arXiv subjects

Lin Wang

Publications and source records attributed to Lin Wang.

At least 163 records · Page 9Linked to original sources

arXiv2025

HumanoidPano: Hybrid Spherical Panoramic-LiDAR Cross-Modal Perception for Humanoid Robots

The perceptual system design for humanoid robots poses unique challenges due to inherent structural constraints that cause severe self-occlusion and limited field-of-view (FOV). We present HumanoidPano, a novel hybrid cross-modal perception framework that synergistically integrates panoramic vision and LiDAR sensing to overcome these limitations. Unlike conventional robot perception systems that rely on monocular cameras or standard multi-sensor configurations, our method establishes geometrically-aware modality alignment through a spherical vision transformer, enabling seamless fusion of 360 visual context with LiDAR's precise depth measurements. First, Spherical Geometry-aware Constraints (SGC) leverage panoramic camera ray properties to guide distortion-regularized sampling offsets for geometric alignment. Second, Spatial Deformable Attention (SDA) aggregates hierarchical 3D features via spherical offsets, enabling efficient 360°-to-BEV fusion with geometrically complete object representations. Third, Panoramic Augmentation (AUG) combines cross-view transformations and semantic alignment to enhance BEV-panoramic feature consistency during data augmentation. Extensive evaluations demonstrate state-of-the-art performance on the 360BEV-Matterport benchmark. Real-world deployment on humanoid platforms validates the system's capability to generate accurate BEV segmentation maps through panoramic-LiDAR co-perception, directly enabling downstream navigation tasks in complex environments. Our work establishes a new paradigm for embodied perception in humanoid robotics.

cs.RO↗

arXiv2025

Text-to-3D Generation by 2D Editing

Distilling 3D representations from pretrained 2D diffusion models is essential for 3D creative applications across gaming, film, and interior design. Current SDS-based methods are hindered by inefficient information distillation from diffusion models, which prevents the creation of photorealistic 3D contents. In this paper, we first reevaluate the SDS approach by analyzing its fundamental nature as a basic image editing process that commonly results in over-saturation, over-smoothing, lack of rich content and diversity due to the poor-quality single-step denoising. In light of this, we then propose a novel method called 3D Generation by Editing (GE3D). Each iteration of GE3D utilizes a 2D editing framework that combines a noising trajectory to preserve the information of the input image, alongside a text-guided denoising trajectory. We optimize the process by aligning the latents across both trajectories. This approach fully exploits pretrained diffusion models to distill multi-granularity information through multiple denoising steps, resulting in photorealistic 3D outputs. Both theoretical and experimental results confirm the effectiveness of our approach, which not only advances 3D generation technology but also establishes a novel connection between 3D generation and 2D editing. This could potentially inspire further research in the field. Code and demos are released at https://jahnsonblack.github.io/GE3D/.

cs.CV↗

arXiv2025

ALCS: An Adaptive Latency Compensation Scheduler for Multipath TCP in Satellite-Terrestrial Integrated Networks

The Satellite-Terrestrial Integrated Network (STIN) enhances end-to-end transmission by simultaneously utilizing terrestrial and satellite networks, offering significant benefits in scenarios like emergency response and cross-continental communication. Low Earth Orbit (LEO) satellite networks offer reduced Round Trip Time (RTT) for long-distance data transmission and serve as a crucial backup during terrestrial network failures. Meanwhile, terrestrial networks are characterized by ample bandwidth resources and generally more stable link conditions. Therefore, integrating Multipath TCP (MPTCP) into STIN is vital for optimizing resource utilization and ensuring efficient data transfer by exploiting the complementary strengths of both networks. However, the inherent challenges of STIN, such as heterogeneity, instability, and handovers, pose difficulties for traditional multipath schedulers, which are typically designed for terrestrial networks. We propose a novel multipath data scheduling approach for STIN, Adaptive Latency Compensation Scheduler (ALCS), to address these issues. ALCS refines transmission latency estimates by incorporating RTT, congestion window size, inflight and queuing packets, and satellite trajectory information. It further employs adaptive mechanisms for latency compensation and proactive handover management. It further employs adaptive mechanisms for latency compensation and proactive handover management. Implemented in the MPTCP Linux Kernel and evaluated in a simulated STIN testbed, ALCS outperforms existing multipath schedulers, delivering faster data transmission and achieving throughput gains of 9.8% to 44.0% compared to benchmark algorithms.

