arXiv subjects

Nan Yang

Publications and source records attributed to Nan Yang.

At least 55 records · Page 3Linked to original sources

arXiv2025

GuardFed: A Trustworthy Federated Learning Framework Against Dual-Facet Attacks

Federated learning (FL) enables privacy-preserving collaborative model training but remains vulnerable to adversarial behaviors that compromise model utility or fairness across sensitive groups. While extensive studies have examined attacks targeting either objective, strategies that simultaneously degrade both utility and fairness remain largely unexplored. To bridge this gap, we introduce the Dual-Facet Attack (DFA), a novel threat model that concurrently undermines predictive accuracy and group fairness. Two variants, Synchronous DFA (S-DFA) and Split DFA (Sp-DFA), are further proposed to capture distinct real-world collusion scenarios. Experimental results show that existing robust FL defenses, including hybrid aggregation schemes, fail to resist DFAs effectively. To counter these threats, we propose GuardFed, a self-adaptive defense framework that maintains a fairness-aware reference model using a small amount of clean server data augmented with synthetic samples. In each training round, GuardFed computes a dual-perspective trust score for every client by jointly evaluating its utility deviation and fairness degradation, thereby enabling selective aggregation of trustworthy updates. Extensive experiments on real-world datasets demonstrate that GuardFed consistently preserves both accuracy and fairness under diverse non-IID and adversarial conditions, achieving state-of-the-art performance compared with existing robust FL methods.

cs.LG↗

arXiv2025

Bidirectional Image-Event Guided Fusion Framework for Low-Light Image Enhancement

Under extreme low-light conditions, frame-based cameras suffer from severe detail loss due to limited dynamic range. Recent studies have introduced event cameras for event-guided low-light image enhancement. However, existing approaches often overlook the flickering artifacts and structural discontinuities caused by dynamic illumination changes and event sparsity. To address these challenges, we propose BiLIE, a Bidirectional image-event guided fusion framework for Low-Light Image Enhancement, which achieves mutual guidance and complementary enhancement between the two modalities. First, to highlight edge details, we develop a Dynamic Adaptive Filtering Enhancement (DAFE) module that performs adaptive high-pass filtering on event representations to suppress flickering artifacts and preserve high-frequency information under varying illumination. Subsequently, we design a Bidirectional Guided Awareness Fusion (BGAF) mechanism, which achieves breakpoint-aware restoration from images to events and structure-aware enhancement from events to images through a two-stage attention mechanism, establishing cross-modal consistency, thereby producing a clear, smooth, and structurally intact fused representation. Moreover, recognizing that existing datasets exhibit insufficient ground-truth fidelity and color accuracy, we construct a high-quality low-light image-event dataset (RELIE) via a reliable ground truth refinement scheme. Extensive experiments demonstrate that our method outperforms existing approaches on both the RELIE and LIE datasets. Notably, on RELIE, BiLIE exceeds the state-of-the-art by 0.81dB in PSNR and shows significant advantages in edge restoration, color fidelity, and noise suppression.

cs.CV↗

arXiv2025

Knowledge-Augmented Question Error Correction for Chinese Question Answer System with QuestionRAG

Input errors in question-answering (QA) systems often lead to incorrect responses. Large language models (LLMs) struggle with this task, frequently failing to interpret user intent (misinterpretation) or unnecessarily altering the original question's structure (over-correction). We propose QuestionRAG, a framework that tackles these problems. To address misinterpretation, it enriches the input with external knowledge (e.g., search results, related entities). To prevent over-correction, it uses reinforcement learning (RL) to align the model's objective with precise correction, not just paraphrasing. Our results demonstrate that knowledge augmentation is critical for understanding faulty questions. Furthermore, RL-based alignment proves significantly more effective than traditional supervised fine-tuning (SFT), boosting the model's ability to follow instructions and generalize. By integrating these two strategies, QuestionRAG unlocks the full potential of LLMs for the question correction task.

cs.CL↗

arXiv2025

Near-Field Secure Beamfocusing With Receiver-Centered Protected Zone

This work studies near-field secure communications through transmit beamfocusing. We examine the benefit of having a protected eavesdropper-free zone around the legitimate receiver, and we determine the worst-case secrecy performance against a potential eavesdropper located anywhere outside the protected zone. A max-min optimization problem is formulated for the beamfocusing design with and without artificial noise transmission. Despite the NP-hardness of the problem, we develop a synchronous gradient descent-ascent framework that approximates the global maximin solution. A low-complexity solution is also derived that delivers excellent performance over a wide range of operating conditions. We further extend this study to a scenario where it is not possible to physically enforce a protected zone. To this end, we consider secure communications through the creation of a virtual protected zone using a full-duplex legitimate receiver. Numerical results demonstrate that exploiting either the physical or virtual receiver-centered protected zone with appropriately designed beamfocusing is an effective strategy for achieving secure near-field communications.

