As an important and challenging problem in computer vision, Panoramic Semantic Segmentation (PASS) aims to give complete scene perception based on an ultra-wide angle of view. Most PASS methods often focus on spherical geometry with RGB input or using the depth information in original or HHA format, which does not make full use of panoramic image geometry. To address these shortcomings, we propose REL-SF4PASS with our REL depth representation based on cylindrical coordinate and Spherical-dynamic Multi-Modal Fusion SMMF. REL is made up of Rectified Depth, Elevation-Gained Vertical Inclination Angle, and Lateral Orientation Angle, which fully represents 3D space in cylindrical coordinate style and the surface normal direction. SMMF aims to ensure the diversity of fusion for different panoramic image regions and reduce the breakage of cylinder side surface expansion in ERP projection, which uses different fusion strategies to match the different regions in panoramic images. Experimental results show that REL-SF4PASS considerably improves performance and robustness on popular benchmark, Stanford2D3D Panoramic datasets. It gains 2.35% average mIoU improvement on all 3 folds and reduces the performance variance by approximately 70% when facing 3D disturbance.

In biomechanical modeling, the representation of ligament attachments is crucial for a realistic simulation of the forces acting between the vertebrae. These forces are typically modeled as vectors connecting ligament landmarks on adjacent vertebrae, making precise identification of these landmarks a key requirement for constructing reliable spine models. Existing automated detection methods are either limited to specific spinal regions or lack sufficient accuracy. This work presents a novel approach for detecting spinal ligament landmarks, which first performs shape-based segmentation of 3D vertebrae and subsequently applies domain-specific rules to identify different types of attachment points. The proposed method outperforms existing approaches by achieving high accuracy and demonstrating strong generalization across all spinal regions. Validation on two independent spinal datasets from multiple patients yielded a mean absolute error (MAE) of 0.7 mm and a root mean square error (RMSE) of 1.1 mm.

We propose a novel neural network-based end-to-end acoustic echo cancellation (E2E-AEC) method capable of streaming inference, which operates effectively without reliance on traditional linear AEC (LAEC) techniques and time delay estimation. Our approach includes several key strategies: First, we introduce and refine progressive learning to gradually enhance echo suppression. Second, our model employs knowledge transfer by initializing with a pre-trained LAECbased model, harnessing the insights gained from LAEC training. Third, we optimize the attention mechanism with a loss function applied on attention weights to achieve precise time alignment between the reference and microphone signals. Lastly, we incorporate voice activity detection to enhance speech quality and improve echo removal by masking the network output when near-end speech is absent. The effectiveness of our approach is validated through experiments conducted on public datasets.

Few-shot class-incremental learning (FSCIL) presents a core challenge in continual learning, requiring models to rapidly adapt to new classes with very limited samples while mitigating catastrophic forgetting. Recent prompt-based methods, which integrate pretrained backbones with task-specific prompts, have made notable progress. However, under extreme few-shot incremental settings, the model's ability to transfer and generalize becomes critical, and it is thus essential to leverage pretrained knowledge to learn feature representations that can be shared across future categories during the base session. Inspired by the mechanism of the CLS token, which is similar to human attention and progressively filters out task-irrelevant information, we propose the CLS Token Attention Steering Prompts (CASP). This approach introduces class-shared trainable bias parameters into the query, key, and value projections of the CLS token to explicitly modulate the self-attention weights. To further enhance generalization, we also design an attention perturbation strategy and perform Manifold Token Mixup in the shallow feature space, synthesizing potential new class features to improve generalization and reserve the representation capacity for upcoming tasks. Experiments on the CUB200, CIFAR100, and ImageNet-R datasets demonstrate that CASP outperforms state-of-the-art methods in both standard and fine-grained FSCIL settings without requiring fine-tuning during incremental phases and while significantly reducing the parameter overhead.

