arXiv subjects

Xiaotong Tu

Publications and source records attributed to Xiaotong Tu.

11 recordsLinked to original sources

arXiv2026

StrixAE: An Intelligent Agent for Audio Enhancement under Complex Distortion Coupling in Real-World Scenarios

Audio enhancement in real-world scenarios involves complex distortion couplings and requires personalized enhancement. Existing solutions struggle to address both simultaneously. To improve robustness and enable autonomous operation in such scenarios, we propose StrixAE, an agent based on a multimodal large language model (MLLM). StrixAE leverages the MLLM as a controller to coordinate multiple audio enhancement and personalization models. To further enhance system robustness, reduce artifacts, and improve generalization across diverse real-world scenarios, StrixAE is trained through a two-stage process: first, CoT supervised fine-tuning on AcoustBench to ground basic reasoning and tool invocation; second, Audio Perception Reinforcement Learning (APRL), a reward design specifically tailored for audio restoration pipelines that jointly optimizes format validity, structural coherence, and perceptual quality. Unlike generic RL fine-tuning, APRL introduces structured rewards that enforce executable pipelines and logical section ordering, enabling the agent to produce reliable, interpretable enhancement plans without hallucinated tools. Based on real-world test datasets, our proposed method outperforms most existing open-source and proprietary solutions, achieving state-of-the-art performance across multiple perceptual metrics and demonstrating strong generalization robustness.

cs.SD↗

arXiv2026

DynTrace: Tracking Dynamic Object Evidence for 4D Spatio-Temporal Reasoning in MLLMs

4D spatio-temporal reasoning, jointly modeling 3D spatial structure and temporal evolution, is essential for understanding dynamic worlds and enabling embodied interaction. While current Multimodal Large Language Models (MLLMs) show strong capabilities in static scene understanding and coarse-grained 4D tasks, they still have notable limitations in continuous dynamic scene perception, especially in tracking dynamic object evidence for coherent 4D spatio-temporal reasoning. This shortcoming stems mainly from relying on sparse frame-level observations, fragmenting continuous dynamic cues and leaving models unable to disentangle genuine object dynamics from camera-induced apparent motion. Inspired by humans tracking dynamic cues while compensating for viewpoint changes, we propose DynTrace, a training-free framework for 4D spatio-temporal reasoning with two complementary components. Dynamic Trajectory Visualization (DTV) reprojects world-coordinate trajectories onto the image plane, providing geometry-informed visual priors that disentangle genuine object dynamics from camera-induced apparent motion. Meanwhile, the Dynamic Trace Token (DT-Token), organized into a Dynamic Trace Graph (DTG), tracks object-level dynamic cues, trace evolution, and key moments, maintaining continuous dynamic object evidence for coherent 4D reasoning. Together, these two components equip MLLMs with continuously tracked dynamic object evidence, grounded in geometry-informed visual priors and structured spatio-temporal traces. DynTrace consistently improves open-source MLLMs, achieving state-of-the-art results on Dyn-Bench, VLM4D, and DSI-Bench, validating the importance of tracking dynamic object evidence for robust 4D spatio-temporal reasoning.

cs.CV↗

arXiv2025

Self-supervised Multiplex Consensus Mamba for General Image Fusion

Image fusion integrates complementary information from different modalities to generate high-quality fused images, thereby enhancing downstream tasks such as object detection and semantic segmentation. Unlike task-specific techniques that primarily focus on consolidating inter-modal information, general image fusion needs to address a wide range of tasks while improving performance without increasing complexity. To achieve this, we propose SMC-Mamba, a Self-supervised Multiplex Consensus Mamba framework for general image fusion. Specifically, the Modality-Agnostic Feature Enhancement (MAFE) module preserves fine details through adaptive gating and enhances global representations via spatial-channel and frequency-rotational scanning. The Multiplex Consensus Cross-modal Mamba (MCCM) module enables dynamic collaboration among experts, reaching a consensus to efficiently integrate complementary information from multiple modalities. The cross-modal scanning within MCCM further strengthens feature interactions across modalities, facilitating seamless integration of critical information from both sources. Additionally, we introduce a Bi-level Self-supervised Contrastive Learning Loss (BSCL), which preserves high-frequency information without increasing computational overhead while simultaneously boosting performance in downstream tasks. Extensive experiments demonstrate that our approach outperforms state-of-the-art (SOTA) image fusion algorithms in tasks such as infrared-visible, medical, multi-focus, and multi-exposure fusion, as well as downstream visual tasks.

