arXiv subjects

Peng Hu

Publications and source records attributed to Peng Hu.

At least 37 records · Page 2Linked to original sources

arXiv2026

Robust Fuzzy Multi-view Learning under View Conflict

Trusted multi-view classification aims to deliver reliable fusion for accurate predictions and has recently attracted substantial attention in both academia and industry. However, existing TMVC methods typically assume strict alignment across different views during both training and testing phases, which is often impractical in real-world scenarios. This limitation motivates us to revisit TMVC and extend it to a more challenging setting: how to mitigate the impact of view conflict (VC) during both training and inference. To tackle this setting, existing TMVC methods suffer from three critical limitations: underestimated uncertainty, misleading decisions, and overfitting to VC. To address these issues, this paper proposes a novel Robust Fuzzy Multi-View Learning (R-FUML) framework grounded in Fuzzy Set Theory. Specifically, R-FUML models network outputs as fuzzy memberships to quantify category credibility and uses an entropy-based method for reliable multi-view fusion. To this end, we present a Robust Multi-view Fusion (RMF) strategy that accounts for both view-specific uncertainty and inter-view conflicts, thereby alleviating the adverse impacts of VC on decision-making. To identify and conquer VC during training, we further design a Robust Learning Against VC (RLVC) framework. RLVC isolates conflicting samples by leveraging neural networks' memory effects and then retrains the model by applying a penalty to these conflicting views. Extensive experiments across eight public datasets demonstrate that R-FUML consistently outperforms 15 state-of-the-art baselines in robustness and uncertainty estimation. The code will be released upon acceptance.

cs.CV↗

arXiv2026

Attention Transfer Is Not Universally Effective for Vision Transformers

A recent work shows that Attention Transfer, which transfers only the attention patterns from a pre-trained teacher Vision Transformer (ViT) to a randomly initialized standard student ViT, is sufficient to recover the full benefit of the teacher's pre-trained weights. We revisit this finding on a comprehensive benchmark of 20 teachers from 11 well-known ViT families and reveal that Attention Transfer is not universally effective. While 7 families transfer successfully, 4 consistently fail, falling up to 5.1\% below the from-scratch no-transfer baseline. Further results demonstrate that this failure is family-consistent across model sizes, and persists under extended training durations, different transfer datasets, and out-of-distribution evaluations. Controlled analyses then consistently localize the problem to the attention-routing channel, indicating that the key issue is not whether the student can match the teacher's attention patterns, but whether the matched patterns remain functional for the student. Crucially, we identify architectural mismatch between the pre-trained teacher and the standard student as the primary mechanism. By adding only the teacher's native architectural components to the student in a randomly initialized state, we completely reverse the failure for all 4 families. Notably, these components alone do not improve from-scratch training, confirming that they specifically unlock the usability of the teacher's attention. We further systematically show that this failure is not explained by the inadequate choice of transfer loss or by differences in pre-training recipes. Our findings refine the prevailing understanding of attention in ViT representations: attention is sufficient \textit{only} when the student architecture matches the teacher.

cs.CV↗

arXiv2026

Queue-Aware and Resilient Routing in LEO Satellite Networks Using Multi-Agent Reinforcement Learning

With the rapid growth in data demand and stringent latency requirements of modern applications has driven significant interest in Low Earth Orbit (LEO) satellite constellations as an emerging solution for global Internet coverage. However, routing in LEO networks remains a fundamental challenge due to highly dynamic topologies, time-varying traffic conditions, and its susceptibility to link failures. Conventional routing algorithms typically assume static link metrics and fail to account for queue backlogs or real-time system variations, making them less effective in such environments. We propose a queue-aware multi-agent deep reinforcement learning (MA-DRL) framework for routing in LEO satellite networks. Each satellite is modeled as an independent agent responsible for making local routing decisions, enabling a distributed and scalable solution. The proposed framework formulates a latency-aware optimization problem that incorporates background traffic, queue dynamics at each satellite, and a resilience score to improve robustness. We evaluate the proposed approach against the state-action-reward-state-action (SARSA) and Dijkstra algorithms. While Dijkstra achieves the lowest end-to-end latency under ideal conditions, its computational and signaling overhead becomes a significant bottleneck as the network scales. In contrast, our proposed approach incurs significantly lower overhead (approximately 50% of Dijkstra at a 5 s recalculation interval), scales efficiently with network size, and effectively manages queue backlogs and resilience under increasing traffic load, demonstrating enhanced robustness and scalability in LEO satellite networks while maintaining competitive latency and resilience scores.