cs.NI↗

arXiv2025

Ev-Layout: A Large-scale Event-based Multi-modal Dataset for Indoor Layout Estimation and Tracking

This paper presents Ev-Layout, a novel large-scale event-based multi-modal dataset designed for indoor layout estimation and tracking. Ev-Layout makes key contributions to the community by: Utilizing a hybrid data collection platform (with a head-mounted display and VR interface) that integrates both RGB and bio-inspired event cameras to capture indoor layouts in motion. Incorporating time-series data from inertial measurement units (IMUs) and ambient lighting conditions recorded during data collection to highlight the potential impact of motion speed and lighting on layout estimation accuracy. The dataset consists of 2.5K sequences, including over 771.3K RGB images and 10 billion event data points. Of these, 39K images are annotated with indoor layouts, enabling research in both event-based and video-based indoor layout estimation. Based on the dataset, we propose an event-based layout estimation pipeline with a novel event-temporal distribution feature module to effectively aggregate the spatio-temporal information from events. Additionally, we introduce a spatio-temporal feature fusion module that can be easily integrated into a transformer module for fusion purposes. Finally, we conduct benchmarking and extensive experiments on the Ev-Layout dataset, demonstrating that our approach significantly improves the accuracy of dynamic indoor layout estimation compared to existing event-based methods.

cs.GR↗

arXiv2025

YouthCare: Building a Personalized Collaborative Video Censorship Tool to Support Parent-Child Joint Media Engagement

To mitigate the negative impacts of online videos on teenagers, existing research and platforms have implemented various parental mediation mechanisms, such as Parent-Child Joint Media Engagement (JME). However, JME generally relies heavily on parents' time, knowledge, and experience. To fill this gap, we aim to design an automatic tool to help parents/children censor videos more effectively and efficiently in JME. For this goal, we first conducted a formative study to identify the needs and expectations of teenagers and parents for such a system. Based on the findings, we designed YouthCare, a personalized collaborative video censorship tool that supports parents and children to collaboratively filter out inappropriate content and select appropriate content in JME. An evaluation with 10 parent-child pairs demonstrated YouthCare's several strengths in supporting video censorship, while also highlighting some potential problems. These findings inspire us to propose several insights for the future design of parent-child collaborative JME systems.

cs.HC↗

arXiv2025

Predicting Long-term Urban Overheating and Their Mitigations from Nature Based Solutions Using Machine Learning and Field Measurements

Urban overheating, exacerbated by climate change, threatens public health and urban sustainability. Traditional approaches, such as numerical simulations and field measurements, face challenges due to uncertainties in input data. This study integrates field measurements with machine learning models to predict the duration and severity of future urban overheating events, focusing on the role of urban greening under different global warming (GW) scenarios. Field measurements were conducted in summer 2024 at an office campus in Ottawa, a cold-climate city. Microclimate data were collected from four locations with varying levels of greenery: a large lawn without trees (Lawn), a parking lot without greenery (Parking), an area with sparsely distributed trees (Tree), and a fully covered forested area (Forest). Machine learning models, including Artificial Neural Networks (ANN), Recurrent Neural Networks (RNN), and Long Short-Term Memory (LSTM) networks, were trained on local microclimate data, with LSTM achieving the best predictions. Four GW scenarios were analyzed, corresponding to different Shared Socioeconomic Pathways (SSP) for 2050 and 2090. Results show that the Universal Thermal Climate Index (UTCI) at the "Parking" location rises from about 27,\textdegree C under GW1.0 to 31,\textdegree C under GW3.5. Moreover, low health risk conditions (UTCI > 26,\textdegree C) increase across all locations due to climate change, regardless of greenery levels. However, tree-covered areas such as "Tree" and "Forest" effectively prevent extreme heat conditions (UTCI > 38.9,\textdegree C). These findings highlight the crucial role of urban greening in mitigating severe thermal stress and enhancing thermal comfort under future climate scenarios.

