arXiv subjects

Yong Dou

Publications and source records attributed to Yong Dou.

At least 19 recordsLinked to original sources

arXiv2026

BeamFocusNet: Beamforming-based Explicit Spatial Signal Focusing for Robust DoA Estimation under Low-SNR and Single-Snapshot Conditions

DoA estimation plays a crucial role in signal processing. Inspired by beamforming, recent works employ neural networks to estimate filters for filtering received signals to achieve DoA estimation. These methods typically generate filters by implicitly focusing signals and suppressing noise. However, this couples the two objectives, making training difficult to balance and resulting in poor robustness, especially under low SNR and limited snapshots. To address this issue, we propose the BeamFocusNet method, which generates filters through explicit signal focusing, introducing a new paradigm for neural network-based filter generation. Extensive experiments under various challenging conditions demonstrate the superiority and robustness of the proposed method in DoA estimation. Code is available at https://github.com/colaudiolab/BeamFocusNet.

eess.SP↗

arXiv2026

LocusGS: Spatially Grounded Tokens for Feed-Forward 3D Gaussian Splatting

Recent query-based feed-forward 3DGS methods represent a scene using learnable queries, each aggregating multi-view evidence and decoding a group of Gaussians. Ideally, different queries should specialize in coherent local regions of the scene. However, we observe that Gaussians decoded from the same query often scatter across distant scene regions, resulting in weak query-level spatial coherence and poor alignment with the scene structure. We attribute this behavior to the purely latent representation of existing Gaussian queries. To address this limitation, we introduce LocusGS, which augments each Gaussian query with a 3D anchor state consisting of a center and a support radius. The anchor state is progressively refined across decoder layers and is used throughout query interaction, multi-view feature aggregation, and Gaussian generation. Specifically, an anchor-to-ray geometric bias guides each query toward spatially relevant image observations, while anchor-centered decoding organizes its Gaussians within a local region. Experiments on novel view synthesis benchmarks show that LocusGS improves rendering quality over query-based Gaussian token baselines under the same Gaussian budget. Further analysis shows that the learned anchors form coherent spatial layouts and lead to more structured Gaussian distributions, demonstrating that explicit anchor states improve the spatial organization. Our project page: https://leo-frank.github.io/LocusGS_viewer.

cs.CV↗

arXiv2026

MAny: Merge Anything for Multimodal Continual Instruction Tuning

Multimodal Continual Instruction Tuning (MCIT) is essential for sequential task adaptation of Multimodal Large Language Models (MLLMs) but is severely restricted by catastrophic forgetting. While existing literature focuses on the reasoning language backbone, in this work, we expose a critical yet neglected dual-forgetting phenomenon across both perception drift in Cross-modal Projection Space and reasoning collapse in Low-rank Parameter Space. To resolve this, we present \textbf{MAny} (\textbf{M}erge \textbf{Any}thing), a framework that merges task-specific knowledge through \textbf{C}ross-modal \textbf{P}rojection \textbf{M}erging (\textbf{CPM}) and \textbf{L}ow-rank \textbf{P}arameter \textbf{M}erging (\textbf{LPM}). Specifically, CPM recovers perceptual alignment by adaptively merging cross-modal visual representations via visual-prototype guidance, ensuring accurate feature recovery during inference. Simultaneously, LPM eliminates mutual interference among task-specific low-rank modules by recursively merging low-rank weight matrices. By leveraging recursive least squares, LPM provides a closed-form solution that mathematically guarantees an optimal fusion trajectory for reasoning stability. Notably, MAny operates as a training-free paradigm that achieves knowledge merging via efficient CPU-based algebraic operations, eliminating additional gradient-based optimization beyond initial tuning. Our extensive evaluations confirm the superior performance and robustness of MAny across multiple MLLMs and benchmarks. Specifically, on the UCIT benchmark, MAny achieves significant leads of up to 8.57\% and 2.85\% in final average accuracy over state-of-the-art methods across two different MLLMs, respectively.

cs.LG↗

arXiv2025

BeamformNet: Deep Learning-Based Beamforming Method for DoA Estimation via Implicit Spatial Signal Focusing and Noise Suppression