eess.SP↗

arXiv2025

Thinking Augmented Pre-training

This paper introduces a simple and scalable approach to improve the data efficiency of large language model (LLM) training by augmenting existing text data with thinking trajectories. The compute for pre-training LLMs has been growing at an unprecedented rate, while the availability of high-quality data remains limited. Consequently, maximizing the utility of available data constitutes a significant research challenge. A primary impediment is that certain high-quality tokens are difficult to learn given a fixed model capacity, as the underlying rationale for a single token can be exceptionally complex and deep. To address this issue, we propose Thinking augmented Pre-Training (TPT), a universal methodology that augments text with automatically generated thinking trajectories. Such augmentation effectively increases the volume of the training data and makes high-quality tokens more learnable through step-by-step reasoning and decomposition. We apply TPT across diverse training configurations up to $100$B tokens, encompassing pre-training with both constrained and abundant data, as well as mid-training from strong open-source checkpoints. Experimental results indicate that our method substantially improves the performance of LLMs across various model sizes and families. Notably, TPT enhances the data efficiency of LLM pre-training by a factor of $3$. For a $3$B parameter model, it improves the post-training performance by over $10\%$ on several challenging reasoning benchmarks.

cs.CL↗

arXiv2025

The constraints on the stochastic gravitational wave background from cosmic strings by an electromagnetic resonance system

As one of the primary detection targets for contemporary gravitational wave (GW) observatories, the stochastic gravitational wave background (SGWB) holds significant potential for enhancing our understanding of the early universe's formation and evolution. Studies indicate that the SGWB spectrum from cosmic strings can span an extraordinarily broad frequency range, extending from extremely low frequencies up to the microwave band. This work specifically investigates the detectability of cosmic string SGWB signals in an electromagnetic (EM) resonance system at GHz frequency. We present a systematic analysis encompassing: (1) the response of high frequency gravitational waves (HFGWs) in such EM resonance system. (2) the development and application of fundamental data processing protocols in the EM resonance system. Our results demonstrate that the EM system shows promising sensitivity to detect cosmic string SGWB signals with tension parameters $Gμ\geq 10^{-11}$ (the corresponding dimensionless amplitude $h \geq 10^{-33}$ at 1 GHz), while potentially establishing new constraints for $Gμ\leq 10^{-11}$ in the microwave band. These findings would complement existing multi-band SGWB observations and provide additional constraints on cosmic-string tension parameters in GHz frequency regimes.

gr-qc↗

arXiv2025

Chain-of-Retrieval Augmented Generation

This paper introduces an approach for training o1-like RAG models that retrieve and reason over relevant information step by step before generating the final answer. Conventional RAG methods usually perform a single retrieval step before the generation process, which limits their effectiveness in addressing complex queries due to imperfect retrieval results. In contrast, our proposed method, CoRAG (Chain-of-Retrieval Augmented Generation), allows the model to dynamically reformulate the query based on the evolving state. To train CoRAG effectively, we utilize rejection sampling to automatically generate intermediate retrieval chains, thereby augmenting existing RAG datasets that only provide the correct final answer. At test time, we propose various decoding strategies to scale the model's test-time compute by controlling the length and number of sampled retrieval chains. Experimental results across multiple benchmarks validate the efficacy of CoRAG, particularly in multi-hop question answering tasks, where we observe more than 10 points improvement in EM score compared to strong baselines. On the KILT benchmark, CoRAG establishes a new state-of-the-art performance across a diverse range of knowledge-intensive tasks. Furthermore, we offer comprehensive analyses to understand the scaling behavior of CoRAG, laying the groundwork for future research aimed at developing factual and grounded foundation models.

cs.IR↗

arXiv2025

Conditional Autoencoder for Generating Binary Neutron Star Waveforms with Tidal and Precession Effects