LLMs, while outperforming humans in a wide range of tasks, can still fail in unanticipated ways. We focus on two pervasive failure modes: (i) hallucinations, where models produce incorrect information about the world, and (ii) the low-resource effect, where the models show impressive performance in high-resource languages like English but the performance degrades significantly in low-resource languages like Bengali. We study the intersection of these issues and ask: do hallucination detectors suffer from the low-resource effect? We conduct experiments on five tasks across three domains (factual recall, STEM, and Humanities). Experiments with four LLMs and three hallucination detectors reveal a curious finding: As expected, the task accuracies in low-resource languages experience large drops (compared to English). However, the drop in detectors' accuracy is often several times smaller than the drop in task accuracy. Our findings suggest that even in low-resource languages, the internal mechanisms of LLMs might encode signals about their uncertainty. Further, the detectors are robust within language (even for non-English) and in multilingual setups, but not in cross-lingual settings without in-language supervision.

Endoscopic Retrograde Cholangiopancreatography (ERCP) is a key procedure in the diagnosis and treatment of biliary and pancreatic diseases. Artificial intelligence has been pointed as one solution to automatize diagnosis. However, public ERCP datasets are scarce, which limits the use of such approach. Therefore, this study aims to help fill this gap by providing a large and curated dataset. The collection is composed of 19.018 raw images and 19.317 processed from 1.602 patients. 5.519 images are labeled, which provides a ready to use dataset. All images were manually inspected and annotated by two gastroenterologist with more than 5 years of experience and reviewed by another gastroenterologist with more than 20 years of experience, all with more than 400 ERCP procedures annually. The utility and validity of the dataset is proven by a classification experiment. This collection aims to provide or contribute for a benchmark in automatic ERCP analysis and diagnosis of biliary and pancreatic diseases.

Longitudinal information in radiology reports refers to the sequential tracking of findings across multiple examinations over time, which is crucial for monitoring disease progression and guiding clinical decisions. Many recent automated radiology report generation methods are designed to capture longitudinal information; however, validating their performance is challenging. There is no proper tool to consistently label temporal changes in both ground-truth and model-generated texts for meaningful comparisons. Existing annotation methods are typically labor-intensive, relying on the use of manual lexicons and rules. Complex rules are closed-source, domain specific and hard to adapt, whereas overly simple ones tend to miss essential specialised information. Large language models (LLMs) offer a promising annotation alternative, as they are capable of capturing nuanced linguistic patterns and semantic similarities without extensive manual intervention. They also adapt well to new contexts. In this study, we therefore propose an LLM-based pipeline to automatically annotate longitudinal information in radiology reports. The pipeline first identifies sentences containing relevant information and then extracts the progression of diseases. We evaluate and compare five mainstream LLMs on these two tasks using 500 manually annotated reports. Considering both efficiency and performance, Qwen2.5-32B was subsequently selected and used to annotate another 95,169 reports from the public MIMIC-CXR dataset. Our Qwen2.5-32B-annotated dataset provided us with a standardized benchmark for evaluating report generation models. Using this new benchmark, we assessed seven state-of-the-art report generation models. Our LLM-based annotation method outperforms existing annotation solutions, achieving 11.3\% and 5.3\% higher F1-scores for longitudinal information detection and disease tracking, respectively.

Circular Synthetic Aperture Sonar (CSAS) provides a 360° azimuth view of the seabed, surpassing the limited aperture and mono-view image of conventional side-scan SAS. This makes CSAS a valuable tool for target recognition in mine warfare where the diversity of point of view is essential for reducing false alarms. CSAS processing typically produces a very high-resolution two-dimensional image. However, the parallax introduced by the circular displacement of the illuminator fill-in the shadow regions, and the shadow cast by an object on the seafloor is lost in favor of azimuth coverage and resolution. Yet the shadows provide complementary information on target shape useful for target recognition. In this paper, we explore a way to retrieve shadow information from CSAS data to improve target analysis and carry 3D reconstruction. Sub-aperture filtering is used to get a collection of images at various points of view along the circular trajectory and fixed focus shadow enhancement (FFSE) is applied to obtain sharp shadows. An interactive interface is also proposed to allow human operators to visualize these shadows along the circular trajectory. A space-carving reconstruction method is applied to infer the 3D shape of the object from the segmented shadows. The results demonstrate the potential of shadows in circular SAS for improving target analysis and 3D reconstruction.