cs.CV↗

arXiv2025

Dissecting Generalized Category Discovery: Multiplex Consensus under Self-Deconstruction

Human perceptual systems excel at inducing and recognizing objects across both known and novel categories, a capability far beyond current machine learning frameworks. While generalized category discovery (GCD) aims to bridge this gap, existing methods predominantly focus on optimizing objective functions. We present an orthogonal solution, inspired by the human cognitive process for novel object understanding: decomposing objects into visual primitives and establishing cross-knowledge comparisons. We propose ConGCD, which establishes primitive-oriented representations through high-level semantic reconstruction, binding intra-class shared attributes via deconstruction. Mirroring human preference diversity in visual processing, where distinct individuals leverage dominant or contextual cues, we implement dominant and contextual consensus units to capture class-discriminative patterns and inherent distributional invariants, respectively. A consensus scheduler dynamically optimizes activation pathways, with final predictions emerging through multiplex consensus integration. Extensive evaluations across coarse- and fine-grained benchmarks demonstrate ConGCD's effectiveness as a consensus-aware paradigm. Code is available at github.com/lytang63/ConGCD.

cs.CV↗

arXiv2025

Efficient Dataset Distillation through Low-Rank Space Sampling

Huge amount of data is the key of the success of deep learning, however, redundant information impairs the generalization ability of the model and increases the burden of calculation. Dataset Distillation (DD) compresses the original dataset into a smaller but representative subset for high-quality data and efficient training strategies. Existing works for DD generate synthetic images by treating each image as an independent entity, thereby overlooking the common features among data. This paper proposes a dataset distillation method based on Matching Training Trajectories with Low-rank Space Sampling(MTT-LSS), which uses low-rank approximations to capture multiple low-dimensional manifold subspaces of the original data. The synthetic data is represented by basis vectors and shared dimension mappers from these subspaces, reducing the cost of generating individual data points while effectively minimizing information redundancy. The proposed method is tested on CIFAR-10, CIFAR-100, and SVHN datasets, and outperforms the baseline methods by an average of 9.9%.

cs.CV↗

arXiv2025

Exploiting Point-Language Models with Dual-Prompts for 3D Anomaly Detection

Anomaly detection (AD) in 3D point clouds is crucial in a wide range of industrial applications, especially in various forms of precision manufacturing. Considering the industrial demand for reliable 3D AD, several methods have been developed. However, most of these approaches typically require training separate models for each category, which is memory-intensive and lacks flexibility. In this paper, we propose a novel Point-Language model with dual-prompts for 3D ANomaly dEtection (PLANE). The approach leverages multi-modal prompts to extend the strong generalization capabilities of pre-trained Point-Language Models (PLMs) to the domain of 3D point cloud AD, achieving impressive detection performance across multiple categories using a single model. Specifically, we propose a dual-prompt learning method, incorporating both text and point cloud prompts. The method utilizes a dynamic prompt creator module (DPCM) to produce sample-specific dynamic prompts, which are then integrated with class-specific static prompts for each modality, effectively driving the PLMs. Additionally, based on the characteristics of point cloud data, we propose a pseudo 3D anomaly generation method (Ano3D) to improve the model's detection capabilities in an unsupervised setting. Experimental results demonstrate that the proposed method, which is under the multi-class-one-model paradigm, achieves a +8.7%/+17% gain on anomaly detection and localization performance as compared to the state-of-the-art one-class-one-model methods for the Anomaly-ShapeNet dataset, and obtains +4.3%/+4.1% gain for the Real3D-AD dataset. Code will be available upon publication.

cs.CV↗

arXiv2025

Integrating Frequency Guidance into Multi-source Domain Generalization for Bearing Fault Diagnosis

Recent generalizable fault diagnosis researches have effectively tackled the distributional shift between unseen working conditions. Most of them mainly focus on learning domain-invariant representation through feature-level methods. However, the increasing numbers of unseen domains may lead to domain-invariant features contain instance-level spurious correlations, which impact the previous models' generalizable ability. To address the limitations, we propose the Fourier-based Augmentation Reconstruction Network, namely FARNet.The methods are motivated by the observation that the Fourier phase component and amplitude component preserve different semantic information of the signals, which can be employed in domain augmentation techniques. The network comprises an amplitude spectrum sub-network and a phase spectrum sub-network, sequentially reducing the discrepancy between the source and target domains. To construct a more robust generalized model, we employ a multi-source domain data augmentation strategy in the frequency domain. Specifically, a Frequency-Spatial Interaction Module (FSIM) is introduced to handle global information and local spatial features, promoting representation learning between the two sub-networks. To refine the decision boundary of our model output compared to conventional triplet loss, we propose a manifold triplet loss to contribute to generalization. Through extensive experiments on the CWRU and SJTU datasets, FARNet demonstrates effective performance and achieves superior results compared to current cross-domain approaches on the benchmarks.

