Searcharxiv⌕ Search

arXiv subjects

Yik-Chung Wu

Publications and source records attributed to Yik-Chung Wu.

At least 37 records · Page 2Linked to original sources

Statistic-Augmented, Decoupled MoE Routing and Aggregating in Autonomous Driving

Autonomous driving (AD) scenarios are inherently complex and diverse, posing significant challenges for a single deep learning model to effectively cover all possible conditions, such as varying weather, traffic densities, and road types. Large Model (LM)-Driven Mixture of Experts (MoE) paradigm offers a promising solution, where LM serves as the backbone to extract latent features while MoE serves as the downstream head to dynamically select and aggregate specialized experts to adapt to different scenarios. However, routing and aggregating in MoE face intrinsic challenges, including imprecise expert selection due to flawed routing strategy and inefficient expert aggregation leading to suboptimal prediction. To address these issues, we propose a statistic-augmented, decoupled MoE }outing and Aggregating Mechanism (MoE-RAM) driven by LM. Specifically, on the one hand, MoE-RAM enhances expert routing by incorporating statistical retrieval mechanism to match LM-extracted latent features with cached prototypical features of the most relevant experts; on the other hand, MoE-RAM adaptively reweights experts' outputs in fusion by measuring statistical distances of experts' instant features against LM-extracted latent features. Benefiting from the synergy of the statistic-augmented MoE's routing and aggregating, MoE-RAM ultimately improves the prediction performance. We take the AD semantic segmentation task as an example to assess the proposed MoE-RAM. Extensive experiments on AD datasets demonstrate the superiority of MoE-RAM compared to other MoE baselines and conventional single-model approaches.

cs.RO↗

FedDSR: Federated Deep Supervision and Regularization Towards Autonomous Driving

Federated Learning (FL) enables collaborative training of autonomous driving (AD) models across distributed vehicles while preserving data privacy. However, FL encounters critical challenges such as poor generalization and slow convergence due to non-independent and identically distributed (non-IID) data from diverse driving environments. To overcome these obstacles, we introduce Federated Deep Supervision and Regularization (FedDSR), a paradigm that incorporates multi-access intermediate layer supervision and regularization within federated AD system. Specifically, FedDSR comprises following integral strategies: (I) to select multiple intermediate layers based on predefined architecture-agnostic standards. (II) to compute mutual information (MI) and negative entropy (NE) on those selected layers to serve as intermediate loss and regularizer. These terms are integrated into the output-layer loss to form a unified optimization objective, enabling comprehensive optimization across the network hierarchy. (III) to aggregate models from vehicles trained based on aforementioned rules of (I) and (II) to generate the global model on central server. By guiding and penalizing the learning of feature representations at intermediate stages, FedDSR enhances the model generalization and accelerates model convergence for federated AD. We then take the semantic segmentation task as an example to assess FedDSR and apply FedDSR to multiple model architectures and FL algorithms. Extensive experiments demonstrate that FedDSR achieves up to 8.93% improvement in mIoU and 28.57% reduction in training rounds, compared to other FL baselines, making it highly suitable for practical deployment in federated AD ecosystems.

cs.RO↗

Aligning Effective Tokens with Video Anomaly in Large Language Models

Understanding abnormal events in videos is a vital and challenging task that has garnered significant attention in a wide range of applications. Although current video understanding Multi-modal Large Language Models (MLLMs) are capable of analyzing general videos, they often struggle to handle anomalies due to the spatial and temporal sparsity of abnormal events, where the redundant information always leads to suboptimal outcomes. To address these challenges, exploiting the representation and generalization capabilities of Vison Language Models (VLMs) and Large Language Models (LLMs), we propose VA-GPT, a novel MLLM designed for summarizing and localizing abnormal events in various videos. Our approach efficiently aligns effective tokens between visual encoders and LLMs through two key proposed modules: Spatial Effective Token Selection (SETS) and Temporal Effective Token Generation (TETG). These modules enable our model to effectively capture and analyze both spatial and temporal information associated with abnormal events, resulting in more accurate responses and interactions. Furthermore, we construct an instruction-following dataset specifically for fine-tuning video-anomaly-aware MLLMs, and introduce a cross-domain evaluation benchmark based on XD-Violence dataset. Our proposed method outperforms existing state-of-the-art methods on various benchmarks.

cs.CV↗

Fighter: Unveiling the Graph Convolutional Nature of Transformers in Time Series Modeling