As Automated Essay Scoring (AES) systems are increasingly used in high-stakes educational settings, concerns regarding algorithmic bias against English as a Second Language (ESL) learners have increased. Current Transformer-based regression models trained primarily on native-speaker corpora often learn spurious correlations between surface-level L2 linguistic features and essay quality. In this study, we conduct a bias study of a fine-tuned DeBERTa-v3 model using the ASAP 2.0 and ELLIPSE datasets, revealing a constrained score scaling for high-proficiency ESL writing where high-proficiency ESL essays receive scores 10.3% lower than Native speaker essays of identical human-rated quality. To mitigate this, we propose applying contrastive learning with a triplet construction strategy: Contrastive Learning with Matched Essay Pairs. We constructed a dataset of 17,161 matched essay pairs and fine-tuned the model using Triplet Margin Loss to align the latent representations of ESL and Native writing. Our approach reduced the high-proficiency scoring disparity by 39.9% (to a 6.2% gap) while maintaining a Quadratic Weighted Kappa (QWK) of 0.76. Post-hoc linguistic analysis suggests the model successfully disentangled sentence complexity from grammatical error, preventing the penalization of valid L2 syntactic structures.

Generalization to unseen concepts is a central challenge due to the scarcity of human annotations in Mention-agnostic Biomedical Concept Recognition (MA-BCR). This work makes two key contributions to systematically address this issue. First, we propose an evaluation framework built on hierarchical concept indices and novel metrics to measure generalization. Second, we explore LLM-based Auto-Labeled Data (ALD) as a scalable resource, creating a task-specific pipeline for its generation. Our research unequivocally shows that while LLM-generated ALD cannot fully substitute for manual annotations, it is a valuable resource for improving generalization, successfully providing models with the broader coverage and structural knowledge needed to approach recognizing unseen concepts. Code and datasets are available at https://github.com/bio-ie-tool/hi-ald.

Orb-weaving spiders detect prey on a web using vibration sensors at leg joints. They often dynamically crouch their legs during prey sensing, likely an active sensing strategy. However, how leg crouching enhances sensing is poorly understood, because measuring system vibrations in behaving animals is difficult. We use robophysical modeling to study this problem. Our previous spider robot had only four legs, simplified leg morphology, and a shallow crouching range of motion. Here, we developed a new spider robot, with eight legs, each with four joints that better approximated spider leg morphology. Leg exoskeletons were 3-D printed and joint stiffness was tuned using integrated silicone molding with variable materials and geometry. Tendon-driven actuation allowed a motor in the body to crouch all eight legs deeply as spiders do, while accelerometers at leg joints record leg vibrations. Experiments showed that our new spider robot reproduced key vibration features observed in the previous robot while improving biological accuracy. Our new robot provides a biologically more accurate robophysical model for studying how leg behaviors modulate vibration sensing on a web.

We introduce EMemBench, a programmatic benchmark for evaluating long-term memory of agents through interactive games. Rather than using a fixed set of questions, EMemBench generates questions from each agent's own trajectory, covering both text and visual game environments. Each template computes verifiable ground truth from underlying game signals, with controlled answerability and balanced coverage over memory skills: single/multi-hop recall, induction, temporal, spatial, logical, and adversarial. We evaluate memory agents with strong LMs/VLMs as backbones, using in-context prompting as baselines. Across 15 text games and multiple visual seeds, results are far from saturated: induction and spatial reasoning are persistent bottlenecks, especially in visual setting. Persistent memory yields clear gains for open backbones on text games, but improvements are less consistent for VLM agents, suggesting that visually grounded episodic memory remains an open challenge. A human study further confirms the difficulty of EMemBench.

This paper addresses the challenge of human-guided navigation for mobile collaborative robots under simultaneous proximity regulation and safety constraints. We introduce Adaptive Reinforcement and Model Predictive Control Switching (ARMS), a hybrid learning-control framework that integrates a reinforcement learning follower trained with Proximal Policy Optimization (PPO) and an analytical one-step Model Predictive Control (MPC) formulated as a quadratic program safety filter. To enable robust perception under partial observability and non-stationary human motion, ARMS employs a decoupled sensing architecture with a Long Short-Term Memory (LSTM) temporal encoder for the human-robot relative state and a spatial encoder for 360-degree LiDAR scans. The core contribution is a learned adaptive neural switcher that performs context-aware soft action fusion between the two controllers, favoring conservative, constraint-aware QP-based control in low-risk regions while progressively shifting control authority to the learned follower in highly cluttered or constrained scenarios where maneuverability is critical, and reverting to the follower action when the QP becomes infeasible. Extensive evaluations against Pure Pursuit, Dynamic Window Approach (DWA), and an RL-only baseline demonstrate that ARMS achieves an 82.5 percent success rate in highly cluttered environments, outperforming DWA and RL-only approaches by 7.1 percent and 3.1 percent, respectively, while reducing average computational latency by 33 percent to 5.2 milliseconds compared to a multi-step MPC baseline. Additional simulation transfer in Gazebo and initial real-world deployment results further indicate the practicality and robustness of ARMS for safe and efficient human-robot collaboration. Source code and a demonstration video are available at https://github.com/21ning/ARMS.git.

