arXiv subjects

Xiang Zhang

Publications and source records attributed to Xiang Zhang.

At least 253 records · Page 14Linked to original sources

arXiv2024

Medformer: A Multi-Granularity Patching Transformer for Medical Time-Series Classification

Medical time series (MedTS) data, such as Electroencephalography (EEG) and Electrocardiography (ECG), play a crucial role in healthcare, such as diagnosing brain and heart diseases. Existing methods for MedTS classification primarily rely on handcrafted biomarkers extraction and CNN-based models, with limited exploration of transformer-based models. In this paper, we introduce Medformer, a multi-granularity patching transformer tailored specifically for MedTS classification. Our method incorporates three novel mechanisms to leverage the unique characteristics of MedTS: cross-channel patching to leverage inter-channel correlations, multi-granularity embedding for capturing features at different scales, and two-stage (intra- and inter-granularity) multi-granularity self-attention for learning features and correlations within and among granularities. We conduct extensive experiments on five public datasets under both subject-dependent and challenging subject-independent setups. Results demonstrate Medformer's superiority over 10 baselines, achieving top averaged ranking across five datasets on all six evaluation metrics. These findings underscore the significant impact of our method on healthcare applications, such as diagnosing Myocardial Infarction, Alzheimer's, and Parkinson's disease. We release the source code at https://github.com/DL4mHealth/Medformer.

eess.SP↗

arXiv2024

Supervised Chain of Thought

Large Language Models (LLMs) have revolutionized natural language processing and hold immense potential for advancing Artificial Intelligence. However, the core architecture of most mainstream LLMs -- the Transformer -- has inherent limitations in computational depth, rendering them theoretically incapable of solving many reasoning tasks that demand increasingly deep computations. Chain of Thought (CoT) prompting has emerged as a technique to address these architectural limitations, as evidenced by several theoretical studies. It offers a promising approach to solving complex reasoning tasks that were previously beyond the capabilities of these models. Despite its successes, CoT and its variants (such as Tree of Thought, Graph of Thought, etc.) rely on a "one-prompt-for-all" approach, using a single prompt structure (e.g., "think step by step") for a wide range of tasks -- from counting and sorting to solving mathematical and algorithmic problems. This approach poses significant challenges for models to generate the correct reasoning steps, as the model must navigate through a vast prompt template space to find the appropriate template for each task. In this work, we build upon previous theoretical analyses of CoT to demonstrate how the one-prompt-for-all approach can negatively affect the computability of LLMs. We partition the solution search space into two: the prompt space and the answer space. Our findings show that task-specific supervision is essential for navigating the prompt space accurately and achieving optimal performance. Through experiments with state-of-the-art LLMs, we reveal a gap in reasoning performance when supervision is applied versus when it is not.

cs.CL↗

arXiv2024

Temporal-Enhanced Multimodal Transformer for Referring Multi-Object Tracking and Segmentation

Referring multi-object tracking (RMOT) is an emerging cross-modal task that aims to locate an arbitrary number of target objects and maintain their identities referred by a language expression in a video. This intricate task involves the reasoning of linguistic and visual modalities, along with the temporal association of target objects. However, the seminal work employs only loose feature fusion and overlooks the utilization of long-term information on tracked objects. In this study, we introduce a compact Transformer-based method, termed TenRMOT. We conduct feature fusion at both encoding and decoding stages to fully exploit the advantages of Transformer architecture. Specifically, we incrementally perform cross-modal fusion layer-by-layer during the encoding phase. In the decoding phase, we utilize language-guided queries to probe memory features for accurate prediction of the desired objects. Moreover, we introduce a query update module that explicitly leverages temporal prior information of the tracked objects to enhance the consistency of their trajectories. In addition, we introduce a novel task called Referring Multi-Object Tracking and Segmentation (RMOTS) and construct a new dataset named Ref-KITTI Segmentation. Our dataset consists of 18 videos with 818 expressions, and each expression averages 10.7 masks, which poses a greater challenge compared to the typical single mask in most existing referring video segmentation datasets. TenRMOT demonstrates superior performance on both the referring multi-object tracking and the segmentation tasks.

cs.CV↗

arXiv2024

Harnessing with Twisting: Single-Arm Deformable Linear Object Manipulation for Industrial Harnessing Task

