arXiv subjects

Bo Wang

Publications and source records attributed to Bo Wang.

At least 289 records · Page 16Linked to original sources

arXiv2025

Facial Foundational Model Advances Early Warning of Coronary Artery Disease from Live Videos with DigitalShadow

Global population aging presents increasing challenges to healthcare systems, with coronary artery disease (CAD) responsible for approximately 17.8 million deaths annually, making it a leading cause of global mortality. As CAD is largely preventable, early detection and proactive management are essential. In this work, we introduce DigitalShadow, an advanced early warning system for CAD, powered by a fine-tuned facial foundation model. The system is pre-trained on 21 million facial images and subsequently fine-tuned into LiveCAD, a specialized CAD risk assessment model trained on 7,004 facial images from 1,751 subjects across four hospitals in China. DigitalShadow functions passively and contactlessly, extracting facial features from live video streams without requiring active user engagement. Integrated with a personalized database, it generates natural language risk reports and individualized health recommendations. With privacy as a core design principle, DigitalShadow supports local deployment to ensure secure handling of user data.

cs.CV↗

arXiv2025

Hear the Scene: Audio-Enhanced Text Spotting

Recent advancements in scene text spotting have focused on end-to-end methodologies that heavily rely on precise location annotations, which are often costly and labor-intensive to procure. In this study, we introduce an innovative approach that leverages only transcription annotations for training text spotting models, substantially reducing the dependency on elaborate annotation processes. Our methodology employs a query-based paradigm that facilitates the learning of implicit location features through the interaction between text queries and image embeddings. These features are later refined during the text recognition phase using an attention activation map. Addressing the challenges associated with training a weakly-supervised model from scratch, we implement a circular curriculum learning strategy to enhance model convergence. Additionally, we introduce a coarse-to-fine cross-attention localization mechanism for more accurate text instance localization. Notably, our framework supports audio-based annotation, which significantly diminishes annotation time and provides an inclusive alternative for individuals with disabilities. Our approach achieves competitive performance against existing benchmarks, demonstrating that high accuracy in text spotting can be attained without extensive location annotations.

cs.CV↗

arXiv2025

SonarT165: A Large-scale Benchmark and STFTrack Framework for Acoustic Object Tracking

Underwater observation systems typically integrate optical cameras and imaging sonar systems. When underwater visibility is insufficient, only sonar systems can provide stable data, which necessitates exploration of the underwater acoustic object tracking (UAOT) task. Previous studies have explored traditional methods and Siamese networks for UAOT. However, the absence of a unified evaluation benchmark has significantly constrained the value of these methods. To alleviate this limitation, we propose the first large-scale UAOT benchmark, SonarT165, comprising 165 square sequences, 165 fan sequences, and 205K high-quality annotations. Experimental results demonstrate that SonarT165 reveals limitations in current state-of-the-art SOT trackers. To address these limitations, we propose STFTrack, an efficient framework for acoustic object tracking. It includes two novel modules, a multi-view template fusion module (MTFM) and an optimal trajectory correction module (OTCM). The MTFM module integrates multi-view feature of both the original image and the binary image of the dynamic template, and introduces a cross-attention-like layer to fuse the spatio-temporal target representations. The OTCM module introduces the acoustic-response-equivalent pixel property and proposes normalized pixel brightness response scores, thereby suppressing suboptimal matches caused by inaccurate Kalman filter prediction boxes. To further improve the model feature, STFTrack introduces a acoustic image enhancement method and a Frequency Enhancement Module (FEM) into its tracking pipeline. Comprehensive experiments show the proposed STFTrack achieves state-of-the-art performance on the proposed benchmark. The code is available at https://github.com/LiYunfengLYF/SonarT165.