Transformers have achieved remarkable success in time series modeling, yet their internal mechanisms remain opaque. This work demystifies the Transformer encoder by establishing its fundamental equivalence to a Graph Convolutional Network (GCN). We show that in the forward pass, the attention distribution matrix serves as a dynamic adjacency matrix, and its composition with subsequent transformations performs computations analogous to graph convolution. Moreover, we demonstrate that in the backward pass, the update dynamics of value and feed-forward projections mirror those of GCN parameters. Building on this unified theoretical reinterpretation, we propose \textbf{Fighter} (Flexible Graph Convolutional Transformer), a streamlined architecture that removes redundant linear projections and incorporates multi-hop graph aggregation. This perspective yields an explicit and interpretable representation of temporal dependencies across different scales, naturally expressed as graph edges. Experiments on standard forecasting benchmarks confirm that Fighter achieves competitive performance while providing clearer mechanistic interpretability of its predictions.

cs.LG↗

Distributed Activity Detection for Cell-Free Hybrid Near-Far Field Communications

A great amount of endeavor has recently been devoted to activity detection for massive machine-type communications in cell-free massive MIMO. However, in practice, as the number of antennas at the access points (APs) increases, the Rayleigh distance that separates the near-field and far-field regions also expands, rendering the conventional assumption of far-field propagation alone impractical. To address this challenge, this paper considers a hybrid near-far field activity detection in cell-free massive MIMO, and establishes a covariance-based formulation, which facilitates the development of a distributed algorithm to alleviate the computational burden at the central processing unit (CPU). Specifically, each AP performs local activity detection for the devices and then transmits the detection result to the CPU for further processing. In particular, a novel coordinate descent algorithm based on the Sherman-Morrison-Woodbury update with Taylor expansion is proposed to handle the local detection problem at each AP. Moreover, we theoretically analyze how the hybrid near-far field channels affect the detection performance. Simulation results validate the theoretical analysis and demonstrate the superior performance of the proposed approach compared with existing approaches.

eess.SP↗

Shadow-FT: Tuning Instruct Model via Training on Paired Base Model

Large language models (LLMs) consistently benefit from further fine-tuning on various tasks. However, we observe that directly tuning the Instruct (i.e., instruction-tuned) models often leads to marginal improvements and even performance degeneration. Notably, paired Base models, the foundation for these Instruct variants, contain highly similar weight values (i.e., less than 2% on average for Llama 3.1 8B). The Base model tends to be a good learner yet a weak backbone without post-training. Therefore, we propose a novel Shadow-FT framework to tune the Instruct models by leveraging the corresponding Base models. The key insight is to fine-tune the Base model, and then \textit{directly} graft the learned weight updates to the Instruct model. Our proposed Shadow-FT introduces no additional parameters, is easy to implement, and significantly improves performance. We conduct extensive experiments on tuning mainstream LLMs, such as Qwen 3 and Llama 3 series, and evaluate them across 19 benchmarks covering coding, reasoning, and mathematical tasks. Experimental results demonstrate that Shadow-FT consistently outperforms conventional full-parameter and parameter-efficient tuning approaches. Further analyses indicate that Shadow-FT can be applied to multimodal large language models (MLLMs) and combined with direct preference optimization~(DPO). Codes and weights are available at \href{https://github.com/wutaiqiang/Shadow-FT}{Github}.

cs.CL↗

To Fold or Not to Fold: Graph Regularized Tensor Train for Visual Data Completion

Tensor train (TT) representation has achieved tremendous success in visual data completion tasks, especially when it is combined with tensor folding. However, folding an image or video tensor breaks the original data structure, leading to local information loss as nearby pixels may be assigned into different dimensions and become far away from each other. In this paper, to fully preserve the local information of the original visual data, we explore not folding the data tensor, and at the same time adopt graph information to regularize local similarity between nearby entries. To overcome the high computational complexity introduced by the graph-based regularization in the TT completion problem, we propose to break the original problem into multiple sub-problems with respect to each TT core fiber, instead of each TT core as in traditional methods. Furthermore, to avoid heavy parameter tuning, a sparsity promoting probabilistic model is built based on the generalized inverse Gaussian (GIG) prior, and an inference algorithm is derived under the mean-field approximation. Experiments on both synthetic data and real-world visual data show the superiority of the proposed methods.

eess.SP↗

iMacHSR: Intermediate Multi-Access Heterogeneous Supervision and Regularization Scheme Toward Architecture-Agnostic Training