stat.AP↗

arXiv2025

It Takes Two to Tango: Serverless Workflow Serving via Bilaterally Engaged Resource Adaptation

Serverless platforms typically adopt an early-binding approach for function sizing, requiring developers to specify an immutable size for each function within a workflow beforehand. Accounting for potential runtime variability, developers must size functions for worst-case scenarios to ensure service-level objectives (SLOs), resulting in significant resource inefficiency. To address this issue, we propose Janus, a novel resource adaptation framework for serverless platforms. Janus employs a late-binding approach, allowing function sizes to be dynamically adapted based on runtime conditions. The main challenge lies in the information barrier between the developer and the provider: developers lack access to runtime information, while providers lack domain knowledge about the workflow. To bridge this gap, Janus allows developers to provide hints containing rules and options for resource adaptation. Providers then follow these hints to dynamically adjust resource allocation at runtime based on real-time function execution information, ensuring compliance with SLOs. We implement Janus and conduct extensive experiments with real-world serverless workflows. Our results demonstrate that Janus enhances resource efficiency by up to 34.7% compared to the state-of-the-art.

cs.DC↗

arXiv2025

When Data Manipulation Meets Attack Goals: An In-depth Survey of Attacks for VLMs

Vision-Language Models (VLMs) have gained considerable prominence in recent years due to their remarkable capability to effectively integrate and process both textual and visual information. This integration has significantly enhanced performance across a diverse spectrum of applications, such as scene perception and robotics. However, the deployment of VLMs has also given rise to critical safety and security concerns, necessitating extensive research to assess the potential vulnerabilities these VLM systems may harbor. In this work, we present an in-depth survey of the attack strategies tailored for VLMs. We categorize these attacks based on their underlying objectives - namely jailbreak, camouflage, and exploitation - while also detailing the various methodologies employed for data manipulation of VLMs. Meanwhile, we outline corresponding defense mechanisms that have been proposed to mitigate these vulnerabilities. By discerning key connections and distinctions among the diverse types of attacks, we propose a compelling taxonomy for VLM attacks. Moreover, we summarize the evaluation metrics that comprehensively describe the characteristics and impact of different attacks on VLMs. Finally, we conclude with a discussion of promising future research directions that could further enhance the robustness and safety of VLMs, emphasizing the importance of ongoing exploration in this critical area of study. To facilitate community engagement, we maintain an up-to-date project page, accessible at: https://github.com/AobtDai/VLM_Attack_Paper_List.

cs.CV↗

arXiv2025

IU4Rec: Interest Unit-Based Product Organization and Recommendation for E-Commerce Platform

Most recommendation systems typically follow a product-based paradigm utilizing user-product interactions to identify the most engaging items for users. However, this product-based paradigm has notable drawbacks for Xianyu~\footnote{Xianyu is China's largest online C2C e-commerce platform where a large portion of the product are post by individual sellers}. Most of the product on Xianyu posted from individual sellers often have limited stock available for distribution, and once the product is sold, it's no longer available for distribution. This result in most items distributed product on Xianyu having relatively few interactions, affecting the effectiveness of traditional recommendation depending on accumulating user-item interactions. To address these issues, we introduce \textbf{IU4Rec}, an \textbf{I}nterest \textbf{U}nit-based two-stage \textbf{Rec}ommendation system framework. We first group products into clusters based on attributes such as category, image, and semantics. These IUs are then integrated into the Recommendation system, delivering both product and technological innovations. IU4Rec begins by grouping products into clusters based on attributes such as category, image, and semantics, forming Interest Units (IUs). Then we redesign the recommendation process into two stages. In the first stage, the focus is on recommend these Interest Units, capturing broad-level interests. In the second stage, it guides users to find the best option among similar products within the selected Interest Unit. User-IU interactions are incorporated into our ranking models, offering the advantage of more persistent IU behaviors compared to item-specific interactions. Experimental results on the production dataset and online A/B testing demonstrate the effectiveness and superiority of our proposed IU-centric recommendation approach.