cs.CV↗

arXiv2025

Program Skeletons for Automated Program Translation

Translating software between programming languages is a challenging task, for which automated techniques have been elusive and hard to scale up to larger programs. A key difficulty in cross-language translation is that one has to re-express the intended behavior of the source program into idiomatic constructs of a different target language. This task needs abstracting away from the source language-specific details, while keeping the overall functionality the same. In this work, we propose a novel and systematic approach for making such translation amenable to automation based on a framework we call program skeletons. A program skeleton retains the high-level structure of the source program by abstracting away and effectively summarizing lower-level concrete code fragments, which can be mechanically translated to the target programming language. A skeleton, by design, permits many different ways of filling in the concrete implementation for fragments, which can work in conjunction with existing data-driven code synthesizers. Most importantly, skeletons can conceptually enable sound decomposition, i.e., if each individual fragment is correctly translated, taken together with the mechanically translated skeleton, the final translated program is deemed to be correct as a whole. We present a prototype system called Skel embodying the idea of skeleton-based translation from Python to JavaScript. Our results show promising scalability compared to prior works. For 9 real-world Python programs, some with more than about 1k lines of code, 95% of their code fragments can be automatically translated, while about 5% require manual effort. All the final translations are correct with respect to whole-program test suites.

cs.PL↗

arXiv2025

Adaptive sieving with semismooth Newton proximal augmented Lagrangian algorithm for multi-task Lasso problems

Multi-task learning enhances model generalization by jointly learning from related tasks. This paper focuses on the $\ell_{1,\infty}$-norm constrained multi-task learning problem, which promotes a shared feature representation while inducing sparsity in task-specific parameters. We propose an adaptive sieving (AS) strategy to efficiently generate a solution path for multi-task Lasso problems. Each subproblem along the path is solved via an inexact semismooth Newton proximal augmented Lagrangian ({\sc Ssnpal}) algorithm, achieving an asymptotically superlinear convergence rate. By exploiting the Karush-Kuhn-Tucker (KKT) conditions and the inherent sparsity of multi-task Lasso solutions, the {\sc Ssnpal} algorithm solves a sequence of reduced subproblems with small dimensions. This approach enables our method to scale effectively to large problems. Numerical experiments on synthetic and real-world datasets demonstrate the superior efficiency and robustness of our algorithm compared to state-of-the-art solvers.

math.OC↗

arXiv2025

Multi-scale DeepOnet (Mscale-DeepOnet) for Mitigating Spectral Bias in Learning High Frequency Operators of Oscillatory Functions

In this paper, a multi-scale DeepOnet (Mscale-DeepOnet) is proposed to reduce the spectral bias of the DeepOnet in learning high-frequency mapping between highly oscillatory functions, with an application to the nonlinear mapping between the coefficient of the Helmholtz equation and its solution. The Mscale-DeepOnet introduces the multiscale neural network in the branch and trunk networks of the original DeepOnet, the resulting Mscale-DeepOnet is shown to be able to capture various high-frequency components of the mapping itself and its image. Numerical results demonstrate the substantial improvement of the Mscale-DeepOnet for the problem of wave scattering in the high-frequency regime over the normal DeepOnet with a similar number of network parameters.

cs.LG↗

arXiv2025

Pangu Ultra: Pushing the Limits of Dense Large Language Models on Ascend NPUs

We present Pangu Ultra, a Large Language Model (LLM) with 135 billion parameters and dense Transformer modules trained on Ascend Neural Processing Units (NPUs). Although the field of LLM has been witnessing unprecedented advances in pushing the scale and capability of LLM in recent years, training such a large-scale model still involves significant optimization and system challenges. To stabilize the training process, we propose depth-scaled sandwich normalization, which effectively eliminates loss spikes during the training process of deep models. We pre-train our model on 13.2 trillion diverse and high-quality tokens and further enhance its reasoning capabilities during post-training. To perform such large-scale training efficiently, we utilize 8,192 Ascend NPUs with a series of system optimizations. Evaluations on multiple diverse benchmarks indicate that Pangu Ultra significantly advances the state-of-the-art capabilities of dense LLMs such as Llama 405B and Mistral Large 2, and even achieves competitive results with DeepSeek-R1, whose sparse model structure contains much more parameters. Our exploration demonstrates that Ascend NPUs are capable of efficiently and effectively training dense models with more than 100 billion parameters. Our model and system will be available for our commercial customers.

cs.CL↗

arXiv2025

Prospects for constraining interacting dark energy cosmology with gravitational-wave bright sirens detected by future SKA-era pulsar timing arrays