cs.NI↗

arXiv2026

In-Orbit Optical SSA Using Proliferated LEO Satellites for Space Traffic Monitoring: An Analytical Framework

The increase in space activities has increased the risks of space debris generation, affecting space safety and sustainability. Traditional space situational awareness (SSA) relies on single star trackers and ground-based tracking facilities. There is limited discussion on the use of in-orbit optical sensors on low Earth orbit (LEO) satellite constellations for SSA, despite their importance for efficient space traffic management systems. In this paper, we aim to address this important challenge. We first present a new analytical system model for utilizing LEO satellite constellations for in-orbit SSA. We then develop a method to evaluate and analyze such a system. We also propose a Poisson expected revisit period algorithm and introduce the period of equivalent orbital distributions to reveal the relationship between revisit period and geometric variables, with insightful results based on real-world and custom satellite constellations. Experiments on real-world constellation show that the representative Poisson expected revisit period ranges from 0.4 days to 5.7 days for targets whose apogee altitude ranges from 552 km to 650 km, while requiring a per-case computation time of 0.4 s to 4.8 s. Our work can inform the future design of in-orbit and onboard computing systems for SSA, such as space object detection and space traffic monitoring systems.

eess.SY↗

arXiv2026

Understanding New-Knowledge-Induced Factual Hallucinations in LLMs: Analysis and Interpretation

Prior works have shown that fine-tuning on new knowledge can induce factual hallucinations in large language models (LLMs), leading to incorrect outputs when evaluated on previously known information. However, the specific manifestations of such hallucination and its underlying mechanisms remain insufficiently understood. Our work addresses this gap by designing a controlled dataset \textit{Biography-Reasoning}, and conducting a fine-grained analysis across multiple knowledge types and two task types, including knowledge question answering (QA) and knowledge reasoning tasks. We find that hallucinations not only severely affect tasks involving newly introduced knowledge, but also propagate to other evaluation tasks. Moreover, when fine-tuning on a dataset in which a specific knowledge type consists entirely of new knowledge, LLMs exhibit elevated hallucination tendencies. This suggests that the degree of unfamiliarity within a particular knowledge type, rather than the overall proportion of new knowledge, is a stronger driver of hallucinations. Through interpretability analysis, we show that learning new knowledge weakens the model's attention to key entities in the input question, leading to an over-reliance on surrounding context and a higher risk of hallucination. Conversely, reintroducing a small amount of known knowledge during the later stages of training restores attention to key entities and substantially mitigates hallucination behavior. Finally, we demonstrate that disrupted attention patterns can propagate across lexically similar contexts, facilitating the spread of hallucinations beyond the original task.

cs.CL↗

arXiv2026

End-to-End Performance of Video Streaming With MPEG-DASH Over Satellite 5G IAB Networks

We present an end-to-end performance evaluation of MPEG-DASH video streaming over a Low-Earth Orbit (LEO) satellite-based 5G Integrated Access and Backhaul (IAB) network. Our objective is to investigate how modern transport protocols and congestion control algorithms affect adaptive video delivery in an integrated satellite-terrestrial network (ISTN), where latency, throughput variation, and playback continuity jointly shape the user Quality-of-Experience (QoE). We implement a simulation framework in ns-3 by adapting open-source modules for the 5G radio access network, LEOS backhaul, transport layer protocols, and MPEG-DASH application behavior. Within this framework, TCP and QUIC are evaluated with multiple congestion control algorithms, including CUBIC, NewReno, and BBR. Performance is assessed using application-level and transport-level metrics, including playback duration, interruption duration, stall count, playback bitrate, throughput, latency, and fairness. The results show that no single configuration is uniformly optimal across all metrics. However, clear tradeoffs are observed among throughput, latency, playback continuity, and fairness. In particular, QUIC-BBR provides the most balanced overall behavior from a streaming QoE perspective, combining adequate playback duration with fewer interruptions and substantially lower latency than other alternatives. These findings highlight the importance of jointly considering transport design and congestion control when evaluating adaptive video streaming over ISTNs.