cs.IR↗

arXiv2025

A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision

Omnidirectional image (ODI) data is captured with a field-of-view of 360x180, which is much wider than the pinhole cameras and captures richer surrounding environment details than the conventional perspective images. In recent years, the availability of customer-level 360 cameras has made omnidirectional vision more popular, and the advance of deep learning (DL) has significantly sparked its research and applications. This paper presents a systematic and comprehensive review and analysis of the recent progress of DL for omnidirectional vision. It delineates the distinct challenges and complexities encountered in applying DL to omnidirectional images as opposed to traditional perspective imagery. Our work covers four main contents: (i) A thorough introduction to the principles of omnidirectional imaging and commonly explored projections of ODI; (ii) A methodical review of varied representation learning approaches tailored for ODI; (iii) An in-depth investigation of optimization strategies specific to omnidirectional vision; (iv) A structural and hierarchical taxonomy of the DL methods for the representative omnidirectional vision tasks, from visual enhancement (e.g., image generation and super-resolution) to 3D geometry and motion estimation (e.g., depth and optical flow estimation), alongside the discussions on emergent research directions; (v) An overview of cutting-edge applications (e.g., autonomous driving and virtual reality), coupled with a critical discussion on prevailing challenges and open questions, to trigger more research in the community.

cs.CV↗

arXiv2025

Rethinking Knowledge in Distillation: An In-context Sample Retrieval Perspective

Conventional knowledge distillation (KD) approaches are designed for the student model to predict similar output as the teacher model for each sample. Unfortunately, the relationship across samples with same class is often neglected. In this paper, we explore to redefine the knowledge in distillation, capturing the relationship between each sample and its corresponding in-context samples (a group of similar samples with the same or different classes), and perform KD from an in-context sample retrieval perspective. As KD is a type of learned label smoothing regularization (LSR), we first conduct a theoretical analysis showing that the teacher's knowledge from the in-context samples is a crucial contributor to regularize the student training with the corresponding samples. Buttressed by the analysis, we propose a novel in-context knowledge distillation (IC-KD) framework that shows its superiority across diverse KD paradigms (offline, online, and teacher-free KD). Firstly, we construct a feature memory bank from the teacher model and retrieve in-context samples for each corresponding sample through retrieval-based learning. We then introduce Positive In-Context Distillation (PICD) to reduce the discrepancy between a sample from the student and the aggregated in-context samples with the same class from the teacher in the logit space. Moreover, Negative In-Context Distillation (NICD) is introduced to separate a sample from the student and the in-context samples with different classes from the teacher in the logit space. Extensive experiments demonstrate that IC-KD is effective across various types of KD, and consistently achieves state-of-the-art performance on CIFAR-100 and ImageNet datasets.

cs.CV↗

arXiv2025

Polarization Profiles of Globular Cluster Pulsars from FAST I. 25 Profiles from Previously Known Pulsars