We explore the constraints on cosmological parameters in interacting dark energy (IDE) models described by energy transfer rates $Q = βH ρ_{\rm de}$ and $Q = βH ρ_{\rm c}$, using simulated gravitational-wave (GW) bright siren data from pulsar timing arrays (PTAs) and the Planck 2018 cosmic microwave background (CMB) data. In particular, we simulate a future PTA observation in the FAST/SKA era with 20 millisecond pulsars (MSPs), each having 20\,ns white noise over a 10-year observation span, and demonstrate that this mock dataset significantly improves the constraint precision of key cosmological parameters such as the Hubble constant $H_0$, matter density $Ω_m$, and the coupling parameter $β$. For the IDE model $Q = βH ρ_{\rm de}$, PTA data alone provides tighter constraints on these parameters than the CMB data alone, primarily due to the high sensitivity of GW standard sirens in probing the late universe. Combining PTA and CMB data further enhances the constraints by 43.6\% for $H_0$, 43.2\% for $Ω_m$, and 44.7\% for $β$, relative to using CMB data alone. In contrast, for $Q = βH ρ_{\rm c}$, the CMB data alone constrains $β$ more tightly than the PTA data, due to the stronger impact of this interaction in the early universe. Nevertheless, the PTA+\,CMB combination still yields improvements of 13.3\% for $H_0$, 22.7\% for $Ω_m$, and 18.2\% for $β$. Increasing the number of MSPs in the PTA further tightens all parameter constraints in both IDE models. Our results highlight the great potential of future PTA observations for significantly improving cosmological parameter estimation in IDE models, offering critical insights into the nature of dark energy and its interaction with dark matter.

astro-ph.CO↗

arXiv2025

MedSAM2: Segment Anything in 3D Medical Images and Videos

Medical image and video segmentation is a critical task for precision medicine, which has witnessed considerable progress in developing task or modality-specific and generalist models for 2D images. However, there have been limited studies on building general-purpose models for 3D images and videos with comprehensive user studies. Here, we present MedSAM2, a promptable segmentation foundation model for 3D image and video segmentation. The model is developed by fine-tuning the Segment Anything Model 2 on a large medical dataset with over 455,000 3D image-mask pairs and 76,000 frames, outperforming previous models across a wide range of organs, lesions, and imaging modalities. Furthermore, we implement a human-in-the-loop pipeline to facilitate the creation of large-scale datasets resulting in, to the best of our knowledge, the most extensive user study to date, involving the annotation of 5,000 CT lesions, 3,984 liver MRI lesions, and 251,550 echocardiogram video frames, demonstrating that MedSAM2 can reduce manual costs by more than 85%. MedSAM2 is also integrated into widely used platforms with user-friendly interfaces for local and cloud deployment, making it a practical tool for supporting efficient, scalable, and high-quality segmentation in both research and healthcare environments.

eess.IV↗

arXiv2025

Ramírez's problems and fibers on well approximable set of systems of affine forms

We show that badly approximable matrices are exactly those that, for any inhomogeneous parameter, can not be inhomogeneous approximated at every monotone divergent rate, which generalizes Ramírez's result (2018). We also establish some metrical results of the fibers on well approximable set of systems of affine forms, which gives answer to two of Ramírez's problems (2018). Furthermore, we prove that badly approximable systems are exactly those that, can not be approximated at each monotone convergent rate ψ. Moreover, we study the topological structure of the set of approximation functions.

math.NT↗

arXiv2025

Content-decoupled Contrastive Learning-based Implicit Degradation Modeling for Blind Image Super-Resolution

Implicit degradation modeling-based blind super-resolution (SR) has attracted more increasing attention in the community due to its excellent generalization to complex degradation scenarios and wide application range. How to extract more discriminative degradation representations and fully adapt them to specific image features is the key to this task. In this paper, we propose a new Content-decoupled Contrastive Learning-based blind image super-resolution (CdCL) framework following the typical blind SR pipeline. This framework introduces negative-free contrastive learning technique for the first time to model the implicit degradation representation, in which a new cyclic shift sampling strategy is designed to ensure decoupling between content features and degradation features from the data perspective, thereby improving the purity and discriminability of the learned implicit degradation space. In addition, we propose a detail-aware implicit degradation adapting module that can better adapt degradation representations to specific LR features by enhancing the basic adaptation unit's perception of image details, significantly reducing the overall SR model complexity. Extensive experiments on synthetic and real data show that our method achieves highly competitive quantitative and qualitative results in various degradation settings while obviously reducing parameters and computational costs, validating the feasibility of designing practical and lightweight blind SR tools.