While deep supervision is a powerful training strategy by supervising intermediate layers with auxiliary losses, it faces three underexplored problems: (I) Existing deep supervision techniques are generally bond with specific model architectures strictly, lacking generality. (II) The identical loss function for intermediate and output layers causes intermediate layers to prioritize output-specific features prematurely, limiting generalizable representations. (III) Lacking regularization on hidden activations risks overconfident predictions, reducing generalization to unseen scenarios. To tackle these challenges, we propose an architecture-agnostic, intermediate Multi-access Heterogeneous Supervision and Regularization (iMacHSR) scheme. Specifically, the proposed iMacHSR introduces below integral strategies: (I) we select multiple intermediate layers based on predefined architecture-agnostic standards; (II) loss functions (different from output-layer loss) are applied to those selected intermediate layers, which can guide intermediate layers to learn diverse and hierarchical representations; and (III) negative entropy regularization on selected layers' hidden features discourages overconfident predictions and mitigates overfitting. These intermediate terms are combined into the output-layer training loss to form a unified optimization objective, enabling comprehensive optimization across the network hierarchy. We then take the semantic understanding task as an example to assess iMacHSR and apply iMacHSR to several model architectures. Extensive experiments on multiple datasets demonstrate that iMacHSR outperforms conventional output-layer single-point supervision method up to 9.19% in mIoU.

cs.RO↗

Adverse Weather-Independent Framework Towards Autonomous Driving Perception through Temporal Correlation and Unfolded Regularization

Various adverse weather conditions such as fog and rain pose a significant challenge to autonomous driving (AD) perception tasks like semantic segmentation, object detection, etc. The common domain adaption strategy is to minimize the disparity between images captured in clear and adverse weather conditions. However, domain adaption faces two challenges: (I) it typically relies on utilizing clear image as a reference, which is challenging to obtain in practice; (II) it generally targets single adverse weather condition and performs poorly when confronting the mixture of multiple adverse weather conditions. To address these issues, we introduce a reference-free and Adverse weather condition-independent (Advent) framework (rather than a specific model architecture) that can be implemented by various backbones and heads. This is achieved by leveraging the homogeneity over short durations, getting rid of clear reference and being generalizable to arbitrary weather condition. Specifically, Advent includes three integral components: (I) Locally Sequential Mechanism (LSM) leverages temporal correlations between adjacent frames to achieve the weather-condition-agnostic effect thanks to the homogeneity behind arbitrary weather condition; (II) Globally Shuffled Mechanism (GSM) is proposed to shuffle segments processed by LSM from different positions of input sequence to prevent the overfitting to LSM-induced temporal patterns; (III) Unfolded Regularizers (URs) are the deep unfolding implementation of two proposed regularizers to penalize the model complexity to enhance across-weather generalization. We take the semantic segmentation task as an example to assess the proposed Advent framework. Extensive experiments demonstrate that the proposed Advent outperforms existing state-of-the-art baselines with large margins.

cs.RO↗

Balancing Latency and Model Accuracy for Fluid Antenna-Assisted LM-Embedded MIMO Network

This paper addresses the challenge of large model (LM)-embedded wireless network for handling the trade-off problem of model accuracy and network latency. To guarantee a high-quality of users' service, the network latency should be minimized while maintaining an acceptable inference accuracy. To meet this requirement, LM quantization is proposed to reduce the latency. However, the excessive quantization may destroy the accuracy of LM inference. To this end, a promising fluid antenna (FA) technology is investigated for enhancing the transmission capacity, leading to a lower network latency in the LM-embedded multiple-input multiple-output (MIMO) network. To design the FA-assisted LM-embedded network with the lower latency and higher accuracy requirements, the latency and peak signal to noise ratio (PSNR) are considered in the objective function. Then, an efficient optimization algorithm is proposed under the block coordinate descent framework. Simulation results are provided to show the convergence behavior of the proposed algorithm, and the performance gains from the proposed FA-assisted LMembedded network over the other benchmark networks in terms of network latency and PSNR.

eess.SP↗

Mixture of Experts-augmented Deep Unfolding for Activity Detection in IRS-aided Systems

