arXiv subjects

Hongkun Yang

Publications and source records attributed to Hongkun Yang.

8 recordsLinked to original sources

arXiv2026

PhySR: Physics-Informed Neural Network for Super-Resolution Reconstruction in Radio Synthesis Imaging

Radio telescope arrays are constrained by the number of antennas and baseline distribution, resulting in incomplete spatial-frequency sampling, limited image resolution, and blurring, distortion, and loss of small-scale structures caused by coupling between the primary and synthesized beams. Existing general-purpose model-driven methods remove observational effects sequentially and may accumulate errors, but cannot directly address limited imaging resolution, while data-driven methods lack explicit physical constraints. We propose PhySR, an end-to-end physics-informed neural network that combines a U-Net backbone, dynamic cascaded upsampling, a multiscale feature residual module, and a differentiable physical forward model incorporating the primary beam response, PSF convolution, and scale mapping. PhySR directly reconstructs high-resolution images from low-resolution dirty images without high-resolution labels while maintaining observation-domain consistency. Experiments on simulated SKA-Mid data show that, for 4x super-resolution, PhySR achieves a PSNR of 44.65 dB, an SSIM of 0.9940, and an RMSE of 0.0065. Compared with existing general-purpose methods, PSNR and SSIM improve by approximately 13.23 dB and 0.3760, respectively. Compared with mainstream deep learning models, PSNR and SSIM improve by 6.50 dB and 0.0682, while RMSE decreases by 0.0069. PhySR also remains stable for 2x and 8x super-resolution and achieves low observation-domain consistency errors, demonstrating advantages in coupling-effect removal, small-scale structure recovery, and physical consistency.

astro-ph.IM↗

arXiv2026

N\"ushuVoice: Reviving the Voice of Endangered N\"ushu with Pitch-Aware Text-to-Speech

N\"ushu is an endangered phonetic script historically used by women in Jiangyong County, southern Hunan, China. While existing computational studies of N\"ushu mainly focus on textual digitization and visual recognition, the acoustic reconstruction of its authentic pronunciation remains largely unexplored. Building a N\"ushu text-to-speech (TTS) system is particularly challenging because available recordings are extremely limited and mostly consist of isolated syllable-level pronunciations rather than natural sentence-level utterances. In this work, we introduce N\"ushuVoice, the first TTS benchmark for N\"ushu. We construct a sentence-level N\"ushu text-to-audio dataset that aligns standardized Unicode N\"ushu text, phonetic transcriptions, standard Chinese translations, and archival recordings. To synthesize speech under this extreme low-resource setting, we propose N\"ushu-PitchVITS, an F0-conditioned VITS framework that leverages N\"ushu's five-level pitch notation as an explicit prosodic inductive bias. Experimental results show that N\"ushu-PitchVITS outperforms strong TTS baselines in spectral fidelity, pitch reconstruction, and human-rated intelligibility. We publicly release the dataset and code at: https://anonymous.4open.science/r/Nvshu-TTS-2EB6.

cs.CL↗

arXiv2026

From Inference Efficiency to Embodied Efficiency: Revisiting Efficiency Metrics for Vision-Language-Action Models

Vision-Language-Action (VLA) models have recently enabled embodied agents to perform increasingly complex tasks by jointly reasoning over visual, linguistic, and motor modalities. However, we find that the prevailing notion of ``efficiency'' in current VLA research, characterized by parameters, FLOPs, or token decoding throughput, does not reflect actual performance on robotic platforms. In real-world execution, efficiency is determined by system-level embodied behaviors such as task completion time, trajectory smoothness, cumulative joint rotation, and motion energy. Through controlled studies across model compression, token sparsification, and action sequence compression, we make several observations that challenge common assumptions. (1) Methods that reduce computation under conventional metrics often increase end-to-end execution cost or degrade motion quality, despite maintaining task success rates. (2) System-level embodied efficiency metrics reveal performance differences in the learned action policies that remain hidden under conventional evaluations. (3) Common adaptation methods such as in-context prompting or supervised fine-tuning show only mild and metric-specific improvements in embodied efficiency. While these methods can reduce targeted embodied-efficiency metrics such as jerk or action rate, the resulting gains may come with trade-offs in other metrics, such as longer completion time. Taken together, our results suggest that conventional inference efficiency metrics can overlook important aspects of embodied execution. Incorporating embodied efficiency provides a more complete view of policy behavior and practical performance, enabling fairer and more comprehensive comparisons of VLA models.