cs.NI↗

arXiv2026

Spatiotemporal Analysis of VIIRS Satellite Observations and Network Traffic During the 2025 Manitoba Wildfires

Climate change has intensified extreme weather and wildfire conditions globally. Canada experienced record-breaking wildfires in 2023 and 2025, burning millions of hectares and severely impacting the Prairie provinces, with Manitoba facing its worst season in 30 years. These events highlight the urgent need to understand and mitigate escalating fire risks. While existing research largely focuses on wildfire management approaches, few studies have explored the relationship between user network traffic and wildfire activity, despite the potential of such correlations to provide valuable spatiotemporal insights into wildfire dynamics. This paper investigates the relationship between wildfire intensity and network performance during the 2025 Manitoba wildfire season, using Visible Infrared Imaging Radiometer Suite (VIIRS) satellite-derived Fire Radiative Power data and large-scale Speedtest measurements. We found statistically significant correlations between wildfire intensity and several network performance metrics in both the province-wide and region-wide case studies, as measured by Spearman's correlation coefficients ($ρ$) and corresponding p-values. Throughput-related metrics showed inverse correlations with wildfire intensity (e.g., download speed: $ρ= -0.214$, $p\_value = 0.004$), whereas latency-related metrics showed positive correlations (e.g., round-trip time latency: $ρ= 0.162$, $p\_value = 0.0308$). The findings suggest satellite fire indicators and network performance metrics together can reveal vulnerabilities during extreme environmental events and support diaster response and recovery efforts.

cs.CY↗

arXiv2026

Beyond Loss Values: Robust Dynamic Pruning via Loss Trajectory Alignment

Existing dynamic data pruning methods often fail under noisy-label settings, as they typically rely on per-sample loss as the ranking criterion. This could mistakenly lead to preserving noisy samples due to their high loss values, resulting in significant performance drop. To address this, we propose AlignPrune, a noise-robust module designed to enhance the reliability of dynamic pruning under label noise. Specifically, AlignPrune introduces the Dynamic Alignment Score (DAS), which is a loss-trajectory-based criterion that enables more accurate identification of noisy samples, thereby improving pruning effectiveness. As a simple yet effective plug-and-play module, AlignPrune can be seamlessly integrated into state-of-the-art dynamic pruning frameworks, consistently outperforming them without modifying either the model architecture or the training pipeline. Extensive experiments on five widely-used benchmarks across various noise types and pruning ratios demonstrate the effectiveness of AlignPrune, boosting accuracy by up to 6.3\% over state-of-the-art baselines. Our results offer a generalizable solution for pruning under noisy data, encouraging further exploration of learning in real-world scenarios. Code is available at: https://github.com/leonqin430/AlignPrune.

cs.CV↗

arXiv2026

Beyond Ground-Truth: Leveraging Image Quality Priors for Real-World Image Restoration