Deep learning-based direction-of-arrival (DoA) estimation has gained increasing popularity. A popular family of DoA estimation algorithms is beamforming methods, which operate by constructing a spatial filter that is applied to array signals. However, these spatial filters obtained by traditional model-driven beamforming algorithms fail under demanding conditions such as coherent sources and a small number of snapshots. In order to obtain a robust spatial filter, this paper proposes BeamformNet-a novel deep learning framework grounded in beamforming principles. Based on the concept of optimal spatial filters, BeamformNet leverages neural networks to approximately obtain the optimal spatial filter via implicit spatial signal focusing and noise suppression, which is then applied to received signals for spatial focusing and noise suppression, thereby enabling accurate DoA estimation. Experimental results on both simulated and real-world speech acoustic source localization data demonstrate that BeamformNet achieves state-of-the-art DoA estimation performance and has better robustness.

cs.CE↗

arXiv2025

Muskie: Multi-view Masked Image Modeling for 3D Vision Pre-training

We present Muskie, a native multi-view vision backbone designed for 3D vision tasks. Unlike existing models, which are frame-wise and exhibit limited multi-view consistency, Muskie is designed to process multiple views simultaneously and introduce multi-view consistency in pre-training stage. Muskie is trained to reconstruct heavily masked content in one view by finding and utilizing geometric correspondences from other views. Through this pretext task and our proposed aggressive masking strategy, the model implicitly to learn view-invariant features and develop strong geometric understanding without any 3D supervision. Compared with state-of-the-art frame-wise backbones such as DINO, Muskie achieves higher multi-view correspondence accuracy. Furthermore, we demonstrate that using Muskie as a backbone consistently enhances performance on downstream 3D tasks, including camera pose estimation and pointmap reconstruction. Codes are publicly available at https://leo-frank.github.io/Muskie/

cs.CV↗

arXiv2025

Transolver is a Linear Transformer: Revisiting Physics-Attention through the Lens of Linear Attention

Recent advances in Transformer-based Neural Operators have enabled significant progress in data-driven solvers for Partial Differential Equations (PDEs). Most current research has focused on reducing the quadratic complexity of attention to address the resulting low training and inference efficiency. Among these works, Transolver stands out as a representative method that introduces Physics-Attention to reduce computational costs. Physics-Attention projects grid points into slices for slice attention, then maps them back through deslicing. However, we observe that Physics-Attention can be reformulated as a special case of linear attention, and that the slice attention may even hurt the model performance. Based on these observations, we argue that its effectiveness primarily arises from the slice and deslice operations rather than interactions between slices. Building on this insight, we propose a two-step transformation to redesign Physics-Attention into a canonical linear attention, which we call Linear Attention Neural Operator (LinearNO). Our method achieves state-of-the-art performance on six standard PDE benchmarks, while reducing the number of parameters by an average of 40.0% and computational cost by 36.2%. Additionally, it delivers superior performance on two challenging, industrial-level datasets: AirfRANS and Shape-Net Car.

cs.LG↗

arXiv2025

Spatial Signal Focusing and Noise Suppression for Direction-of-Arrival Estimation in Large-Aperture 2D Arrays under Demanding Conditions

Direction-of-Arrival (DOA) estimation in sensor arrays faces limitations under demanding conditions, including low signal-to-noise ratio, single-snapshot scenarios, coherent sources, and unknown source counts. Conventional beamforming suffers from sidelobe interference, adaptive methods (e.g., MVDR) and subspace algorithms (e.g., MUSIC) degrade with limited snapshots or coherent signals, while sparse-recovery approaches (e.g., L1-SVD) incur high computational complexity for large arrays. In this article, we construct the concept of the optimal spatial filter to solve the DOA estimation problem under demanding conditions by utilizing the sparsity of spatial signals. By utilizing the concept of the optimal spatial filter, we have transformed the DOA estimation problem into a solution problem for the optimal spatial filter. We propose the Spatial Signal Focusing and Noise Suppression (SSFNS) algorithm, which is a novel DOA estimation framework grounded in the theoretical existence of an optimal spatial filter, to solve for the optimal spatial filter and obtain DOA. Through experiments, it was found that the proposed algorithm is suitable for large aperture two-dimensional arrays and experiments have shown that our proposed algorithm performs better than other algorithms in scenarios with few snapshots or even a single snapshot, low signal-to-noise ratio, coherent signals, and unknown signal numbers in two-dimensional large aperture arrays.

eess.SP↗

arXiv2025

Unify Variables in Neural Scaling Laws for General Audio Representations via Embedding Effective Rank

