arXiv subjects

Bin Chen

Publications and source records attributed to Bin Chen.

At least 253 records · Page 14Linked to original sources

arXiv2025

Assessing Color Vision Test in Large Vision-language Models

With the widespread adoption of large vision-language models, the capacity for color vision in these models is crucial. However, the color vision abilities of large visual-language models have not yet been thoroughly explored. To address this gap, we define a color vision testing task for large vision-language models and construct a dataset \footnote{Anonymous Github Showing some of the data https://anonymous.4open.science/r/color-vision-test-dataset-3BCD} that covers multiple categories of test questions and tasks of varying difficulty levels. Furthermore, we analyze the types of errors made by large vision-language models and propose fine-tuning strategies to enhance their performance in color vision tests.

cs.CV↗

arXiv2025

Near-Horizon Polarization as a Diagnostic of Black Hole Spacetime

A key challenge in imaging supermassive black holes is disentangling gravitational effects from plasma physics in order to accurately determine spacetime properties, particularly black hole spin. In this Letter, we present a fully covariant and rigorous analysis of the synchrotron emission from accreting plasma in the equatorial plane in the stationary, axisymmetric, high-conductivity regime, and identify--for the first time--a distinctive near-horizon polarization pattern that remains robust across different flow structures. This pattern arises from strong frame dragging near the event horizon, which induces a degeneracy among plasma flow and magnetic field configurations, yielding a polarization signature determined solely by the spacetime geometry and the observer's inclination. The near-horizon polarization thus offers a clean and precise probe of black hole spin and other fundamental parameters. If future space-based millimeter VLBI observations can resolve synchrotron emission originating within approximately 1$\%$ of the event horizon radius in M87* or Sgr A*, this universal polarization pattern may become observable.

gr-qc↗

arXiv2025

Analytical Model for Light Scattering in Transparent Composites

Transparent composites that combine optical transmittance with mechanical performance are increasingly important for applications in optical devices, sustainable building materials, and photonic engineering. However, predicting light scattering in such materials remains a challenge due to complex, multi-scale microstructural interactions. Here, we present a physically grounded and computationally efficient analytical model. It predicts angular light scattering in transparent composites based on the Average Interface Number (AIN), a single governing microstructural metric derived in this work from geometrical optics. The model accurately captures angular scattering behavior in both fiber- and particle-reinforced composites, as well as in transparent wood. We further introduce the Equivalent Average Interface Number (EAIN), combining AIN with refractive index mismatch into a unified parameter for fast haze prediction. Deep neural network (DNN) analyses confirm AIN as the dominant feature influencing optical scattering. The model predictions are supported by ray-tracing simulations and experimental trends from literature. Finally, we demonstrate the application of our model in fast image rendering simulations through transparent composites. This work provides a compact and practical toolbox for optical design and optimization of transparent structural materials.

physics.optics↗

arXiv2025

Chain-of-Memory: Enhancing GUI Agents for Cross-Application Navigation

Multimodal large language models (MLLMs) are attracting growing attention in the development of Graphical User Interface (GUI) agents. Existing approaches often rely on historical screenshots or actions to implicitly represent the task state. This reliance poses challenges for GUI agents in accurately understanding task states and underscores the absence of effective mechanisms to store critical information in complex and lengthy cross-app tasks. To address these challenges, we propose Chain-of-Memory (CoM), a novel approach for explicitly modeling short-term and long-term memory in GUI agents. CoM achieves this by capturing action descriptions, integrating task-relevant screen information, and maintaining a dedicated memory module to store and manage this information. By leveraging explicit memory representations, CoM enables GUI agents to better understand task states and retain critical historical information persistently. To equip GUI agents with memory management capabilities and evaluate the effectiveness of CoM, we developed the GUI Odyssey-CoM, a dataset comprising 111k screen-action pairs annotated with Chain-of-Memory. Experimental results demonstrate that CoM significantly improves GUI agents' performance in cross-application tasks. Additionally, GUI Odyssey-CoM enables 7B models to achieve memory management capabilities comparable to 72B models. The dataset and code will be open-sourced.