Wire-harnessing tasks pose great challenges to be automated by the robot due to the complex dynamics and unpredictable behavior of the deformable wire. Traditional methods, often reliant on dual-robot arms or tactile sensing, face limitations in adaptability, cost, and scalability. This paper introduces a novel single-robot wire-harnessing pipeline that leverages a robot's twisting motion to generate necessary wire tension for precise insertion into clamps, using only one robot arm with an integrated force/torque (F/T) sensor. Benefiting from this design, the single robot arm can efficiently apply tension for wire routing and insertion into clamps in a narrow space. Our approach is structured around four principal components: a Model Predictive Control (MPC) based on the Koopman operator for tension tracking and wire following, a motion planner for sequencing harnessing waypoints, a suite of insertion primitives for clamp engagement, and a fix-point switching mechanism for wire constraint updating. Evaluated on an industrial-level wire harnessing task, our method demonstrated superior performance and reliability over conventional approaches, efficiently handling both single and multiple wire configurations with high success rates.

cs.RO↗

arXiv2024

Ion-Assisted Nanoscale Material Engineering in Atomic Layers

Achieving deterministic control over the properties of low-dimensional materials with nanoscale precision is a long-sought goal. Mastering this capability has a transformative impact on the design of multifunctional electrical and optical devices. Here, we present an ion-assisted synthetic technique that enables precise control over the material composition and energy landscape of two-dimensional (2D) atomic crystals. Our method transforms binary transition metal dichalcogenides (TMDs), like MoSe$_2$, into ternary MoS$_{2α}$Se$_{2(1-α})$ alloys with systematically adjustable compositions, $α$. By piecewise assembly of the lateral, compositionally modulated MoS$_{2α}$Se$_{2(1-α)}$ segments within 2D atomic layers, we present a synthetic pathway towards the realization of multi-compositional designer materials. Our technique enables the fabrication of complex structures with arbitrary boundaries, dimensions as small as 30 nm, and fully customizable energy landscapes. Our optical characterizations further showcase the potential for implementing tailored optoelectronics in these engineered 2D crystals.

cond-mat.mtrl-sci↗

arXiv2024

Fine-Grained Vectorized Merge Sorting on RISC-V: From Register to Cache

Merge sort as a divide-sort-merge paradigm has been widely applied in computer science fields. As modern reduced instruction set computing architectures like the fifth generation (RISC-V) regard multiple registers as a vector register group for wide instruction parallelism, optimizing merge sort with this vectorized property is becoming increasingly common. In this paper, we overhaul the divide-sort-merge paradigm, from its register-level sort to the cache-aware merge, to develop a fine-grained RISC-V vectorized merge sort (RVMS). From the register-level view, the inline vectorized transpose instruction is missed in RISC-V, so implementing it efficiently is non-trivial. Besides, the vectorized comparisons do not always work well in the merging networks. Both issues primarily stem from the expensive data shuffle instruction. To bypass it, RVMS strides to take register data as the proxy of data shuffle to accelerate the transpose operation, and meanwhile replaces vectorized comparisons with scalar cousin for more light real value swap. On the other hand, as cache-aware merge makes larger data merge in the cache, most merge schemes have two drawbacks: the in-cache merge usually has low cache utilization, while the out-of-cache merging network remains an ineffectively symmetric structure. To this end, we propose the half-merge scheme to employ the auxiliary space of in-place merge to halve the footprint of naive merge sort, and meanwhile copy one sequence to this space to avoid the former data exchange. Furthermore, an asymmetric merging network is developed to adapt to two different input sizes.

cs.DC↗

arXiv2024

Unique and Universal scaling in dynamical quantum phase transitions

Universality and scaling are fundamental concepts in equilibrium continuous phase transitions. Here, we unveil a unique and universal scaling behavior of the critical time in slowly driven dynamical quantum phase transition. Going beyond the analogy with equilibrium phase transition, we find that the critical time exhibits a power-law scaling with quenching rate and the scaling exponent is fully determined by underlining universality class. We explain this unique scaling behavior based on the adiabatic-impulse scenario in the Kibble-Zurek mechanism. This universal scaling behavior is verified to be valid not only in noninteracting single-particle system, but also in many-body interacting system, and not only in Hermitian system, but also in non-Hermitian system. Our study unravels a deep and fundamental relationship between dynamical phase transition and equilibrium phase tranition.