Scaling laws have profoundly shaped our understanding of model performance in computer vision and natural language processing, yet their application to general audio representation learning remains underexplored. A key challenge lies in the multifactorial nature of general audio representation-representation quality is jointly influenced by variables such as audio length, embedding dimensionality, model depth, model architecture, data volume, etc., many of which are difficult to isolate or express analytically. In this work, we present a systematic study of scaling laws for general audio representations by utilizing embedding effective rank (RankMe) as a unifying metric that encapsulates the impact of diverse variables on representation quality. RankMe enables a label-free, information-theoretic quantification of audio embeddings, allowing us to examine scaling behaviors across a wide hyper-parameter space, including model size, training data volume, computational budget, architectural configurations, etc. Our empirical findings reveal a consistent power-law relationship between RankMe and representation quality, suggesting that embedding effective rank serves as a reliable proxy for assessing and predicting model performance in audio representation learning. This work not only validates the applicability of classical scaling principles to the general audio domain but also offers a theoretically grounded and empirically robust framework for guiding future model scaling strategies in audio foundation models.

cs.SD↗

arXiv2025

AudioSet-R: A Refined AudioSet with Multi-Stage LLM Label Reannotation

AudioSet is a widely used benchmark in the audio research community and has significantly advanced various audio-related tasks. However, persistent issues with label accuracy and completeness remain critical bottlenecks that limit performance in downstream applications.To address the aforementioned challenges, we propose a three-stage reannotation framework that harnesses general-purpose audio-language foundation models to systematically improve the label quality of AudioSet. The framework employs a cross-modal prompting strategy, inspired by the concept of prompt chaining, wherein prompts are sequentially composed to execute subtasks (audio comprehension, label synthesis, and semantic alignment). Leveraging this framework, we construct a high-quality, structured relabeled version of AudioSet-R. Extensive experiments conducted on representative audio classification models--including AST, PANNs, SSAST, and AudioMAE--consistently demonstrate substantial performance improvements, thereby validating the generalizability and effectiveness of the proposed approach in enhancing label reliability.The code is publicly available at: https://github.com/colaudiolab/AudioSet-R.

cs.SD↗

arXiv2025

Mono3R: Exploiting Monocular Cues for Geometric 3D Reconstruction

Recent advances in data-driven geometric multi-view 3D reconstruction foundation models (e.g., DUSt3R) have shown remarkable performance across various 3D vision tasks, facilitated by the release of large-scale, high-quality 3D datasets. However, as we observed, constrained by their matching-based principles, the reconstruction quality of existing models suffers significant degradation in challenging regions with limited matching cues, particularly in weakly textured areas and low-light conditions. To mitigate these limitations, we propose to harness the inherent robustness of monocular geometry estimation to compensate for the inherent shortcomings of matching-based methods. Specifically, we introduce a monocular-guided refinement module that integrates monocular geometric priors into multi-view reconstruction frameworks. This integration substantially enhances the robustness of multi-view reconstruction systems, leading to high-quality feed-forward reconstructions. Comprehensive experiments across multiple benchmarks demonstrate that our method achieves substantial improvements in both mutli-view camera pose estimation and point cloud accuracy.

cs.CV↗

arXiv2025

Regist3R: Incremental Registration with Stereo Foundation Model

Multi-view 3D reconstruction has remained an essential yet challenging problem in the field of computer vision. While DUSt3R and its successors have achieved breakthroughs in 3D reconstruction from unposed images, these methods exhibit significant limitations when scaling to multi-view scenarios, including high computational cost and cumulative error induced by global alignment. To address these challenges, we propose Regist3R, a novel stereo foundation model tailored for efficient and scalable incremental reconstruction. Regist3R leverages an incremental reconstruction paradigm, enabling large-scale 3D reconstructions from unordered and many-view image collections. We evaluate Regist3R on public datasets for camera pose estimation and 3D reconstruction. Our experiments demonstrate that Regist3R achieves comparable performance with optimization-based methods while significantly improving computational efficiency, and outperforms existing multi-view reconstruction models. Furthermore, to assess its performance in real-world applications, we introduce a challenging oblique aerial dataset which has long spatial spans and hundreds of views. The results highlight the effectiveness of Regist3R. We also demonstrate the first attempt to reconstruct large-scale scenes encompassing over thousands of views through pointmap-based foundation models, showcasing its potential for practical applications in large-scale 3D reconstruction tasks, including urban modeling, aerial mapping, and beyond.