In the realm of activity detection for massive machine-type communications, intelligent reflecting surfaces (IRS) have shown significant potential in enhancing coverage for devices lacking direct connections to the base station (BS). However, traditional activity detection methods are typically designed for a single type of channel model, which does not reflect the complexities of real-world scenarios, particularly in systems incorporating IRS. To address this challenge, this paper introduces a novel approach that combines model-driven deep unfolding with a mixture of experts (MoE) framework. By automatically selecting one of three expert designs and applying it to the unfolded projected gradient method, our approach eliminates the need for prior knowledge of channel types between devices and the BS. Simulation results demonstrate that the proposed MoE-augmented deep unfolding method surpasses the traditional covariance-based method and black-box neural network design, delivering superior detection performance under mixed channel fading conditions.

cs.LG↗

FieldFormer: Self-supervised Reconstruction of Physical Fields via Tensor Attention Prior

Reconstructing physical field tensors from \textit{in situ} observations, such as radio maps and ocean sound speed fields, is crucial for enabling environment-aware decision making in various applications, e.g., wireless communications and underwater acoustics. Field data reconstruction is often challenging, due to the limited and noisy nature of the observations, necessitating the incorporation of prior information to aid the reconstruction process. Deep neural network-based data-driven structural constraints (e.g., ``deeply learned priors'') have showed promising performance. However, this family of techniques faces challenges such as model mismatches between training and testing phases. This work introduces FieldFormer, a self-supervised neural prior learned solely from the limited {\it in situ} observations without the need of offline training. Specifically, the proposed framework starts with modeling the fields of interest using the tensor Tucker model of a high multilinear rank, which ensures a universal approximation property for all fields. In the sequel, an attention mechanism is incorporated to learn the sparsity pattern that underlies the core tensor in order to reduce the solution space. In this way, a ``complexity-adaptive'' neural representation, grounded in the Tucker decomposition, is obtained that can flexibly represent various types of fields. A theoretical analysis is provided to support the recoverability of the proposed design. Moreover, extensive experiments, using various physical field tensors, demonstrate the superiority of the proposed approach compared to state-of-the-art baselines.

eess.SP↗

Channel Estimation for Rydberg Atomic Receivers

The rapid development of the quantum technology presents huge opportunities for 6G communications. Leveraging the quantum properties of highly excited Rydberg atoms, Rydberg atom-based antennas present distinct advantages, such as high sensitivity, broad frequency range, and compact size, over traditional antennas. To realize efficient precoding, accurate channel state information is essential. However, due to the distinct characteristics of atomic receivers, traditional channel estimation algorithms developed for conventional receivers are no longer applicable. To this end, we propose a novel channel estimation algorithm based on projection gradient descent (PGD), which is applicable to both one-dimensional (1D) and twodimensional (2D) arrays. Simulation results are provided to show the effectiveness of our proposed channel estimation method.

cs.IT↗

Enhancing Large Vision Model in Street Scene Semantic Understanding through Leveraging Posterior Optimization Trajectory

To improve the generalization of the autonomous driving (AD) perception model, vehicles need to update the model over time based on the continuously collected data. As time progresses, the amount of data fitted by the AD model expands, which helps to improve the AD model generalization substantially. However, such ever-expanding data is a double-edged sword for the AD model. Specifically, as the fitted data volume grows to exceed the the AD model's fitting capacities, the AD model is prone to under-fitting. To address this issue, we propose to use a pretrained Large Vision Models (LVMs) as backbone coupled with downstream perception head to understand AD semantic information. This design can not only surmount the aforementioned under-fitting problem due to LVMs' powerful fitting capabilities, but also enhance the perception generalization thanks to LVMs' vast and diverse training data. On the other hand, to mitigate vehicles' computational burden of training the perception head while running LVM backbone, we introduce a Posterior Optimization Trajectory (POT)-Guided optimization scheme (POTGui) to accelerate the convergence. Concretely, we propose a POT Generator (POTGen) to generate posterior (future) optimization direction in advance to guide the current optimization iteration, through which the model can generally converge within 10 epochs. Extensive experiments demonstrate that the proposed method improves the performance by over 66.48\% and converges faster over 6 times, compared to the existing state-of-the-art approach.