cs.LG↗

arXiv2026

DeAR: Fine-Grained VLM Adaptation by Decomposing Attention Head Roles

Prompt learning is a dominant paradigm for adapting pre-trained Vision-Language Models (VLMs) to downstream tasks. However, existing methods often rely on a simplistic, layer-centric view, assuming shallow layers capture general features while deep layers handle task-specific knowledge. This assumption results in uncontrolled interactions between learnable tokens and original tokens. Task-specific knowledge could degrades the model's core generalization and creates a trade-off between task adaptation and the preservation of zero-shot generalization. To address this, we challenge the layer-centric view and propose \textbf{DeAR}, a framework that achieves fine-grained VLM adaptation by \textbf{De}composing \textbf{A}ttention head \textbf{R}oles. We posit that the functional specialization within VLMs occurs not between layers, but at the finer-grained level of individual attention heads in the deeper layers. Based on this insight, we introduce a novel metric, Concept Entropy, to systematically classify attention heads into distinct functional roles: \textit{Attribute}, \textit{Generalization}, and \textit{Mixed}. Guided by these roles, we introduce specialized attribute tokens and a Role-Based Attention Mask mechanism to precisely control information flow, ensuring generalization heads remain isolated from task-specific knowledge. We further incorporate a Task-Adaptive Fusion Strategy for inference. Extensive experiments on fifteen datasets show that DeAR achieves a strong balance between task adaptation and generalization, outperforming previous methods across various tasks.

cs.CV↗

arXiv2026

How Implicit Bias Accumulates and Propagates in LLM Long-term Memory

Long-term memory mechanisms enable Large Language Models (LLMs) to maintain continuity and personalization across extended interaction lifecycles, but they also introduce new and underexplored risks related to fairness. In this work, we study how implicit bias, defined as subtle statistical prejudice, accumulates and propagates within LLMs equipped with long-term memory. To support systematic analysis, we introduce the Decision-based Implicit Bias (DIB) Benchmark, a large-scale dataset comprising 3,776 decision-making scenarios across nine social domains, designed to quantify implicit bias in long-term decision processes. Using a realistic long-horizon simulation framework, we evaluate six state-of-the-art LLMs integrated with three representative memory architectures on DIB and demonstrate that LLMs' implicit bias does not remain static but intensifies over time and propagates across unrelated domains. We further analyze mitigation strategies and show that a static system-level prompting baseline provides limited and short-lived debiasing effects. To address this limitation, we propose Dynamic Memory Tagging (DMT), an agentic intervention that enforces fairness constraints at memory write time. Extensive experimental results show that DMT substantially reduces bias accumulation and effectively curtails cross-domain bias propagation.

cs.LG↗

arXiv2026

AppellateGen: A Benchmark for Appellate Legal Judgment Generation

Legal judgment generation is a critical task in legal intelligence. However, existing research in legal judgment generation has predominantly focused on first-instance trials, relying on static fact-to-verdict mappings while neglecting the dialectical nature of appellate (second-instance) review. To address this, we introduce AppellateGen, a benchmark for second-instance legal judgment generation comprising 7,351 case pairs. The task requires models to draft legally binding judgments by reasoning over the initial verdict and evidentiary updates, thereby modeling the causal dependency between trial stages. We further propose a judicial Standard Operating Procedure (SOP)-based Legal Multi-Agent System (SLMAS) to simulate judicial workflows, which decomposes the generation process into discrete stages of issue identification, retrieval, and drafting. Experimental results indicate that while SLMAS improves logical consistency, the complexity of appellate reasoning remains a substantial challenge for current LLMs. The dataset and code are publicly available at: https://anonymous.4open.science/r/AppellateGen-5763.

cs.CY↗

arXiv2016

SICS: Secure In-Cloud Service Function Chaining

There is an increasing trend that enterprises outsource their network functions to the cloud for lower cost and ease of management. However, network function outsourcing brings threats to the privacy of enterprises since the cloud is able to access the traffic and rules of in-cloud network functions. Current tools for secure network function outsourcing either incur large performance overhead or do not support real-time updates. In this paper, we present SICS, a secure service function chain outsourcing framework. SICS encrypts each packet header and use a label for in-cloud rule matching, which enables the cloud to perform its functionalities correctly with minimum header information leakage. Evaluation results show that SICS achieves higher throughput, faster construction and update speed, and lower resource overhead at both enterprise and cloud sides, compared to existing solutions.

cs.NI↗

arXiv2009

Optimization of Energy Efficient Transmission in Underwater Sensor Networks

Underwater communication is a challenging topic due to its singular channel characteristics. Most protocols used in terrestrial wireless communication can not be directly applied in the underwater world. In this paper, we focus on the issue of energy efficient transmission in underwater sensor networks (UWSNs) and analyze this problem in a rigorous and theoretical way. We formalize an optimization problem which aims to minimize energy consumption and simultaneously accounts for other performance metrics such as the data reliability and the communication delay. With the help of Karush-Kuhn-Tucker conditions (KKT conditions), we derive a simple and explicit, but nevertheless accurate, approximate solution under reasonable assumptions. This approximate solution provides theoretical guidelines for designing durable and reliable UWSNs. Our result also shows that reliability and communication delay are crucial factors to the energy consumption for transmission.

cs.NI↗