eess.IV↗

arXiv2025

Highly Parallelized Reinforcement Learning Training with Relaxed Assignment Dependencies

As the demands for superior agents grow, the training complexity of Deep Reinforcement Learning (DRL) becomes higher. Thus, accelerating training of DRL has become a major research focus. Dividing the DRL training process into subtasks and using parallel computation can effectively reduce training costs. However, current DRL training systems lack sufficient parallelization due to data assignment between subtask components. This assignment issue has been ignored, but addressing it can further boost training efficiency. Therefore, we propose a high-throughput distributed RL training system called TianJi. It relaxes assignment dependencies between subtask components and enables event-driven asynchronous communication. Meanwhile, TianJi maintains clear boundaries between subtask components. To address convergence uncertainty from relaxed assignment dependencies, TianJi proposes a distributed strategy based on the balance of sample production and consumption. The strategy controls the staleness of samples to correct their quality, ensuring convergence. We conducted extensive experiments. TianJi achieves a convergence time acceleration ratio of up to 4.37 compared to related comparison systems. When scaled to eight computational nodes, TianJi shows a convergence time speedup of 1.6 and a throughput speedup of 7.13 relative to XingTian, demonstrating its capability to accelerate training and scalability. In data transmission efficiency experiments, TianJi significantly outperforms other systems, approaching hardware limits. TianJi also shows effectiveness in on-policy algorithms, achieving convergence time acceleration ratios of 4.36 and 2.95 compared to RLlib and XingTian. TianJi is accessible at https://github.com/HiPRL/TianJi.git.

cs.LG↗

arXiv2025

Audio-Language Models for Audio-Centric Tasks: A Systematic Survey

Audio-Language Models (ALMs), trained on paired audio-text data, are designed to process, understand, and reason about audio-centric multimodal content. Unlike traditional supervised approaches that use predefined labels, ALMs leverage natural language supervision to better handle complex real-world audio scenes with multiple overlapping events. While demonstrating impressive zero-shot and task generalization capabilities, there is still a notable lack of systematic surveys that comprehensively organize and analyze developments. In this paper, we present the first systematic review of ALMs with three main contributions: (1) comprehensive coverage of ALM works across speech, music, and sound from a general audio perspective; (2) a unified taxonomy of ALM foundations, including model architectures and training objectives; (3) establishment of a research landscape capturing mutual promotion and constraints among different research aspects, aiding in summarizing evaluations, limitations, concerns and promising directions. Our review contributes to helping researchers understand the development of existing technologies and future trends, while also providing valuable references for implementation in practical applications.

cs.SD↗

arXiv2024

AudioCIL: A Python Toolbox for Audio Class-Incremental Learning with Multiple Scenes

Deep learning, with its robust aotomatic feature extraction capabilities, has demonstrated significant success in audio signal processing. Typically, these methods rely on static, pre-collected large-scale datasets for training, performing well on a fixed number of classes. However, the real world is characterized by constant change, with new audio classes emerging from streaming or temporary availability due to privacy. This dynamic nature of audio environments necessitates models that can incrementally learn new knowledge for new classes without discarding existing information. Introducing incremental learning to the field of audio signal processing, i.e., Audio Class-Incremental Learning (AuCIL), is a meaningful endeavor. We propose such a toolbox named AudioCIL to align audio signal processing algorithms with real-world scenarios and strengthen research in audio class-incremental learning. Code is available at https://github.com/colaudiolab/AudioCIL.

cs.SD↗

arXiv2024

RuleRAG: Rule-Guided Retrieval-Augmented Generation with Language Models for Question Answering

Retrieval-augmented generation (RAG) has shown promising potential in knowledge intensive question answering (QA). However, existing approaches only consider the query itself, neither specifying the retrieval preferences for the retrievers nor informing the generators of how to refer to the retrieved documents for the answers, which poses a significant challenge to the QA performance. To address these issues, we propose Rule-guided Retrieval-Augmented Generation with LMs, which explicitly introduces rules for in-context learning (RuleRAG-ICL) to guide retrievers to recall related documents in the directions of rules and uniformly guide generators to reason attributed by the same rules. Moreover, most existing RAG datasets were constructed without considering rules and Knowledge Graphs (KGs) are recognized as providing high-quality rules. Therefore, we construct five rule-aware RAG benchmarks for QA, RuleQA, based on KGs to stress the significance of retrieval and reasoning with rules. Experiments on RuleQA demonstrate RuleRAG-ICL improves the retrieval quality of +89.2% in Recall@10 and answer accuracy of +103.1% in Exact Match, and RuleRAG-FT yields more enhancement. In addition, experiments on four existing RAG datasets show RuleRAG is also effective by offering rules in RuleQA to them, further proving the generalization of rule guidance in RuleRAG.