cs.LG↗

arXiv2024

Unsupervised Low-light Image Enhancement with Lookup Tables and Diffusion Priors

Low-light image enhancement (LIE) aims at precisely and efficiently recovering an image degraded in poor illumination environments. Recent advanced LIE techniques are using deep neural networks, which require lots of low-normal light image pairs, network parameters, and computational resources. As a result, their practicality is limited. In this work, we devise a novel unsupervised LIE framework based on diffusion priors and lookup tables (DPLUT) to achieve efficient low-light image recovery. The proposed approach comprises two critical components: a light adjustment lookup table (LLUT) and a noise suppression lookup table (NLUT). LLUT is optimized with a set of unsupervised losses. It aims at predicting pixel-wise curve parameters for the dynamic range adjustment of a specific image. NLUT is designed to remove the amplified noise after the light brightens. As diffusion models are sensitive to noise, diffusion priors are introduced to achieve high-performance noise suppression. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods in terms of visual quality and efficiency.

cs.CV↗

arXiv2023

Learning an Interpretable End-to-End Network for Real-Time Acoustic Beamforming

Recently, many forms of audio industrial applications, such as sound monitoring and source localization, have begun exploiting smart multi-modal devices equipped with a microphone array. Regrettably, model-based methods are often difficult to employ for such devices due to their high computational complexity, as well as the difficulty of appropriately selecting the user-determined parameters. As an alternative, one may use deep network-based methods, but these are often difficult to generalize, nor can they generate the desired beamforming map directly. In this paper, a computationally efficient acoustic beamforming algorithm is proposed, which may be unrolled to form a model-based deep learning network for real-time imaging, here termed the DAMAS-FISTA-Net. By exploiting the natural structure of an acoustic beamformer, the proposed network inherits the physical knowledge of the acoustic system, and thus learns the underlying physical properties of the propagation. As a result, all the network parameters may be learned end-to-end, guided by a model-based prior using back-propagation. Notably, the proposed network enables an excellent interpretability and the ability of being able to process the raw data directly. Extensive numerical experiments using both simulated and real-world data illustrate the preferable performance of the DAMAS-FISTA-Net as compared to alternative approaches.

cs.SD↗

arXiv2022

Hint-dynamic Knowledge Distillation

Knowledge Distillation (KD) transfers the knowledge from a high-capacity teacher model to promote a smaller student model. Existing efforts guide the distillation by matching their prediction logits, feature embedding, etc., while leaving how to efficiently utilize them in junction less explored. In this paper, we propose Hint-dynamic Knowledge Distillation, dubbed HKD, which excavates the knowledge from the teacher' s hints in a dynamic scheme. The guidance effect from the knowledge hints usually varies in different instances and learning stages, which motivates us to customize a specific hint-learning manner for each instance adaptively. Specifically, a meta-weight network is introduced to generate the instance-wise weight coefficients about knowledge hints in the perception of the dynamical learning progress of the student model. We further present a weight ensembling strategy to eliminate the potential bias of coefficient estimation by exploiting the historical statics. Experiments on standard benchmarks of CIFAR-100 and Tiny-ImageNet manifest that the proposed HKD well boost the effect of knowledge distillation tasks.

cs.CV↗

arXiv2022

Acoustic-Net: A Novel Neural Network for Sound Localization and Quantification

Acoustic source localization has been applied in different fields, such as aeronautics and ocean science, generally using multiple microphones array data to reconstruct the source location. However, the model-based beamforming methods fail to achieve the high-resolution of conventional beamforming maps. Deep neural networks are also appropriate to locate the sound source, but in general, these methods with complex network structures are hard to be recognized by hardware. In this paper, a novel neural network, termed the Acoustic-Net, is proposed to locate and quantify the sound source simply using the original signals. The experiments demonstrate that the proposed method significantly improves the accuracy of sound source prediction and the computing speed, which may generalize well to real data. The code and trained models are available at https://github.com/JoaquinChou/Acoustic-Net.

cs.SD↗