Gravitational waves from binary neutron star mergers provide critical insights into dense matter physics and strong-field gravity, yet accurate waveform modeling remains computationally intensive. We present a deep generative model for gravitational waveforms from binary neutron star mergers that captures the late inspiral, merger, and ringdown phases while incorporating spin precession and tidal effects. Using a conditional autoencoder architecture, the model efficiently produces high-fidelity waveforms across a broad parameter space, including component masses (m1, m2), spin components (S1x, S1y, S1z, S2x, S2y, S2z), and tidal deformabilities (Lambda1, Lambda2). Trained on 1*10^6 waveforms generated by the IMRPhenomXP_NRTidalv2 model, our network achieves a mean mismatch of 2.13*10^-3. The generation time for a single waveform is 0.12 s, compared to 0.66 s for IMRPhenomXP_NRTidalv2, representing a speedup of about fivefold. When generating 1000 waveforms, the model completes the task in 0.75 s, roughly ten times faster than the baseline. This significant acceleration facilitates rapid parameter estimation and real-time gravitational-wave searches. With improved precision and efficiency, the model can support low-latency detection and broader applications in multi-messenger astrophysics.

astro-ph.GA↗

arXiv2025

PSTTS: A Plug-and-Play Token Selector for Efficient Event-based Spatio-temporal Representation Learning

Mainstream event-based spatio-temporal representation learning methods typically process event streams by converting them into sequences of event frames, achieving remarkable performance. However, they neglect the high spatial sparsity and inter-frame motion redundancy inherent in event frame sequences, leading to significant computational overhead. Existing token sparsification methods for RGB videos rely on unreliable intermediate token representations and neglect the influence of event noise, making them ineffective for direct application to event data. In this paper, we propose Progressive Spatio-Temporal Token Selection (PSTTS), a Plug-and-Play module for event data without introducing any additional parameters. PSTTS exploits the spatio-temporal distribution characteristics embedded in raw event data to effectively identify and discard spatio-temporal redundant tokens, achieving an optimal trade-off between accuracy and efficiency. Specifically, PSTTS consists of two stages, Spatial Token Purification and Temporal Token Selection. Spatial Token Purification discards noise and non-event regions by assessing the spatio-temporal consistency of events within each event frame to prevent interference with subsequent temporal redundancy evaluation. Temporal Token Selection evaluates the motion pattern similarity between adjacent event frames, precisely identifying and removing redundant temporal information. We apply PSTTS to four representative backbones UniformerV2, VideoSwin, EVMamba, and ExACT on the HARDVS, DailyDVS-200, and SeACT datasets. Experimental results demonstrate that PSTTS achieves significant efficiency improvements. Specifically, PSTTS reduces FLOPs by 29-43.6% and increases FPS by 21.6-41.3% on the DailyDVS-200 dataset, while maintaining task accuracy. Our code will be available.

cs.CV↗

arXiv2025

Examining False Positives under Inference Scaling for Mathematical Reasoning

Recent advancements in language models have led to significant improvements in mathematical reasoning across various benchmarks. However, most of these benchmarks rely on automatic evaluation methods that only compare final answers using heuristics, without verifying the underlying reasoning steps. This limitation results in false positive solutions, where models may produce correct final answers but with flawed deduction paths. In this paper, we systematically examine the prevalence of false positive solutions in mathematical problem solving for language models. We analyze the characteristics and extent of this issue across different open-source models, datasets of varying difficulty levels, and decoding strategies. Specifically, we explore how false positives influence the inference time scaling behavior of language models. Our experimental results reveal that: (1) false positive solutions persist across different models, datasets, and decoding methods, (2) sampling-based inference time scaling methods do not alleviate the problem, and (3) the pass@N evaluation metric is more susceptible to false positives, suggesting a significantly lower scaling ceiling than what automatic evaluations indicate. Additionally, we analyze specific instances of false positives and discuss potential limitations in self-improvement techniques and synthetic data generation under such conditions. Our data and code are publicly available at https://github.com/Wloner0809/False-Positives-in-Math.

cs.CL↗

arXiv2025

Securing Integrated Sensing and Communication Against a Mobile Adversary: A Stackelberg Game with Deep Reinforcement Learning