cs.IR↗

arXiv2024

Contrastive Learning-based Chaining-Cluster for Multilingual Voice-Face Association

The innate correlation between a person's face and voice has recently emerged as a compelling area of study, especially within the context of multilingual environments. This paper introduces our novel solution to the Face-Voice Association in Multilingual Environments (FAME) 2024 challenge, focusing on a contrastive learning-based chaining-cluster method to enhance face-voice association. This task involves the challenges of building biometric relations between auditory and visual modality cues and modelling the prosody interdependence between different languages while addressing both intrinsic and extrinsic variability present in the data. To handle these non-trivial challenges, our method employs supervised cross-contrastive (SCC) learning to establish robust associations between voices and faces in multi-language scenarios. Following this, we have specifically designed a chaining-cluster-based post-processing step to mitigate the impact of outliers often found in unconstrained in the wild data. We conducted extensive experiments to investigate the impact of language on face-voice association. The overall results were evaluated on the FAME public evaluation platform, where we achieved 2nd place. The results demonstrate the superior performance of our method, and we validate the robustness and effectiveness of our proposed approach. Code is available at https://github.com/colaudiolab/FAME24_solution.

cs.SD↗

arXiv2024

VoxNeuS: Enhancing Voxel-Based Neural Surface Reconstruction via Gradient Interpolation

Neural Surface Reconstruction learns a Signed Distance Field~(SDF) to reconstruct the 3D model from multi-view images. Previous works adopt voxel-based explicit representation to improve efficiency. However, they ignored the gradient instability of interpolation in the voxel grid, leading to degradation on convergence and smoothness. Besides, previous works entangled the optimization of geometry and radiance, which leads to the deformation of geometry to explain radiance, causing artifacts when reconstructing textured planes. In this work, we reveal that the instability of gradient comes from its discontinuity during trilinear interpolation, and propose to use the interpolated gradient instead of the original analytical gradient to eliminate the discontinuity. Based on gradient interpolation, we propose VoxNeuS, a lightweight surface reconstruction method for computational and memory efficient neural surface reconstruction. Thanks to the explicit representation, the gradient of regularization terms, i.e. Eikonal and curvature loss, are directly solved, avoiding computation and memory-access overhead. Further, VoxNeuS adopts a geometry-radiance disentangled architecture to handle the geometry deformation from radiance optimization. The experimental results show that VoxNeuS achieves better reconstruction quality than previous works. The entire training process takes 15 minutes and less than 3 GB of memory on a single 2080ti GPU.

cs.CV↗

arXiv2024

DistGrid: Scalable Scene Reconstruction with Distributed Multi-resolution Hash Grid

Neural Radiance Field~(NeRF) achieves extremely high quality in object-scaled and indoor scene reconstruction. However, there exist some challenges when reconstructing large-scale scenes. MLP-based NeRFs suffer from limited network capacity, while volume-based NeRFs are heavily memory-consuming when the scene resolution increases. Recent approaches propose to geographically partition the scene and learn each sub-region using an individual NeRF. Such partitioning strategies help volume-based NeRF exceed the single GPU memory limit and scale to larger scenes. However, this approach requires multiple background NeRF to handle out-of-partition rays, which leads to redundancy of learning. Inspired by the fact that the background of current partition is the foreground of adjacent partition, we propose a scalable scene reconstruction method based on joint Multi-resolution Hash Grids, named DistGrid. In this method, the scene is divided into multiple closely-paved yet non-overlapped Axis-Aligned Bounding Boxes, and a novel segmented volume rendering method is proposed to handle cross-boundary rays, thereby eliminating the need for background NeRFs. The experiments demonstrate that our method outperforms existing methods on all evaluated large-scale scenes, and provides visually plausible scene reconstruction. The scalability of our method on reconstruction quality is further evaluated qualitatively and quantitatively.

cs.CV↗