Pulsar polarization profiles are critical for understanding their magnetospheric structures and radiation mechanisms. We present polarization profile measurements for 25 pulsars in globular clusters (GCs) from the observation of the Five-hundred-meter Aperture Spherical radio Telescope (FAST). The diversity of polarization profiles shows complex magnetic structure and emission pattern of pulsars. Among these, the polarization profiles of 15 pulsars were firstly measured. M53A present a 57\% linear polarization ratio, being highest among these 25 GC pulsars. M15H present a 42\% circular polarization ratio, which is the highest among these 25 pulsars. The average ratios of circular and absolute circular polarization of these GC pulsars are -1\% and 10\% respectively, lower than normal pulsars measured with Parkes (\citealt{Oswald2023}), which are 5\% and 32\%, respectively. The Rotation Measure (RM) values of each pulsar were measured, giving the range of pulsar(s) from M3, M5, M15, M71, M53, NGC6517, NGC6539, NGC6760 being 8(1) to 16(1) rad $m^{-2}$, -1(2) to -4(6) rad $m^{-2}$, -70(2) to -76(1) rad $m^{-2}$, -480(14) rad $m^{-2}$ (M71A only), -2(1) rad $m^{-2}$ (M53A only), 187(1) to 212(2) rad $m^{-2}$, 109(1) rad $m^{-2}$ (NGC6539A only), and 102(1) to 129(4) rad $m^{-2}$. The GCs closer to the Galactic plane (GP) tend to have larger RM. This is consistent with previous study (\citealt{Hutschenreuter2022}).

astro-ph.HE↗

arXiv2024

MAGIC++: Efficient and Resilient Modality-Agnostic Semantic Segmentation via Hierarchical Modality Selection

In this paper, we address the challenging modality-agnostic semantic segmentation (MaSS), aiming at centering the value of every modality at every feature granularity. Training with all available visual modalities and effectively fusing an arbitrary combination of them is essential for robust multi-modal fusion in semantic segmentation, especially in real-world scenarios, yet remains less explored to date. Existing approaches often place RGB at the center, treating other modalities as secondary, resulting in an asymmetric architecture. However, RGB alone can be limiting in scenarios like nighttime, where modalities such as event data excel. Therefore, a resilient fusion model must dynamically adapt to each modality's strengths while compensating for weaker inputs.To this end, we introduce the MAGIC++ framework, which comprises two key plug-and-play modules for effective multi-modal fusion and hierarchical modality selection that can be equipped with various backbone models. Firstly, we introduce a multi-modal interaction module to efficiently process features from the input multi-modal batches and extract complementary scene information with channel-wise and spatial-wise guidance. On top, a unified multi-scale arbitrary-modal selection module is proposed to utilize the aggregated features as the benchmark to rank the multi-modal features based on the similarity scores at hierarchical feature spaces. This way, our method can eliminate the dependence on RGB modality at every feature granularity and better overcome sensor failures and environmental noises while ensuring the segmentation performance. Under the common multi-modal setting, our method achieves state-of-the-art performance on both real-world and synthetic benchmarks. Moreover, our method is superior in the novel modality-agnostic setting, where it outperforms prior arts by a large margin.

cs.CV↗

arXiv2024

TouchASP: Elastic Automatic Speech Perception that Everyone Can Touch

Large Automatic Speech Recognition (ASR) models demand a vast number of parameters, copious amounts of data, and significant computational resources during the training process. However, such models can merely be deployed on high-compute cloud platforms and are only capable of performing speech recognition tasks. This leads to high costs and restricted capabilities. In this report, we initially propose the elastic mixture of the expert (eMoE) model. This model can be trained just once and then be elastically scaled in accordance with deployment requirements. Secondly, we devise an unsupervised data creation and validation procedure and gather millions of hours of audio data from diverse domains for training. Using these two techniques, our system achieves elastic deployment capabilities while reducing the Character Error Rate (CER) on the SpeechIO testsets from 4.98\% to 2.45\%. Thirdly, our model is not only competent in Mandarin speech recognition but also proficient in multilingual, multi-dialect, emotion, gender, and sound event perception. We refer to this as Automatic Speech Perception (ASP), and the perception results are presented in the experimental section.

eess.AS↗

arXiv2024

MetaRuleGPT: Recursive Numerical Reasoning of Language Models Trained with Simple Rules