cs.AI↗

arXiv2025

ReasonGRM: Enhancing Generative Reward Models through Large Reasoning Models

Generative Reward Models (GRMs) provide greater flexibility than scalar reward models in capturing human preferences, but their effectiveness is limited by poor reasoning capabilities. This often results in incomplete or overly speculative reasoning paths, leading to hallucinations or missing key information in complex tasks. We address this challenge with ReasonGRM, a three-stage generative reward modeling framework. In the first stage, Zero-RL is used to generate concise, outcome-directed reasoning paths that reduce the likelihood of critical omissions. In the second stage, we introduce a novel evaluation metric, $R^\star$, which scores reasoning paths based on their generation likelihood. This favors paths that reach correct answers with minimal exploration, helping to reduce hallucination-prone data during training. In the final stage, the model is further refined through reinforcement learning on challenging examples to enhance its preference discrimination capabilities. Experiments on three public benchmarks show that ReasonGRM achieves competitive or state-of-the-art performance, outperforming previous best GRMs by 1.8\% on average and surpassing proprietary models such as GPT-4o by up to 5.6\%. These results demonstrate the effectiveness of reasoning-aware training and highlight the importance of high-quality rationale selection for reliable preference modeling.

cs.CL↗

arXiv2025

NTIRE 2025 Image Shadow Removal Challenge Report

This work examines the findings of the NTIRE 2025 Shadow Removal Challenge. A total of 306 participants have registered, with 17 teams successfully submitting their solutions during the final evaluation phase. Following the last two editions, this challenge had two evaluation tracks: one focusing on reconstruction fidelity and the other on visual perception through a user study. Both tracks were evaluated with images from the WSRD+ dataset, simulating interactions between self- and cast-shadows with a large number of diverse objects, textures, and materials.

cs.CV↗

arXiv2025

A Comprehensive Survey on Underwater Acoustic Target Positioning and Tracking: Progress, Challenges, and Perspectives

Underwater target tracking technology plays a pivotal role in marine resource exploration, environmental monitoring, and national defense security. Given that acoustic waves represent an effective medium for long-distance transmission in aquatic environments, underwater acoustic target tracking has become a prominent research area of underwater communications and networking. Existing literature reviews often offer a narrow perspective or inadequately address the paradigm shifts driven by emerging technologies like deep learning and reinforcement learning. To address these gaps, this work presents a systematic survey of this field and introduces an innovative multidimensional taxonomy framework based on target scale, sensor perception modes, and sensor collaboration patterns. Within this framework, we comprehensively survey the literature (more than 180 publications) over the period 2016-2025, spanning from the theoretical foundations to diverse algorithmic approaches in underwater acoustic target tracking. Particularly, we emphasize the transformative potential and recent advancements of machine learning techniques, including deep learning and reinforcement learning, in enhancing the performance and adaptability of underwater tracking systems. Finally, this survey concludes by identifying key challenges in the field and proposing future avenues based on emerging technologies such as federated learning, blockchain, embodied intelligence, and large models.

eess.SP↗

arXiv2025

Noise in Maps of the Sun at Radio Wavelengths II: Solar Use Cases

Noise in images of strong celestial sources at radio wavelengths using Fourier synthesis arrays can be dominated by the source itself, so-called self-noise. We outlined the theory of self-noise for strong sources in a companion paper. Here we consider the case of noise in maps of radio emission from the Sun which, as we show, is always dominated by self noise. We consider several classes of science use cases for current and planned arrays designed to observe the Sun in order to understand limitations imposed by self-noise. We focus on instruments operating at decimeter and centimeter wavelengths but the results are applicable to other wavelength regimes.

astro-ph.SR↗

arXiv2025

Noise in Maps of the Sun at Radio Wavelengths I: Theoretical Considerations

The Sun is a powerful source of radio emissions, so much so that, unlike most celestial sources, this emission can dominate the system noise of radio telescopes. We outline the theory of noise in maps formed by Fourier synthesis techniques at radio wavelengths, with a focus on self-noise: that is, noise due to the source itself. As a means of developing intuition we consider noise for the case of a single dish, a two-element interferometer, and an n-element array for simple limiting cases. We then turn to the question of the distribution of noise on a map of an arbitrary source observed at radio wavelengths by an n-element interferometric array. We consider the implications of self-noise for observations of the Sun in a companion paper.

astro-ph.SR↗

arXiv2025

Point Cloud Mixture-of-Domain-Experts Model for 3D Self-supervised Learning

Point clouds, as a primary representation of 3D data, can be categorized into scene domain point clouds and object domain point clouds. Point cloud self-supervised learning (SSL) has become a mainstream paradigm for learning 3D representations. However, existing point cloud SSL primarily focuses on learning domain-specific 3D representations within a single domain, neglecting the complementary nature of cross-domain knowledge, which limits the learning of 3D representations. In this paper, we propose to learn a comprehensive Point cloud Mixture-of-Domain-Experts model (Point-MoDE) via a block-to-scene pre-training strategy. Specifically, we first propose a mixture-of-domain-expert model consisting of scene domain experts and multiple shared object domain experts. Furthermore, we propose a block-to-scene pretraining strategy, which leverages the features of point blocks in the object domain to regress their initial positions in the scene domain through object-level block mask reconstruction and scene-level block position regression. By integrating the complementary knowledge between object and scene, this strategy simultaneously facilitates the learning of both object-domain and scene-domain representations, leading to a more comprehensive 3D representation. Extensive experiments in downstream tasks demonstrate the superiority of our model.