Real-world image restoration aims to restore high-quality (HQ) images from degraded low-quality (LQ) inputs captured under uncontrolled conditions. Existing methods typically depend on ground-truth (GT) supervision, assuming that GT provides perfect reference quality. However, GT can still contain images with inconsistent perceptual fidelity, causing models to converge to the average quality level of the training data rather than achieving the highest perceptual quality attainable. To address these problems, we propose a novel framework, termed IQPIR, that introduces an Image Quality Prior (IQP)-extracted from pre-trained No-Reference Image Quality Assessment (NR-IQA) models-to guide the restoration process toward perceptually optimal outputs explicitly. Our approach synergistically integrates IQP with a learned codebook prior through three key mechanisms: (1) a quality-conditioned Transformer, where NR-IQA-derived scores serve as conditioning signals to steer the predicted representation toward maximal perceptual quality. This design provides a plug-and-play enhancement compatible with existing restoration architectures without structural modification; and (2) a dual-branch codebook structure, which disentangles common and HQ-specific features, ensuring a comprehensive representation of both generic structural information and quality-sensitive attributes; and (3) a discrete representation-based quality optimization strategy, which mitigates over-optimization effects commonly observed in continuous latent spaces. Extensive experiments on real-world image restoration demonstrate that our method not only surpasses cutting-edge methods but also serves as a generalizable quality-guided enhancement strategy for existing methods. The code is available.

cs.CV↗

arXiv2026

Next-Scale Prediction: A Self-Supervised Approach for Real-World Image Denoising

Self-supervised real-world image denoising remains a fundamental challenge, arising from the antagonistic trade-off between decorrelating spatially structured noise and preserving high-frequency details. Existing blind-spot network (BSN) methods rely on pixel-shuffle downsampling (PD) to decorrelate noise, but aggressive downsampling fragments fine structures, while milder downsampling fails to remove correlated noise. To address this, we introduce Next-Scale Prediction (NSP), a novel self-supervised paradigm that decouples noise decorrelation from detail preservation. NSP constructs cross-scale training pairs, where BSN takes low-resolution, fully decorrelated sub-images as input to predict high-resolution targets that retain fine details. As a by-product, NSP naturally supports super-resolution of noisy images without retraining or modification. Extensive experiments demonstrate that NSP achieves state-of-the-art self-supervised denoising performance on real-world benchmarks, significantly alleviating the long-standing conflict between noise decorrelation and detail preservation. The code is available at https://github.com/XLearning-SCU/2026-CVPR-NSP.

cs.CV↗

arXiv2026

Personalized Federated Learning via Gaussian Generative Modeling

Federated learning has emerged as a paradigm to train models collaboratively on inherently distributed client data while safeguarding privacy. In this context, personalized federated learning tackles the challenge of data heterogeneity by equipping each client with a dedicated model. A prevalent strategy decouples the model into a shared feature extractor and a personalized classifier head, where the latter actively guides the representation learning. However, previous works have focused on classifier head-guided personalization, neglecting the potential personalized characteristics in the representation distribution. Building on this insight, we propose pFedGM, a method based on Gaussian generative modeling. The approach begins by training a Gaussian generator that models client heterogeneity via weighted re-sampling. A balance between global collaboration and personalization is then struck by employing a dual objective: a shared objective that maximizes inter-class distance across clients, and a local objective that minimizes intra-class distance within them. To achieve this, we decouple the conventional Gaussian classifier into a navigator for global optimization, and a statistic extractor for capturing distributional statistics. Inspired by the Kalman gain, the algorithm then employs a dual-scale fusion framework at global and local levels to equip each client with a personalized classifier head. In this framework, we model the global representation distribution as a prior and the client-specific data as the likelihood, enabling Bayesian inference for class probability estimation. The evaluation covers a comprehensive range of scenarios: heterogeneity in class counts, environmental corruption, and multiple benchmark datasets and configurations. pFedGM achieves superior or competitive performance compared to state-of-the-art methods.

cs.LG↗

arXiv2026

QualiTeacher: Quality-Conditioned Pseudo-Labeling for Real-World Image Restoration

