LLMs) with real-time, parameterized access to authoritative oceanographic data streams hosted by the National Oceanic and Atmospheric Administration (NOAA). Each query such as "What was Boston Harbor's highest water level in 2024?" triggers real-time API calls that identify, parse, and synthesize relevant datasets into reproducible natural-language responses and data visualizations. In a blind comparison with three widely used AI chat-interface products, only OceanAI produced NOAA-sourced values with original data references; others either declined to answer or provided unsupported results. Designed for extensibility, OceanAI connects to multiple NOAA data products and variables, supporting applications in marine hazard forecasting, ecosystem assessment, and water-quality monitoring. By grounding outputs and verifiable observations, OceanAI advances transparency, reproducibility, and trust, offering a scalable framework for AI-enabled decision support within the oceans. A public demonstration is available at https://oceanai.ai4ocean.xyz.

cs.CL↗

arXiv2025

SeG-SR: Integrating Semantic Knowledge into Remote Sensing Image Super-Resolution via Vision-Language Model

High-resolution (HR) remote sensing imagery plays a vital role in a wide range of applications, including urban planning and environmental monitoring. However, due to limitations in sensors and data transmission links, the images acquired in practice often suffer from resolution degradation. Remote Sensing Image Super-Resolution (RSISR) aims to reconstruct HR images from low-resolution (LR) inputs, providing a cost-effective and efficient alternative to direct HR image acquisition. Existing RSISR methods primarily focus on low-level characteristics in pixel space, while neglecting the high-level understanding of remote sensing scenes. This may lead to semantically inconsistent artifacts in the reconstructed results. Motivated by this observation, our work aims to explore the role of high-level semantic knowledge in improving RSISR performance. We propose a Semantic-Guided Super-Resolution framework, SeG-SR, which leverages Vision-Language Models (VLMs) to extract semantic knowledge from input images and uses it to guide the super resolution (SR) process. Specifically, we first design a Semantic Feature Extraction Module (SFEM) that utilizes a pretrained VLM to extract semantic knowledge from remote sensing images. Next, we propose a Semantic Localization Module (SLM), which derives a series of semantic guidance from the extracted semantic knowledge. Finally, we develop a Learnable Modulation Module (LMM) that uses semantic guidance to modulate the features extracted by the SR network, effectively incorporating high-level scene understanding into the SR pipeline. We validate the effectiveness and generalizability of SeG-SR through extensive experiments: SeG-SR achieves state-of-the-art performance on three datasets, and consistently improves performance across various SR architectures. Notably, for the x4 SR task on UCMerced dataset, it attained a PSNR of 29.3042 dB and an SSIM of 0.7961.

cs.CV↗

arXiv2025

LongInsightBench: A Comprehensive Benchmark for Evaluating Omni-Modal Models on Human-Centric Long-Video Understanding

We introduce \textbf{LongInsightBench}, the first benchmark designed to assess models' ability to understand long videos, with a focus on human language, viewpoints, actions, and other contextual elements, while integrating \textbf{visual, audio, and text} modalities. Our benchmark excels in three key areas: \textbf{a) Long-Duration, Information-Dense Videos:} We carefully select approximately 1,000 videos from open-source datasets FineVideo based on duration limit and the information density of both visual and audio modalities, focusing on content like lectures, interviews, and vlogs, which contain rich language elements. \textbf{b) Diverse and Challenging Task Scenarios:} We have designed six challenging task scenarios, including both Intra-Event and Inter-Event Tasks. \textbf{c) Rigorous and Comprehensive Quality Assurance Pipelines:} We have developed a three-step, semi-automated data quality assurance pipeline to ensure the difficulty and validity of the synthesized questions and answer options. Based on LongInsightBench, we designed a series of experiments. Experimental results shows that Omni-modal models(OLMs) still face challenge in tasks requiring precise temporal localization (T-Loc) and long-range causal inference (CE-Caus). Extended experiments reveal the information loss and processing bias in multi-modal fusion of OLMs. Our dataset and code is available at https://anonymous.4open.science/r/LongInsightBench-910F/.

cs.CV↗

arXiv2025

Institutional Research Computing Capabilities in Australia: 2024

Institutional research computing infrastructure plays a vital role in Australia's research ecosystem, complementing and extending national facilities. This paper analyses research computing capabilities across Australian universities and organisations, showing how institutional systems support research excellence through local compute resources, specialised hardware, and cluster solutions. Our study finds that nearly 112,258 CPU cores and 2,241 GPUs serve over 6,000 researchers as essential bridges between desktops and national facilities, enabling workflows from development to large-scale computations. The estimated replacement value of this infrastructure is $144M AUD. Drawing on detailed data from multiple institutions, we identify key patterns in deployment, utilisation, and strategic alignment with research priorities. Institutional resources provide critical support for data-intensive projects, facilitate training and higher-degree student research, enable prototyping and development, and ensure data sovereignty compliance when required. The analysis shows how these facilities leverage national investments while addressing institution-specific needs that national systems cannot meet. We present evidence that strategic investment in institutional capabilities yields significant returns through greater research productivity, enhanced graduate training, and improved outcomes. The study offers insights for organisations planning computing strategies and highlights the importance of maintaining robust institutional resources alongside national facilities.

cs.DC↗

arXiv2025

ICME 2025 Generalizable HDR and SDR Video Quality Measurement Grand Challenge

This paper reports IEEE International Conference on Multimedia \& Expo (ICME) 2025 Grand Challenge on Generalizable HDR and SDR Video Quality Measurement. With the rapid development of video technology, especially High Dynamic Range (HDR) and Standard Dynamic Range (SDR) contents, the need for robust and generalizable Video Quality Assessment (VQA) methods has become increasingly demanded. Existing VQA models often struggle to deliver consistent performance across varying dynamic ranges, distortion types, and diverse content. This challenge was established to benchmark and promote VQA approaches capable of jointly handling HDR and SDR content. In the final evaluation phase, five teams submitted seven models along with technical reports to the Full Reference (FR) and No Reference (NR) tracks. Among them, four methods outperformed VMAF baseline, while the top-performing model achieved state-of-the-art performance, setting a new benchmark for generalizable video quality assessment.

eess.IV↗