Evaluating the clinical correctness and reasoning fidelity of automatically generated medical imaging reports remains a critical yet unresolved challenge. Existing evaluation methods often fail to capture the structured diagnostic logic that underlies radiological interpretation, resulting in unreliable judgments and limited clinical relevance. We introduce AgentsEval, a multi-agent stream reasoning framework that emulates the collaborative diagnostic workflow of radiologists. By dividing the evaluation process into interpretable steps including criteria definition, evidence extraction, alignment, and consistency scoring, AgentsEval provides explicit reasoning traces and structured clinical feedback. We also construct a multi-domain perturbation-based benchmark covering five medical report datasets with diverse imaging modalities and controlled semantic variations. Experimental results demonstrate that AgentsEval delivers clinically aligned, semantically faithful, and interpretable evaluations that remain robust under paraphrastic, semantic, and stylistic perturbations. This framework represents a step toward transparent and clinically grounded assessment of medical report generation systems, fostering trustworthy integration of large language models into clinical practice.

The sample efficiency challenge in Deep Reinforcement Learning (DRL) compromises its industrial adoption due to the high cost and time demands of real-world training. Virtual environments offer a cost-effective alternative for training DRL agents, but the transfer of learned policies to real setups is hindered by the sim-to-real gap. Achieving zero-shot transfer, where agents perform directly in real environments without additional tuning, is particularly desirable for its efficiency and practical value. This work proposes a novel domain adaptation approach relying on a Style-Identified Cycle Consistent Generative Adversarial Network (StyleID-CycleGAN or SICGAN), an original Cycle Consistent Generative Adversarial Network (CycleGAN) based model. SICGAN translates raw virtual observations into real-synthetic images, creating a hybrid domain for training DRL agents that combines virtual dynamics with real-like visual inputs. Following virtual training, the agent can be directly deployed, bypassing the need for real-world training. The pipeline is validated with two distinct industrial robots in the approaching phase of a pick-and-place operation. In virtual environments agents achieve success rates of 90 to 100\%, and real-world deployment confirms robust zero-shot transfer (i.e., without additional training in the physical environment) with accuracies above 95\% for most workspace regions. We use augmented reality targets to improve the evaluation process efficiency, and experimentally demonstrate that the agent successfully generalizes to real objects of varying colors and shapes, including LEGO\textsuperscript{\textregistered}~cubes and a mug. These results establish the proposed pipeline as an efficient, scalable solution to the sim-to-real problem.

It is well-known that audio classifiers often rely on non-musically relevant features and spurious correlations to classify audio. Hence audio classifiers are easy to manipulate or confuse, resulting in wrong classifications. While inducing a misclassification is not hard, until now the set of features that the classifiers rely on was not well understood. In this paper we introduce a new method that uses causal reasoning to discover features of the frequency space that are sufficient and necessary for a given classification. We describe an implementation of this algorithm in the tool FreqReX and provide experimental results on a number of standard benchmark datasets. Our experiments show that causally sufficient and necessary subsets allow us to manipulate the outputs of the models in a variety of ways by changing the input very slightly. Namely, a change to one out of 240,000 frequencies results in a change in classification 58% of the time, and the change can be so small that it is practically inaudible. These results show that causal analysis is useful for understanding the reasoning process of audio classifiers and can be used to successfully manipulate their outputs.