cs.CV↗

Nonparametric Teaching for Graph Property Learners

Inferring properties of graph-structured data, e.g., the solubility of molecules, essentially involves learning the implicit mapping from graphs to their properties. This learning process is often costly for graph property learners like Graph Convolutional Networks (GCNs). To address this, we propose a paradigm called Graph Neural Teaching (GraNT) that reinterprets the learning process through a novel nonparametric teaching perspective. Specifically, the latter offers a theoretical framework for teaching implicitly defined (i.e., nonparametric) mappings via example selection. Such an implicit mapping is realized by a dense set of graph-property pairs, with the GraNT teacher selecting a subset of them to promote faster convergence in GCN training. By analytically examining the impact of graph structure on parameter-based gradient descent during training, and recasting the evolution of GCNs--shaped by parameter updates--through functional gradient descent in nonparametric teaching, we show for the first time that teaching graph property learners (i.e., GCNs) is consistent with teaching structure-aware nonparametric learners. These new findings readily commit GraNT to enhancing learning efficiency of the graph property learner, showing significant reductions in training time for graph-level regression (-36.62%), graph-level classification (-38.19%), node-level regression (-30.97%) and node-level classification (-47.30%), all while maintaining its generalization performance.

cs.LG↗

Deep Unfolding with Kernel-based Quantization in MIMO Detection

The development of edge computing places critical demands on energy-efficient model deployment for multiple-input multiple-output (MIMO) detection tasks. Deploying deep unfolding models such as PGD-Nets and ADMM-Nets into resource-constrained edge devices using quantization methods is challenging. Existing quantization methods based on quantization aware training (QAT) suffer from performance degradation due to their reliance on parametric distribution assumption of activations and static quantization step sizes. To address these challenges, this paper proposes a novel kernel-based adaptive quantization (KAQ) framework for deep unfolding networks. By utilizing a joint kernel density estimation (KDE) and maximum mean discrepancy (MMD) approach to align activation distributions between full-precision and quantized models, the need for prior distribution assumptions is eliminated. Additionally, a dynamic step size updating method is introduced to adjust the quantization step size based on the channel conditions of wireless networks. Extensive simulations demonstrate that the accuracy of proposed KAQ framework outperforms traditional methods and successfully reduces the model's inference latency.

cs.LG↗

FedEMA: Federated Exponential Moving Averaging with Negative Entropy Regularizer in Autonomous Driving

Street Scene Semantic Understanding (denoted as S3U) is a crucial but complex task for autonomous driving (AD) vehicles. Their inference models typically face poor generalization due to domain-shift. Federated Learning (FL) has emerged as a promising paradigm for enhancing the generalization of AD models through privacy-preserving distributed learning. However, these FL AD models face significant temporal catastrophic forgetting when deployed in dynamically evolving environments, where continuous adaptation causes abrupt erosion of historical knowledge. This paper proposes Federated Exponential Moving Average (FedEMA), a novel framework that addresses this challenge through two integral innovations: (I) Server-side model's historical fitting capability preservation via fusing current FL round's aggregation model and a proposed previous FL round's exponential moving average (EMA) model; (II) Vehicle-side negative entropy regularization to prevent FL models' possible overfitting to EMA-introduced temporal patterns. Above two strategies empower FedEMA a dual-objective optimization that balances model generalization and adaptability. In addition, we conduct theoretical convergence analysis for the proposed FedEMA. Extensive experiments both on Cityscapes dataset and Camvid dataset demonstrate FedEMA's superiority over existing approaches, showing 7.12% higher mean Intersection-over-Union (mIoU).

cs.RO↗

Exploiting Dynamic Sparsity for Near-Field Spatial Non-Stationary XL-MIMO Channel Tracking

This work considers a spatial non-stationary channel tracking problem in broadband extremely large-scale multiple-input-multiple-output (XL-MIMO) systems. In the case of spatial non-stationary, each scatterer has a certain visibility region (VR) over antennas and power change may occur among visible antennas. Concentrating on the temporal correlation of XL-MIMO channels, we design a three-layer Markov prior model and hierarchical two-dimensional (2D) Markov model to exploit the dynamic sparsity of sparse channel vectors and VRs, respectively. Then, we formulate the channel tracking problem as a bilinear measurement process, and a novel dynamic alternating maximum a posteriori (DA-MAP) framework is developed to solve the problem. The DA-MAP contains four basic modules: channel estimation module, VR detection module, grid update module, and temporal correlated module. Specifically, the first module is an inverse-free variational Bayesian inference (IF-VBI) estimator that avoids computational intensive matrix inverse each iteration; the second module is a turbo compressive sensing (Turbo-CS) algorithm that only needs small-scale matrix operations in a parallel fashion; the third module refines the polar-delay domain grid; and the fourth module can process the temporal prior information to ensure high-efficiency channel tracking. Simulations show that the proposed method can achieve a significant channel tracking performance while achieving low computational overhead.

eess.SP↗