cs.CV↗

arXiv2025

Delayed phosphate release can highly improve energy efficiency of muscle contraction

While the power stroke of myosin and the release of inorganic phosphate (Pi) play crucial roles in transforming ATP's chemical energy into mechanical work across diverse biological systems, the exact temporal relationship between these events continues to be intensely debated. In this study, from a functional perspective, we computationally investigate the impact of Pi-release kinetics during the power stroke on muscle contraction dynamics. By implementing a mechanics model of the sarcomere unit that comprehensively incorporates the chemomechanical cycle of individual myosin molecules, we successfully replicate a broad range of experimental observations through parameter variation. Our simulation results reveal that delayed Pi-release can significantly enhance energy efficiency during muscle contraction. This work suggests that a gradual Pi-release that is not directly coupled with the lever arm swing may offer a route to adjust the stability of a working myosin on the actin filament, thereby modulating the power stroke to influence muscle contraction.

physics.bio-ph↗

arXiv2025

Temporal Saliency-Guided Distillation: A Scalable Framework for Distilling Video Datasets

Dataset distillation (DD) has emerged as a powerful paradigm for dataset compression, enabling the synthesis of compact surrogate datasets that approximate the training utility of large-scale ones. While significant progress has been achieved in distilling image datasets, extending DD to the video domain remains challenging due to the high dimensionality and temporal complexity inherent in video data. Existing video distillation (VD) methods often suffer from excessive computational costs and struggle to preserve temporal dynamics, as naïve extensions of image-based approaches typically lead to degraded performance. In this paper, we propose a novel uni-level video dataset distillation framework that directly optimizes synthetic videos with respect to a pre-trained model. To address temporal redundancy and enhance motion preservation, we introduce a temporal saliency-guided filtering mechanism that leverages inter-frame differences to guide the distillation process, encouraging the retention of informative temporal cues while suppressing frame-level redundancy. Extensive experiments on standard video benchmarks demonstrate that our method achieves state-of-the-art performance, bridging the gap between real and distilled video data and offering a scalable solution for video dataset compression.

cs.CV↗

arXiv2025

PMA: Towards Parameter-Efficient Point Cloud Understanding via Point Mamba Adapter

Applying pre-trained models to assist point cloud understanding has recently become a mainstream paradigm in 3D perception. However, existing application strategies are straightforward, utilizing only the final output of the pre-trained model for various task heads. It neglects the rich complementary information in the intermediate layer, thereby failing to fully unlock the potential of pre-trained models. To overcome this limitation, we propose an orthogonal solution: Point Mamba Adapter (PMA), which constructs an ordered feature sequence from all layers of the pre-trained model and leverages Mamba to fuse all complementary semantics, thereby promoting comprehensive point cloud understanding. Constructing this ordered sequence is non-trivial due to the inherent isotropy of 3D space. Therefore, we further propose a geometry-constrained gate prompt generator (G2PG) shared across different layers, which applies shared geometric constraints to the output gates of the Mamba and dynamically optimizes the spatial order, thus enabling more effective integration of multi-layer information. Extensive experiments conducted on challenging point cloud datasets across various tasks demonstrate that our PMA elevates the capability for point cloud understanding to a new level by fusing diverse complementary intermediate features. Code is available at https://github.com/zyh16143998882/PMA.

cs.CV↗

arXiv2025

ImageRAG: Enhancing Ultra High Resolution Remote Sensing Imagery Analysis with ImageRAG