In this paper, we study a secure integrated sensing and communication (ISAC) system employing a full-duplex base station with sensing capabilities against a mobile proactive adversarial target$\unicode{x2014}$a malicious unmanned aerial vehicle (M-UAV). We develop a game-theoretic model to enhance communication security, radar sensing accuracy, and power efficiency. The interaction between the legitimate network and the mobile adversary is formulated as a non-cooperative Stackelberg game (NSG), where the M-UAV acts as the leader and strategically adjusts its trajectory to improve its eavesdropping ability while conserving power and avoiding obstacles. In response, the legitimate network, acting as the follower, dynamically allocates resources to minimize network power usage while ensuring required secrecy rates and sensing performance. To address this challenging problem, we propose a low-complexity successive convex approximation (SCA) method for network resource optimization combined with a deep reinforcement learning (DRL) algorithm for adaptive M-UAV trajectory planning through sequential interactions and learning. Simulation results demonstrate the efficacy of the proposed method in addressing security challenges of dynamic ISAC systems in 6G, i.e., achieving a Stackelberg equilibrium with robust performance while mitigating the adversary's ability to intercept network signals.

cs.IT↗

arXiv2025

Focus Through Motion: RGB-Event Collaborative Token Sparsification for Efficient Object Detection

Existing RGB-Event detection methods process the low-information regions of both modalities (background in images and non-event regions in event data) uniformly during feature extraction and fusion, resulting in high computational costs and suboptimal performance. To mitigate the computational redundancy during feature extraction, researchers have respectively proposed token sparsification methods for the image and event modalities. However, these methods employ a fixed number or threshold for token selection, hindering the retention of informative tokens for samples with varying complexity. To achieve a better balance between accuracy and efficiency, we propose FocusMamba, which performs adaptive collaborative sparsification of multimodal features and efficiently integrates complementary information. Specifically, an Event-Guided Multimodal Sparsification (EGMS) strategy is designed to identify and adaptively discard low-information regions within each modality by leveraging scene content changes perceived by the event camera. Based on the sparsification results, a Cross-Modality Focus Fusion (CMFF) module is proposed to effectively capture and integrate complementary features from both modalities. Experiments on the DSEC-Det and PKU-DAVIS-SOD datasets demonstrate that the proposed method achieves superior performance in both accuracy and efficiency compared to existing methods. The code will be available at https://github.com/Zizzzzzzz/FocusMamba.

cs.CV↗

arXiv2025

Beyond conventional vision: RGB-event fusion for robust object detection in dynamic traffic scenarios

The dynamic range limitation of conventional RGB cameras reduces global contrast and causes loss of high-frequency details such as textures and edges in complex traffic environments (e.g., nighttime driving, tunnels), hindering discriminative feature extraction and degrading frame-based object detection. To address this, we integrate a bio-inspired event camera with an RGB camera to provide high dynamic range information and propose a motion cue fusion network (MCFNet), which achieves optimal spatiotemporal alignment and adaptive cross-modal feature fusion under challenging lighting. Specifically, an event correction module (ECM) temporally aligns asynchronous event streams with image frames via optical-flow-based warping, jointly optimized with the detection network to learn task-aware event representations. The event dynamic upsampling module (EDUM) enhances spatial resolution of event frames to match image structures, ensuring precise spatiotemporal alignment. The cross-modal mamba fusion module (CMM) uses adaptive feature fusion with a novel interlaced scanning mechanism, effectively integrating complementary information for robust detection. Experiments conducted on the DSEC-Det and PKU-DAVIS-SOD datasets demonstrate that MCFNet significantly outperforms existing methods in various poor lighting and fast moving traffic scenarios. Notably, on the DSEC-Det dataset, MCFNet achieves a remarkable improvement, surpassing the best existing methods by 7.4% in mAP50 and 1.7% in mAP metrics, respectively. The code is available at https://github.com/Charm11492/MCFNet.

cs.CV↗

arXiv2025

Low Complexity Artificial Noise Aided Beam Focusing Design in Near-Field Terahertz Communications

In this paper, we develop a novel low-complexity artificial noise (AN) aided beam focusing scheme in a near-field terahertz wiretap communication system. In this system, the base station (BS) equipped with a large-scale array transmits signals to a legitimate user, while mitigating information leakage to an eavesdropper. We formulate an optimization problem to maximize the secrecy rate achieved at the legitimate user and solve it by designing the optimal beam focusing and power allocation. Numerical results demonstrate the significant performance improvement achieved by the proposed AN aided beam focusing scheme, especially when the eavesdropper is located closer to the BS than the legitimate user.