Real-world image restoration (RWIR) is a highly challenging task due to the absence of clean ground-truth images. Many recent methods resort to pseudo-label (PL) supervision, often within a Mean-Teacher (MT) framework. However, these methods face a critical paradox: unconditionally trusting the often imperfect, low-quality PLs forces the student model to learn undesirable artifacts, while discarding them severely limits data diversity and impairs model generalization. In this paper, we propose QualiTeacher, a novel framework that transforms pseudo-label quality from a noisy liability into a conditional supervisory signal. Instead of filtering, QualiTeacher explicitly conditions the student model on the quality of the PLs, estimated by an ensemble of complementary non-reference image quality assessment (NR-IQA) models spanning low-level distortion and semantic-level assessment. This strategy teaches the student network to learn a quality-graded restoration manifold, enabling it to understand what constitutes different quality levels. Consequently, it can not only avoid mimicking artifacts from low-quality labels but also extrapolate to generate results of higher quality than the teacher itself. To ensure the robustness and accuracy of this quality-driven learning, we further enhance the process with a multi-augmentation scheme to diversify the PL quality spectrum, a score-based preference optimization strategy inspired by Direct Preference Optimization (DPO) to enforce a monotonically ordered quality separation, and a cropped consistency loss to prevent adversarial over-optimization (reward hacking) of the IQA models. Experiments on standard RWIR benchmarks demonstrate that QualiTeacher can serve as a plug-and-play strategy to improve the quality of the existing pseudo-labeling framework, establishing a new paradigm for learning from imperfect supervision. Code will be released.

cs.CV↗

arXiv2026

Observation of Chiral Bound States in the Continuum in Self-biased Magneto-optical Photonic Crystals

Chiral bound states in the continuum (BICs) are confined photonic modes with infinite quality factors and chiral response, offering significant potential for chiral optics. Although a novel type of spin-orbital-locking chiral BIC was recently predicted in magneto-optical (MO) photonic crystals (PhCs) that break time-reversal symmetry (TRS), its experimental realization has remained elusive. Here, we report the first experimental observation of such chiral BICs in self-biased MO PhCs, which operate without external magnetic fields. Moreover, we experimentally demonstrate that the chirality and the surrounding near-circular polarization of these chiral BICs can be switched simply by reversing the remanent magnetization, without any structural changes. Unlike conventional chiral BICs that preserve TRS, these magnetically induced chiral BICs exhibit exceptional robustness against structural imperfections and perturbations. This work represents a significant advancement in the topological photonics of chiral BICs, opening new pathways toward robust chiral optical devices.

physics.optics↗

arXiv2026

AstroTimer: Rethinking Non-Access Stratum Timers in LEO Constellations

Low-Earth Orbit (LEO) constellations expand 5G coverage to remote regions but differ fundamentally from terrestrial networks due to rapidly changing topologies, fluctuating delays, and constrained onboard resources. Existing 3GPP Non-Access Stratum (NAS) timers, inherited from terrestrial and geostationary (GEO) or medium Earth orbit (MEO) systems, fail to accommodate these dynamics, leading to signaling storms and inefficiency. This paper introduces AstroTimer, a lightweight, adaptive framework for sizing NAS timers based on LEO-specific parameters such as link variability, processing delays, and network-function placement. AstroTimer derives a closed-form timer model with low computational cost and optimizes both watchdog and backoff timers for the 5G registration procedure. Simulation results demonstrate that AstroTimer significantly reduces registration time, retry frequency, and user equipment (UE) energy consumption compared to 3GPP defaults, while preventing signaling overloads. The proposed approach provides an operator-ready foundation for reliable, efficient, and scalable non-terrestrial 5G/6G deployments.

eess.SY↗

arXiv2025

Branch Learning in MRI: More Data, More Models, More Training

We investigated two complementary strategies for multicontrast cardiac MR reconstruction: physics-consistent data-space augmentation (DualSpaceCMR) and parameter-efficient capacity scaling via VQPrompt and Moero. DualSpaceCMR couples image-level transforms with kspace noise and motion simulations while preserving forwardmodel consistency. VQPrompt adds a lightweight bottleneck prompt; Moero embeds a sparse mixture of experts within a deep unrolled network with histogram-based routing. In the multivendor, multisite CMRxRecon25 benchmark, we evaluate fewshot and out-of-distribution generalization. On small datasets, k-space motion-plus-noise improves reconstruction; on the large benchmark it degrades performance, revealing sensitivity to augmentation ratio and schedule. VQPrompt produces modest and consistent gains with negligible memory overhead. Moero continues to improve after early plateaus and maintains baseline-like fewshot and out-of-distribution behavior despite mild overfitting, but sparse routing lowers PyTorch throughput and makes wall clock time the main bottleneck. These results motivate scale-aware augmentation and suggest prompt-based capacity scaling as a practical path, while efficiency improvements are crucial for sparse expert models.