cs.CV↗

arXiv2025

Leader-Follower Formation and Tracking Control of Underactuated Surface Vessels

This Technical Note presents a simple control approach for global trajectory tracking and formation control of underactuated surface vessels equipped with only two propellers. The control approach exploits the inherent cascaded structure of the vehicle dynamics and is divided into control designs at the kinematics and kinetics levels. A controller with a low-gain feature is designed at the kinematics level by incorporating the cascaded system method, persistency of excitation, and the small-gain theorem. Furthermore, a PD+ controller is designed to achieve the velocity tracking at the kinetics level. The proposed control laws are partially linear and saturated linear and easy to implement. Based on a leader-follower scheme, our control approach applies to the formation tracking control problem of multi-vehicle systems under a directed spanning tree topology. Our main results guarantee uniform global asymptotic stability for the closed-loop system, which implies robustness with respect to bounded disturbances in the sense of Malkin's total stability, also known as local input-to-state stability.

eess.SY↗

arXiv2025

Contrastive Learning Guided Latent Diffusion Model for Image-to-Image Translation

The diffusion model has demonstrated superior performance in synthesizing diverse and high-quality images for text-guided image translation. However, there remains room for improvement in both the formulation of text prompts and the preservation of reference image content. First, variations in target text prompts can significantly influence the quality of the generated images, and it is often challenging for users to craft an optimal prompt that fully captures the content of the input image. Second, while existing models can introduce desired modifications to specific regions of the reference image, they frequently induce unintended alterations in areas that should remain unchanged. To address these challenges, we propose pix2pix-zeroCon, a zero-shot diffusion-based method that eliminates the need for additional training by leveraging patch-wise contrastive loss. Specifically, we automatically determine the editing direction in the text embedding space based on the reference image and target prompts. Furthermore, to ensure precise content and structural preservation in the edited image, we introduce cross-attention guiding loss and patch-wise contrastive loss between the generated and original image embeddings within a pre-trained diffusion model. Notably, our approach requires no additional training and operates directly on a pre-trained text-to-image diffusion model. Extensive experiments demonstrate that our method surpasses existing models in image-to-image translation, achieving enhanced fidelity and controllability.

cs.CV↗

arXiv2025

Gazing at Rewards: Eye Movements as a Lens into Human and AI Decision-Making in Hybrid Visual Foraging

Imagine searching a collection of coins for quarters ($0.25$), dimes ($0.10$), nickels ($0.05$), and pennies ($0.01$)-a hybrid foraging task where observers look for multiple instances of multiple target types. In such tasks, how do target values and their prevalence influence foraging and eye movement behaviors (e.g., should you prioritize rare quarters or common nickels)? To explore this, we conducted human psychophysics experiments, revealing that humans are proficient reward foragers. Their eye fixations are drawn to regions with higher average rewards, fixation durations are longer on more valuable targets, and their cumulative rewards exceed chance, approaching the upper bound of optimal foragers. To probe these decision-making processes of humans, we developed a transformer-based Visual Forager (VF) model trained via reinforcement learning. Our VF model takes a series of targets, their corresponding values, and the search image as inputs, processes the images using foveated vision, and produces a sequence of eye movements along with decisions on whether to collect each fixated item. Our model outperforms all baselines, achieves cumulative rewards comparable to those of humans, and approximates human foraging behavior in eye movements and foraging biases within time-limited environments. Furthermore, stress tests on out-of-distribution tasks with novel targets, unseen values, and varying set sizes demonstrate the VF model's effective generalization. Our work offers valuable insights into the relationship between eye movements and decision-making, with our model serving as a powerful tool for further exploration of this connection. All data, code, and models are available at https://github.com/ZhangLab-DeepNeuroCogLab/visual-forager.