Recent studies have highlighted the limitations of large language models in mathematical reasoning, particularly their inability to capture the underlying logic. Inspired by meta-learning, we propose that models should acquire not only task-specific knowledge but also transferable problem-solving skills. We introduce MetaRuleGPT, a novel Transformer-based architecture that performs precise numerical calculations and complex logical operations by learning and combining different rules. In contrast with traditional training sets, which are heavily composed of massive raw instance data, MetaRuleGPT is pre-trained on much less abstract datasets containing basic, compound, and iterative rules for mathematical reasoning. Extensive experimental results demonstrate MetaRuleGPT can mimic human's rule-following capabilities, break down complexity, and iteratively derive accurate results for complex mathematical problems. These findings prove the potential of rule learning to enhance the numerical reasoning abilities of language models.

cs.CL↗

arXiv2024

Recent Trends in Linear Text Segmentation: a Survey

Linear Text Segmentation is the task of automatically tagging text documents with topic shifts, i.e. the places in the text where the topics change. A well-established area of research in Natural Language Processing, drawing from well-understood concepts in linguistic and computational linguistic research, the field has recently seen a lot of interest as a result of the surge of text, video, and audio available on the web, which in turn require ways of summarising and categorizing the mole of content for which linear text segmentation is a fundamental step. In this survey, we provide an extensive overview of current advances in linear text segmentation, describing the state of the art in terms of resources and approaches for the task. Finally, we highlight the limitations of available resources and of the task itself, while indicating ways forward based on the most recent literature and under-explored research directions.

cs.CL↗

arXiv2024

BrightDreamer: Generic 3D Gaussian Generative Framework for Fast Text-to-3D Synthesis

Text-to-3D synthesis has recently seen intriguing advances by combining the text-to-image priors with 3D representation methods, e.g., 3D Gaussian Splatting (3D GS), via Score Distillation Sampling (SDS). However, a hurdle of existing methods is the low efficiency, per-prompt optimization for a single 3D object. Therefore, it is imperative for a paradigm shift from per-prompt optimization to feed-forward generation for any unseen text prompts, which yet remains challenging. An obstacle is how to directly generate a set of millions of 3D Gaussians to represent a 3D object. This paper presents BrightDreamer, an end-to-end feed-forward approach that can achieve generalizable and fast (77 ms) text-to-3D generation. Our key idea is to formulate the generation process as estimating the 3D deformation from an anchor shape with predefined positions. For this, we first propose a Text-guided Shape Deformation (TSD) network to predict the deformed shape and its new positions, used as the centers (one attribute) of 3D Gaussians. To estimate the other four attributes (i.e., scaling, rotation, opacity, and SH), we then design a novel Text-guided Triplane Generator (TTG) to generate a triplane representation for a 3D object. The center of each Gaussian enables us to transform the spatial feature into the four attributes. The generated 3D Gaussians can be finally rendered at 705 frames per second. Extensive experiments demonstrate the superiority of our method over existing methods. Also, BrightDreamer possesses a strong semantic understanding capability even for complex text prompts. The code is available in the project page.

cs.CV↗

arXiv2024

3D microstructural generation from 2D images of cement paste using generative adversarial networks

Establishing a realistic three-dimensional (3D) microstructure is a crucial step for studying microstructure development of hardened cement pastes. However, acquiring 3D microstructural images for cement often involves high costs and quality compromises. This paper proposes a generative adversarial networks-based method for generating 3D microstructures from a single two-dimensional (2D) image, capable of producing high-quality and realistic 3D images at low cost. In the method, a framework (CEM3DMG) is designed to synthesize 3D images by learning microstructural information from a 2D cross-sectional image. Experimental results show that CEM3DMG can generate realistic 3D images of large size. Visual observation confirms that the generated 3D images exhibit similar microstructural features to the 2D images, including similar pore distribution and particle morphology. Furthermore, quantitative analysis reveals that reconstructed 3D microstructures closely match the real 2D microstructure in terms of gray level histogram, phase proportions, and pore size distribution. The source code for CEM3DMG is available in the GitHub repository at: https://github.com/NBICLAB/CEM3DMG.

eess.IV↗