We propose a reliable and energy-efficient framework for 3D brain tumor segmentation using spiking neural networks (SNNs). A multi-view ensemble of sagittal, coronal, and axial SNN models provides voxel-wise uncertainty estimation and enhances segmentation robustness. To address the high computational cost in training SNN models for semantic image segmentation, we employ Forward Propagation Through Time (FPTT), which maintains temporal learning efficiency with significantly reduced computational cost. Experiments on the Multimodal Brain Tumor Segmentation Challenges (BraTS 2017 and BraTS 2023) demonstrate competitive accuracy, well-calibrated uncertainty, and an 87% reduction in FLOPs, underscoring the potential of SNNs for reliable, low-power medical IoT and Point-of-Care systems.

Large language models can perform well on many isolated tasks, yet they continue to struggle on multi-turn, long-horizon agentic problems that require skills such as planning, state tracking, and long context processing. In this work, we aim to better understand the relative importance of advancing these underlying capabilities for success on such tasks. We develop an oracle counterfactual framework for multi-turn problems that asks: how would an agent perform if it could leverage an oracle to perfectly perform a specific task? The change in the agent's performance due to this oracle assistance allows us to measure the criticality of such oracle skill in the future advancement of AI agents. We introduce a suite of procedurally generated, game-like tasks with tunable complexity. These controlled environments allow us to provide precise oracle interventions, such as perfect planning or flawless state tracking, and make it possible to isolate the contribution of each oracle without confounding effects present in real-world benchmarks. Our results show that while some interventions (e.g., planning) consistently improve performance across settings, the usefulness of other skills is dependent on the properties of the environment and language model. Our work sheds light on the challenges of multi-turn agentic environments to guide the future efforts in the development of AI agents and language models.

Recent advances in image editing leverage latent diffusion models (LDMs) for versatile, text-prompt-driven edits across diverse tasks. Yet, maintaining pixel-level edge structures-crucial for tasks such as photorealistic style transfer or image tone adjustment-remains as a challenge for latent-diffusion-based editing. To overcome this limitation, we propose a novel Structure Preservation Loss (SPL) that leverages local linear models to quantify structural differences between input and edited images. Our training-free approach integrates SPL directly into the diffusion model's generative process to ensure structural fidelity. This core mechanism is complemented by a post-processing step to mitigate LDM decoding distortions, a masking strategy for precise edit localization, and a color preservation loss to preserve hues in unedited areas. Experiments confirm SPL enhances structural fidelity, delivering state-of-the-art performance in latent-diffusion-based image editing. Our code will be publicly released at https://github.com/gongms00/SPL.

We find that correct-to-incorrect sycophancy signals are most linearly separable within multi-head attention activations. Motivated by the linear representation hypothesis, we train linear probes across the residual stream, multilayer perceptron (MLP), and attention layers to analyze where these signals emerge. Although separability appears in the residual stream and MLPs, steering using these probes is most effective in a sparse subset of middle-layer attention heads. Using TruthfulQA as the base dataset, we find that probes trained on it transfer effectively to other factual QA benchmarks. Furthermore, comparing our discovered direction to previously identified "truthful" directions reveals limited overlap, suggesting that factual accuracy, and deference resistance, arise from related but distinct mechanisms. Attention-pattern analysis further indicates that the influential heads attend disproportionately to expressions of user doubt, contributing to sycophantic shifts. Overall, these findings suggest that sycophancy can be mitigated through simple, targeted linear interventions that exploit the internal geometry of attention activations.

Researchers have identified various sources of tool positioning errors for articulated industrial robots and have proposed dedicated compensation strategies. However, these typically require individual, specialized experiments with separate models and identification procedures. This article presents a unified approach to the static calibration of industrial robots that identifies a robot model, including geometric and non-geometric effects (compliant bending, thermal deformation, gear transmission errors), using only a single, straightforward experiment for data collection. The model augments the kinematic chain with virtual joints for each modeled effect and realizes the identification using Gauss-Newton optimization with analytic gradients. Fisher information spectra show that the estimation is well-conditioned and the parameterization near-minimal, whereas systematic temporal cross-validation and model ablations demonstrate robustness of the model identification. The resulting model is very accurate and its identification robust, achieving a mean position error of 26.8 $μm$ on a KUKA KR30 industrial robot compared to 102.3 $μm$ for purely geometric calibration.