cs.AI↗

arXiv2025

RustMap: Towards Project-Scale C-to-Rust Migration via Program Analysis and LLM

Migrating existing C programs into Rust is increasingly desired, as Rust offers superior memory safety while maintaining C's high performance. However, vastly different features between C and Rust--e.g., distinct definitions and usages of pointers and references--pose significant challenges beyond mere syntactic translation. Existing automated translation tools, such as C2Rust, may rely too much on syntactic, template-based translation and generate unsafe Rust code that is hard for human developers to read, maintain, or even compile. More semantic-aware translation that produces safer, idiomatic, and runnable Rust code is much needed. This paper introduces a novel dependency-guided and large language model (LLM)-based C-to-Rust translation approach, RustMap, based on three key ideas: (1) Utilize LLM capabilities to produce idiomatic Rust code from given small pieces of C code, (2) Mitigate LLM limitations in handling large codebases by breaking project-scale C programs into smaller units for translation according to their usage dependencies and composing them into a runnable Rust program, and (3) Enhance the correctness of the translated Rust program by using test cases to check input/output equivalence, isolate faulty code when execution states deviate, and iteratively refine the translation using feedback from compilation and test errors. We empirically evaluate RustMap on 126 real-world programs, including 125 from Rosetta Code and a 7000+ line bzip2 implementation using GPT-4o as the LLM. RustMap shows promising results, guiding GPT-4o to produce idiomatic, readable, and functional Rust code with significantly less unsafe code than other tools, and revealing non-trivial translation patterns reusable for future research.

cs.SE↗

arXiv2025

D&M: Enriching E-commerce Videos with Sound Effects by Key Moment Detection and SFX Matching

Videos showcasing specific products are increasingly important for E-commerce. Key moments naturally exist as the first appearance of a specific product, presentation of its distinctive features, the presence of a buying link, etc. Adding proper sound effects (SFX) to these key moments, or video decoration with SFX (VDSFX), is crucial for enhancing the user engaging experience. Previous studies about adding SFX to videos perform video to SFX matching at a holistic level, lacking the ability of adding SFX to a specific moment. Meanwhile, previous studies on video highlight detection or video moment retrieval consider only moment localization, leaving moment to SFX matching untouched. By contrast, we propose in this paper D&M, a unified method that accomplishes key moment detection and moment to SFX matching simultaneously. Moreover, for the new VDSFX task we build a large-scale dataset SFX-Moment from an E-commerce platform. For a fair comparison, we build competitive baselines by extending a number of current video moment detection methods to the new task. Extensive experiments on SFX-Moment show the superior performance of the proposed method over the baselines.

cs.CV↗

arXiv2025

Graph-Weighted Contrastive Learning for Semi-Supervised Hyperspectral Image Classification

Most existing graph-based semi-supervised hyperspectral image classification methods rely on superpixel partitioning techniques. However, they suffer from misclassification of certain pixels due to inaccuracies in superpixel boundaries, \ie, the initial inaccuracies in superpixel partitioning limit overall classification performance. In this paper, we propose a novel graph-weighted contrastive learning approach that avoids the use of superpixel partitioning and directly employs neural networks to learn hyperspectral image representation. Furthermore, while many approaches require all graph nodes to be available during training, our approach supports mini-batch training by processing only a subset of nodes at a time, reducing computational complexity and improving generalization to unseen nodes. Experimental results on three widely-used datasets demonstrate the effectiveness of the proposed approach compared to baselines relying on superpixel partitioning.

cs.CV↗

arXiv2025

LLMs are Bug Replicators: An Empirical Study on LLMs' Capability in Completing Bug-prone Code

Large Language Models (LLMs) have demonstrated remarkable performance in code completion. However, the training data used to develop these models often contain a significant amount of buggy code. Yet, it remains unclear to what extent these buggy instances influence LLMs' performance when tackling bug-prone code completion tasks. To fill this gap, this paper presents the first empirical study evaluating the performance of LLMs in completing bug-prone code. Through extensive experiments on 7 LLMs and the Defects4J dataset, we analyze LLMs' accuracy, robustness, and limitations in this challenging context. Our experimental results show that completing bug-prone code is significantly more challenging for LLMs than completing normal code. Notably, in bug-prone tasks, the likelihood of LLMs generating correct code is nearly the same as generating buggy code, and it is substantially lower than in normal code completion tasks (e.g., 12.27% vs. 29.85% for GPT-4). To our surprise, 44.44% of the bugs LLMs make are completely identical to the pre-fix version, indicating that LLMs have been seriously biased by historical bugs when completing code. Additionally, we investigate the effectiveness of existing post-processing techniques and find that while they can improve consistency, they do not significantly reduce error rates in bug-prone code scenarios. Our research highlights the limitations of current LLMs in handling bug-prone code and underscores the need for improved models and post-processing strategies to enhance code completion accuracy in real-world development environments.

cs.SE↗