Ultra High Resolution (UHR) remote sensing imagery (RSI) (e.g. 100,000 $\times$ 100,000 pixels or more) poses a significant challenge for current Remote Sensing Multimodal Large Language Models (RSMLLMs). If choose to resize the UHR image to standard input image size, the extensive spatial and contextual information that UHR images contain will be neglected. Otherwise, the original size of these images often exceeds the token limits of standard RSMLLMs, making it difficult to process the entire image and capture long-range dependencies to answer the query based on the abundant visual context. In this paper, we introduce ImageRAG for RS, a training-free framework to address the complexities of analyzing UHR remote sensing imagery. By transforming UHR remote sensing image analysis task to image's long context selection task, we design an innovative image contextual retrieval mechanism based on the Retrieval-Augmented Generation (RAG) technique, denoted as ImageRAG. ImageRAG's core innovation lies in its ability to selectively retrieve and focus on the most relevant portions of the UHR image as visual contexts that pertain to a given query. Fast path and slow path are proposed in this framework to handle this task efficiently and effectively. ImageRAG allows RSMLLMs to manage extensive context and spatial information from UHR RSI, ensuring the analysis is both accurate and efficient. Codebase will be released in https://github.com/om-ai-lab/ImageRAG

cs.CV↗

arXiv2025

A Study of Semi-Fungible Token based Wi-Fi Access Control

Current Wi-Fi authentication methods face issues such as insufficient security, user privacy leakage, high management costs, and difficulty in billing. To address these challenges, a Wi-Fi access control solution based on blockchain smart contracts is proposed. Firstly, semi-fungible Wi-Fi tokens (SFWTs) are designed using the ERC1155 token standard as credentials for users to access Wi-Fi. Secondly, a Wi-Fi access control system based on SFWTs is developed to securely verify and manage the access rights of Wi-Fi users. Experimental results demonstrate that SFWTs, designed based on the ERC1155 standard, along with the SFWT access right verification process, can significantly reduce Wi-Fi operating costs and authentication time, effectively meeting users' needs for safe and convenient Wi-Fi access.

cs.CR↗

arXiv2025

D3C2-Net: Dual-Domain Deep Convolutional Coding Network for Compressive Sensing

By mapping iterative optimization algorithms into neural networks (NNs), deep unfolding networks (DUNs) exhibit well-defined and interpretable structures and achieve remarkable success in the field of compressive sensing (CS). However, most existing DUNs solely rely on the image-domain unfolding, which restricts the information transmission capacity and reconstruction flexibility, leading to their loss of image details and unsatisfactory performance. To overcome these limitations, this paper develops a dual-domain optimization framework that combines the priors of (1) image- and (2) convolutional-coding-domains and offers generality to CS and other inverse imaging tasks. By converting this optimization framework into deep NN structures, we present a Dual-Domain Deep Convolutional Coding Network (D3C2-Net), which enjoys the ability to efficiently transmit high-capacity self-adaptive convolutional features across all its unfolded stages. Our theoretical analyses and experiments on simulated and real captured data, covering 2D and 3D natural, medical, and scientific signals, demonstrate the effectiveness, practicality, superior performance, and generalization ability of our method over other competing approaches and its significant potential in achieving a balance among accuracy, complexity, and interpretability. Code is available at https://github.com/lwq20020127/D3C2-Net.

cs.CV↗

arXiv2025

Dynamic Spectrum Sharing Based on the Rentable NFT Standard ERC4907

Centralized Dynamic Spectrum Sharing (DSS) faces challenges like data security, high management costs, and limited scalability. To address these issues, a blockchain-based DSS scheme has been proposed in this paper. First, we utilize the ERC4907 standard to mint Non-Fungible Spectrum Tokens (NFSTs) that serve as unique identifiers for spectrum resources and facilitate renting. Next, we develop a smart contract for NFST auctions, ensuring secure spectrum transactions through the auction process. Lastly, we create a Web3 spectrum auction platform where users can access idle spectrum data and participate in auctions for NFST leases corresponding to the available spectrum. Experimental results demonstrate that our NFST, designed according to the ERC4907 standard, effectively meets users' secure and efficient DSS requirements, making it a feasible solution.

cs.NI↗

arXiv2025

Going Beyond Feature Similarity: Effective Dataset Distillation based on Class-Aware Conditional Mutual Information

Dataset distillation (DD) aims to minimize the time and memory consumption needed for training deep neural networks on large datasets, by creating a smaller synthetic dataset that has similar performance to that of the full real dataset. However, current dataset distillation methods often result in synthetic datasets that are excessively difficult for networks to learn from, due to the compression of a substantial amount of information from the original data through metrics measuring feature similarity, e,g., distribution matching (DM). In this work, we introduce conditional mutual information (CMI) to assess the class-aware complexity of a dataset and propose a novel method by minimizing CMI. Specifically, we minimize the distillation loss while constraining the class-aware complexity of the synthetic dataset by minimizing its empirical CMI from the feature space of pre-trained networks, simultaneously. Conducting on a thorough set of experiments, we show that our method can serve as a general regularization method to existing DD methods and improve the performance and training efficiency.

cs.CV↗