cs.IT↗

arXiv2025

Magneto-photoelectrochemical 2D heterojunction platform for biosensing detection

Photoelectrochemical (PEC) biosensors exhibit significant potential for biomolecule detection due to their high sensitivity and low background noise. However, their performance is severely constrained by the rapid recombination of photogenerated charge carriers. This study innovatively introduces a non-contact magnetic modulation strategy to suppress electron-hole recombination by manipulating carrier spin states, thereby significantly enhancing photoelectric conversion efficiency. Building on this mechanism, we developed a novel magnetically modulated PEC biosensing platform based on the MXenes/cobalt-doped titanium dioxide (Co-TiO2) heterostructure. This platform achieved ultrasensitive detection of protein kinase A (PKA) activity. Compared to an identical probe-modified biosensor without magnetic field application, the developed platform demonstrated a 68.75% enhancement in detection sensitivity and achieved an ultralow detection limit for PKA of 0.00016 U/mL. It also exhibited a wide linear range from 0.005 to 80 U/mL. This research not only provides a novel methodology for kinase activity analysis but also pioneers the innovative strategy of magnetic modulation for enhanced PEC sensing. It opens new avenues for developing high-performance biosensing platforms, holding significant promise for early disease diagnosis and drug screening applications.

physics.app-ph↗

arXiv2025

MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings

Multimodal embedding models, built upon causal Vision Language Models (VLMs), have shown promise in various tasks. However, current approaches face three key limitations: the use of causal attention in VLM backbones is suboptimal for embedding tasks; scalability issues due to reliance on high-quality labeled paired data for contrastive learning; and limited diversity in training objectives and data. To address these issues, we propose MoCa, a two-stage framework for transforming pre-trained VLMs into effective bidirectional multimodal embedding models. The first stage, Modality-aware Continual Pre-training, introduces a joint reconstruction objective that simultaneously denoises interleaved text and image inputs, enhancing bidirectional context-aware reasoning. The second stage, Heterogeneous Contrastive Fine-tuning, leverages diverse, semantically rich multimodal data beyond simple image-caption pairs to enhance generalization and alignment. Our method addresses the stated limitations by introducing bidirectional attention through continual pre-training, scaling effectively with massive unlabeled datasets via joint reconstruction objectives, and utilizing diverse multimodal data for enhanced representation robustness. Experiments demonstrate that MoCa consistently improves performance across MMEB and ViDoRe-v2 benchmarks, achieving new state-of-the-art results, and exhibits strong scalability with both model size and training data on MMEB.

cs.CV↗

arXiv2025

4Seasons: A Cross-Season Dataset for Multi-Weather SLAM in Autonomous Driving

We present a novel dataset covering seasonal and challenging perceptual conditions for autonomous driving. Among others, it enables research on visual odometry, global place recognition, and map-based re-localization tracking. The data was collected in different scenarios and under a wide variety of weather conditions and illuminations, including day and night. This resulted in more than 350 km of recordings in nine different environments ranging from multi-level parking garage over urban (including tunnels) to countryside and highway. We provide globally consistent reference poses with up-to centimeter accuracy obtained from the fusion of direct stereo visual-inertial odometry with RTK-GNSS. The full dataset is available at https://go.vision.in.tum.de/4seasons.

cs.CV↗

arXiv2025

4Seasons: Benchmarking Visual SLAM and Long-Term Localization for Autonomous Driving in Challenging Conditions

In this paper, we present a novel visual SLAM and long-term localization benchmark for autonomous driving in challenging conditions based on the large-scale 4Seasons dataset. The proposed benchmark provides drastic appearance variations caused by seasonal changes and diverse weather and illumination conditions. While significant progress has been made in advancing visual SLAM on small-scale datasets with similar conditions, there is still a lack of unified benchmarks representative of real-world scenarios for autonomous driving. We introduce a new unified benchmark for jointly evaluating visual odometry, global place recognition, and map-based visual localization performance which is crucial to successfully enable autonomous driving in any condition. The data has been collected for more than one year, resulting in more than 300 km of recordings in nine different environments ranging from a multi-level parking garage to urban (including tunnels) to countryside and highway. We provide globally consistent reference poses with up to centimeter-level accuracy obtained from the fusion of direct stereo-inertial odometry with RTK GNSS. We evaluate the performance of several state-of-the-art visual odometry and visual localization baseline approaches on the benchmark and analyze their properties. The experimental results provide new insights into current approaches and show promising potential for future research. Our benchmark and evaluation protocols will be available at https://go.vision.in.tum.de/4seasons.

cs.CV↗