Massively multilingual language models enable cross-lingual generalization but underperform on low-resource and unseen languages. While adapter-based fine-tuning offers a parameter-efficient solution, training language-specific adapters at scale remains costly. We introduce Typologically Informed Parameter Aggregation (TIPA), a training-free method that constructs proxy language adapters by aggregating existing ones, weighted by typological similarity. Integrated into the MAD-X framework, these proxies enable zero-shot cross-lingual transfer without additional training. We evaluate TIPA on five NLP tasks and over 230 languages. TIPA consistently outperforms or matches baselines such as English-only fine-tuning or selecting the typologically closest language adapter. We see the largest gains for languages lacking dedicated adapters. Our results demonstrate that typologically informed aggregation provides a viable alternative to language-specific modules without any training needed.

The growing demand for diverse and high-quality facial datasets for training and testing biometric systems is challenged by privacy regulations, data scarcity, and ethical concerns. Synthetic facial images offer a potential solution, yet existing generative models often struggle to balance realism, diversity, and identity preservation. This paper presents SCHIGAND, a novel synthetic face generation pipeline integrating StyleCLIP, HyperStyle, InterfaceGAN, and Diffusion models to produce highly realistic and controllable facial datasets. SCHIGAND enhances identity preservation while generating realistic intra-class variations and maintaining inter-class distinctiveness, making it suitable for biometric testing. The generated datasets were evaluated using ArcFace, a leading facial verification model, to assess their effectiveness in comparison to real-world facial datasets. Experimental results demonstrate that SCHIGAND achieves a balance between image quality and diversity, addressing key limitations of prior generative models. This research highlights the potential of SCHIGAND to supplement and, in some cases, replace real data for facial biometric applications, paving the way for privacy-compliant and scalable solutions in synthetic dataset generation.

Social media data has been of interest to Natural Language Processing (NLP) practitioners for over a decade, because of its richness in information, but also challenges for automatic processing. Since language use is more informal, spontaneous, and adheres to many different sociolects, the performance of NLP models often deteriorates. One solution to this problem is to transform data to a standard variant before processing it, which is also called lexical normalization. There has been a wide variety of benchmarks and models proposed for this task. The MultiLexNorm benchmark proposed to unify these efforts, but it consists almost solely of languages from the Indo-European language family in the Latin script. Hence, we propose an extension to MultiLexNorm, which covers 5 Asian languages from different language families in 4 different scripts. We show that the previous state-of-the-art model performs worse on the new languages and propose a new architecture based on Large Language Models (LLMs), which shows more robust performance. Finally, we analyze remaining errors, revealing future directions for this task.

Large language model (LLM)-powered assistants have recently integrated memory mechanisms that record user preferences, leading to more personalized and user-aligned responses. However, irrelevant personalized memories are often introduced into the context, interfering with the LLM's intent understanding. To comprehensively investigate the dual effects of personalization, we develop RPEval, a benchmark comprising a personalized intent reasoning dataset and a multi-granularity evaluation protocol. RPEval reveals the widespread phenomenon of irrational personalization in existing LLMs and, through error pattern analysis, illustrates its negative impact on user experience. Finally, we introduce RP-Reasoner, which treats memory utilization as a pragmatic reasoning process, enabling the selective integration of personalized information. Experimental results demonstrate that our method significantly outperforms carefully designed baselines on RPEval, and resolves 80% of the bad cases observed in a large-scale commercial personalized assistant, highlighting the potential of pragmatic reasoning to mitigate irrational personalization. Our benchmark is publicly available at https://github.com/XueyangFeng/RPEval.

Although Large Language Models (LLMs) excel in many tasks, their application to Speech-to-Speech Translation (S2ST) is underexplored and hindered by data scarcity. To bridge this gap, we propose PROST-LLM (PROgressive Speech-to-speech Translation) to enhance the S2ST capabilities in LLMs progressively. First, we fine-tune the LLMs with the CVSS corpus, employing designed tri-task learning and chain of modality methods to boost the initial performance. Then, leveraging the fine-tuned model, we generate preference pairs through self-sampling and back-translation without human evaluation. Finally, these preference pairs are used for preference optimization to enhance the model's S2ST capability further. Extensive experiments confirm the effectiveness of our proposed PROST-LLM in improving the S2ST capability of LLMs.