eess.IV↗

arXiv2025

Conditional Representation Learning for Customized Tasks

Conventional representation learning methods learn a universal representation that primarily captures dominant semantics, which may not always align with customized downstream tasks. For instance, in animal habitat analysis, researchers prioritize scene-related features, whereas universal embeddings emphasize categorical semantics, leading to suboptimal results. As a solution, existing approaches resort to supervised fine-tuning, which however incurs high computational and annotation costs. In this paper, we propose Conditional Representation Learning (CRL), aiming to extract representations tailored to arbitrary user-specified criteria. Specifically, we reveal that the semantics of a space are determined by its basis, thereby enabling a set of descriptive words to approximate the basis for a customized feature space. Building upon this insight, given a user-specified criterion, CRL first employs a large language model (LLM) to generate descriptive texts to construct the semantic basis, then projects the image representation into this conditional feature space leveraging a vision-language model (VLM). The conditional representation better captures semantics for the specific criterion, which could be utilized for multiple customized tasks. Extensive experiments on classification and retrieval tasks demonstrate the superiority and generality of the proposed CRL. The code is available at https://github.com/XLearning-SCU/2025-NeurIPS-CRL.

cs.CV↗

arXiv2025

An Efficient and Generalizable Transfer Learning Method for Weather Condition Detection on Ground Terminals

The increasing adoption of satellite Internet with low-Earth-orbit (LEO) satellites in mega-constellations allows ubiquitous connectivity to rural and remote areas. However, weather events have a significant impact on the performance and reliability of satellite Internet. Adverse weather events such as snow and rain can disturb the performance and operations of satellite Internet's essential ground terminal components, such as satellite antennas, significantly disrupting the space-ground link conditions between LEO satellites and ground stations. This challenge calls for not only region-based weather forecasts but also fine-grained detection capability on ground terminal components of fine-grained weather conditions. Such a capability can assist in fault diagnostics and mitigation for reliable satellite Internet, but its solutions are lacking, not to mention the effectiveness and generalization that are essential in real-world deployments. This paper discusses an efficient transfer learning (TL) method that can enable a ground component to locally detect representative weather-related conditions. The proposed method can detect snow, wet, and other conditions resulting from adverse and typical weather events and shows superior performance compared to the typical deep learning methods, such as YOLOv7, YOLOv9, Faster R-CNN, and R-YOLO. Our TL method also shows the advantage of being generalizable to various scenarios.

cs.CV↗

arXiv2025

TernaryCLIP: Efficiently Compressing Vision-Language Models with Ternary Weights and Distilled Knowledge

Recent years have witnessed an increasing interest in image-text contrastive modeling, exemplified by models such as Contrastive Language-Image Pretraining (CLIP). In this paper, we propose the TernaryCLIP, a lightweight computational framework that converts connection weights of both vision and text encoders of CLIP into the ternary format, instead of full-precision or floating ones. TernaryCLIP incorporates quantization-aware training and distillation modules, preventing precision degradation and enabling low-cost and high-efficiency computations. Comprehensive experiments demonstrate that TernaryCLIP can achieve up to 99\% ternarized weights with 1.58-bit representation, 16.98 $\times$ compression ratio, 2.3 $\times$ inference acceleration, 16 $\times$ storage reduction, 10 $\times$ memory optimization, and 60\% sparsity while maintaining promising performance on zero-shot image classification and image-text retrieval tasks across 41 commonly used datasets. Our work highlights the feasibility of extreme quantization for large multimodal models, supporting effective and efficient deployment on resource-constrained devices. The model and code can be accessed from Hugging Face and GitHub.

cs.CV↗