arXiv subjects

Yuxiang Shen

Publications and source records attributed to Yuxiang Shen.

5 recordsLinked to original sources

arXiv2026

HoRFFI: High-Openness RF Fingerprint Identification with a Similarity-Enhanced Variational Information Bottleneck

Radio frequency fingerprint identification (RFFI) is a promising technique for wireless device authentication. However, practical RFFI systems must enroll newly authorized devices while rejecting previously unseen ones, even when the feature extractor is trained on only a few labeled base-device classes, giving rise to a high-openness RFFI problem. Existing open-set recognition methods typically rely on feature spaces learned from a large and diverse set of known-device classes, limiting their applicability in practical scenarios. To address this challenge, we propose HoRFFI, a high-openness RFFI framework that supports scalable device identification and unknown-device rejection using only a small number of labeled training devices. HoRFFI employs a similarity-enhanced variational information bottleneck (SVIB)-based supervision mechanism, which reduces the encoder's dependence on training-class diversity and learns a more transferable embedding space. This supervision mechanism uses feature-space augmentation and clustering to derive inter-sample similarity information, which provides supplementary supervision for regularizing the embedding space. Experiments on public LoRa and Wi-Fi datasets show that HoRFFI achieves absolute improvements of $0.112$ and $0.288$ in novel-class accuracy, respectively, and corresponding absolute AUC improvements of $0.029$ and $0.060$ over the best-performing baselines.

cs.CR↗

arXiv2026

LookWise: Knowing When and Where to Look for Fine-Grained Visual Reasoning in Multimodal Large Language Models

Multimodal Large Language Models (MLLMs) are shifting towards "Thinking with Images" by actively exploring image details. While effective, large-scale training is computationally expensive, which has spurred growing interest in lightweight, training-free solutions. However, existing training-free methods suffer from two flaws: perceptual redundancy from indiscriminate cropping, which increases computational cost and introduces noise; and a drift between semantic intent and spatial attention, which prevents accurate localization of user-focused regions. To address these challenges, we propose LookWise, a framework for adaptive visual reasoning. LookWise follows a two-stage pipeline: a confidence-based module decides when to look more carefully, and a semantic-guided localization module determines where to look. This design enables MLLMs to adaptively acquire fine-grained visual evidence without additional training. Experiments on fine-grained and high-resolution visual reasoning benchmarks show that LookWise consistently improves accuracy over strong baselines while achieving an approximately $4.0\times$ inference speedup over the search-based method ZoomEye, demonstrating robust cross-model generalization.

cs.CV↗

arXiv2025

LLaVA-RadZ: Can Multimodal Large Language Models Effectively Tackle Zero-shot Radiology Recognition?

Recently, Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in visual understanding and reasoning across various vision-language tasks. However, we found that MLLMs cannot process effectively from fine-grained medical image data in the traditional Visual Question Answering (VQA) pipeline, as they do not exploit the captured features and available medical knowledge fully, results in MLLMs usually performing poorly in zero-shot medical disease recognition. Fortunately, this limitation does not indicate that MLLMs are fundamentally incapable of addressing fine-grained recognition tasks. From a feature representation perspective, MLLMs demonstrate considerable potential for tackling such challenging problems. Thus, to address this challenge, we propose LLaVA-RadZ, a simple yet effective framework for zero-shot medical disease recognition via utilizing the existing MLLM features. Specifically, we design an end-to-end training strategy, termed Decoding-Side Feature Alignment Training (DFAT) to take advantage of the characteristics of the MLLM decoder architecture and incorporate modality-specific tokens tailored for different modalities. Additionally, we introduce a Domain Knowledge Anchoring Module (DKAM) to exploit the intrinsic medical knowledge of large models, which mitigates the category semantic gap in image-text alignment. Extensive experiments demonstrate that our LLaVA-RadZ significantly outperforms traditional MLLMs in zero-shot disease recognition, achieving the comparable performance to the well-established and highly-optimized CLIP-based approaches.

cs.CV↗

arXiv2025

IFShip: Interpretable Fine-grained Ship Classification with Domain Knowledge-Enhanced Vision-Language Models

End-to-end interpretation currently dominates the remote sensing fine-grained ship classification (RS-FGSC) task. However, the inference process remains uninterpretable, leading to criticisms of these models as "black box" systems. To address this issue, we propose a domain knowledge-enhanced Chain-of-Thought (CoT) prompt generation mechanism, which is used to semi-automatically construct a task-specific instruction-following dataset, TITANIC-FGS. By training on TITANIC-FGS, we adapt general-domain vision-language models (VLMs) to the FGSC task, resulting in a model named IFShip. Building upon IFShip, we develop an FGSC visual chatbot that redefines the FGSC problem as a step-by-step reasoning task and conveys the reasoning process in natural language. Experimental results show that IFShip outperforms state-of-the-art FGSC algorithms in both interpretability and classification accuracy. Furthermore, compared to VLMs such as LLaVA and MiniGPT-4, IFShip demonstrates superior performance on the FGSC task. It provides an accurate chain of reasoning when fine-grained ship types are recognizable to the human eye and offers interpretable explanations when they are not. Our dataset is publicly available at: https://github.com/lostwolves/IFShip.

cs.CL↗

arXiv2020

Elementary Properties of Positive Concave Mappings with Applications to Network Planning and Optimization

This study presents novel methods for computing fixed points of positive concave mappings and for characterizing the existence of fixed points. These methods are particularly important in planning and optimization tasks in wireless networks. For example, previous studies have shown that the feasibility of a network design can be quickly evaluated by computing the fixed point of a concave mapping that is constructed based on many environmental and network control parameters such as the position of base stations, channel conditions, and antenna tilts. To address this and more general problems, given a positive concave mapping, we show two alternative but equivalent ways to construct a matrix that is guaranteed to have spectral radius strictly smaller than one if the mapping has a fixed point. This matrix is then used to build a new mapping that preserves the fixed point of the original positive concave mapping. We show that the standard fixed point iterations using the new mapping converges faster than the standard iterations applied to the original concave mapping. As exemplary applications of the proposed methods, we consider the problems of power and load planning in networks based on the orthogonal frequency division multiple access (OFDMA) technology.

cs.IT↗