Unmanned Aerial Vehicle (UAV) applications have become increasingly prevalent in aerial photography and object recognition. However, there are major challenges to accurately capturing small targets in object detection due to the imbalanced scale and the blurred edges. To address these issues, boundary and position information mining (BPIM) framework is proposed for capturing object edge and location cues. The proposed BPIM includes position information guidance (PIG) module for obtaining location information, boundary information guidance (BIG) module for extracting object edge, cross scale fusion (CSF) module for gradually assembling the shallow layer image feature, three feature fusion (TFF) module for progressively combining position and boundary information, and adaptive weight fusion (AWF) module for flexibly merging the deep layer semantic feature. Therefore, BPIM can integrate boundary, position, and scale information in image for small object detection using attention mechanisms and cross-scale feature fusion strategies. Furthermore, BPIM not only improves the discrimination of the contextual feature by adaptive weight fusion with boundary, but also enhances small object perceptions by cross-scale position fusion. On the VisDrone2021, DOTA1.0, and WiderPerson datasets, experimental results show the better performances of BPIM compared to the baseline Yolov5-P2, and obtains the promising performance in the state-of-the-art methods with comparable computation load.

Recently, due to the advancement of multimodal technology, people are attempting to use visual large language models (VLLMs) in industrial production. Many deep learning models (DLMs) deployed in the production environment are gradually being replaced by VLLMs. Compared with DLMs, VLLMs have some advantages in industrial applications: (1) Their strong generalization ability enables them to perform well across a wide range of tasks. (2) They are flexible and can deal with unfamiliar samples through context learning quickly. However, VLLMs also have obvious drawbacks: (1) VLLMs do not perform as well as custom-developed DLMs in specific domains. (2) The number of parameters in VLLMs is generally quite large, and their deployment requires substantial computational resources. (3) VLLMs generally operate much slower than DLMs, making real-time response challenging to achieve. To better utilize VLLMs in industrial applications, we introduce AuroraEdge-V-2B in this work, a compact, robust, and high-speed VLLM designed for edge deployment. To make the model run faster, we also propose a compression-fusion method to improve inference efficiency. AuroraEdge-V-2B has the following notable features: (1) Easy deployment and faster: It has only 2B parameters and is highly suitable for edge deployment, offering better real-time performance. (2) Fewer visual tokens and cheaper: It significantly reduces the number of visual tokens in the decoding process, thereby reducing the floating-point operations by half during inference and making it cheaper to use. (3) Strong performance: It gets a higher score on 9 benchmarks than models with the same number of parameter (e.g., Qwen2-VL-2B, Qwen2.5-VL-3B, InternVL-2.5-2B).

Intelligent medical image analysis is essential for clinical decision support but is often limited by scarce annotations, constrained computational resources, and suboptimal model generalization. To address these challenges, we propose a lightweight medical image classification framework that integrates self-supervised contrastive learning with quantum-enhanced feature modeling. MobileNetV2 is employed as a compact backbone and pretrained using a SimCLR-style self-supervised paradigm on unlabeled images. A lightweight parameterized quantum circuit (PQC) is embedded as a quantum feature enhancement module, forming a hybrid classical-quantum architecture, which is subsequently fine-tuned on limited labeled data. Experimental results demonstrate that, with only approximately 2-3 million parameters and low computational cost, the proposed method consistently outperforms classical baselines without self-supervised learning or quantum enhancement in terms of Accuracy, AUC, and F1-score. Feature visualization further indicates improved discriminability and representation stability. Overall, this work provides a practical and forward-looking solution for high-performance medical artificial intelligence under resource-constrained settings.

Mamba, a selective state-space model (SSM), has emerged as an efficient alternative to Transformers for speech modeling, enabling long-sequence processing with linear complexity. While effective in speech separation, existing approaches, whether in the time or time-frequency domain, typically decompose the input along a single dimension into short one-dimensional sequences before processing them with Mamba, which restricts it to local 1D modeling and limits its ability to capture global dependencies across the 2D spectrogram. In this work, we propose an efficient omni-directional attention (OA) mechanism built upon unidirectional Mamba, which models global dependencies from ten different directions on the spectrogram. We expand the proposed mechanism into two baseline separation models and evaluate on three public datasets. Experimental results show that our approach consistently achieves significant performance gains over the baselines while preserving linear complexity, outperforming existing state-of-the-art (SOTA) systems.