cond-mat.stat-mech↗

arXiv2024

Takin: A Cohort of Superior Quality Zero-shot Speech Generation Models

With the advent of the big data and large language model era, zero-shot personalized rapid customization has emerged as a significant trend. In this report, we introduce Takin AudioLLM, a series of techniques and models, mainly including Takin TTS, Takin VC, and Takin Morphing, specifically designed for audiobook production. These models are capable of zero-shot speech production, generating high-quality speech that is nearly indistinguishable from real human speech and facilitating individuals to customize the speech content according to their own needs. Specifically, we first introduce Takin TTS, a neural codec language model that builds upon an enhanced neural speech codec and a multi-task training framework, capable of generating high-fidelity natural speech in a zero-shot way. For Takin VC, we advocate an effective content and timbre joint modeling approach to improve the speaker similarity, while advocating for a conditional flow matching based decoder to further enhance its naturalness and expressiveness. Last, we propose the Takin Morphing system with highly decoupled and advanced timbre and prosody modeling approaches, which enables individuals to customize speech production with their preferred timbre and prosody in a precise and controllable manner. Extensive experiments validate the effectiveness and robustness of our Takin AudioLLM series models. For detailed demos, please refer to https://everest-ai.github.io/takinaudiollm/.

cs.SD↗

arXiv2024

CamLoPA: A Hidden Wireless Camera Localization Framework via Signal Propagation Path Analysis

Hidden wireless cameras pose significant privacy threats, necessitating effective detection and localization methods. However, existing solutions often require spacious activity areas, expensive specialized devices, or pre-collected training data, limiting their practical deployment. To address these limitations, we introduce CamLoPA, a training-free wireless camera detection and localization framework that operates with minimal activity space constraints using low-cost commercial-off-the-shelf (COTS) devices. CamLoPA can achieve detection and localization in just 45 seconds of user activities with a Raspberry Pi board. During this short period, it analyzes the causal relationship between the wireless traffic and user movement to detect the presence of a snooping camera. Upon detection, CamLoPA employs a novel azimuth location model based on wireless signal propagation path analysis. Specifically, this model leverages the time ratio of user paths crossing the First Fresnel Zone (FFZ) to determine the azimuth angle of the camera. Then CamLoPA refines the localization by identifying the camera's quadrant. We evaluate CamLoPA across various devices and environments, demonstrating that it achieves 95.37% snooping camera detection accuracy and an average localization error of 17.23, under the significantly reduced activity space requirements. Our demo are available at https://www.youtube.com/watch?v=GKam04FzeM4.

cs.CR↗

arXiv2024

Autoregressive + Chain of Thought = Recurrent: Recurrence's Role in Language Models' Computability and a Revisit of Recurrent Transformer

The Transformer architecture excels in a variety of language modeling tasks, outperforming traditional neural architectures such as RNN and LSTM. This is partially due to its elimination of recurrent connections, which allows for parallel training and a smoother flow of gradients. However, this move away from recurrent structures places the Transformer model at the lower end of Chomsky's computational hierarchy, imposing limitations on its computational abilities. Consequently, even advanced Transformer-based models face considerable difficulties in tasks like counting, string reversal, and multiplication. These tasks, though seemingly elementary, require a level of computational complexity that exceeds the capabilities of the Transformer architecture. Concurrently, the emergence of ``Chain of Thought" (CoT) prompting has enabled Transformer-based language models to tackle tasks that were previously impossible or poorly executed. In this work, we thoroughly investigate the influence of recurrent structures in neural models on their reasoning abilities and computability, contrasting the role autoregression plays in the neural models' computational power. We then shed light on how the CoT approach can mimic recurrent computation and act as a bridge between autoregression and recurrence in the context of language models. It is this approximated recurrence that notably improves the model's performance and computational capacity. Moreover, we revisit recent recurrent-based Transformer model designs, focusing on their computational abilities through our proposed concept of ``recurrence-completeness" and identify key theoretical limitations in models like Linear Transformer and RWKV. Through this, we aim to provide insight into the neural model architectures and prompt better model design.

cs.CL↗

arXiv2024

Transtreaming: Adaptive Delay-aware Transformer for Real-time Streaming Perception

Real-time object detection is critical for the decision-making process for many real-world applications, such as collision avoidance and path planning in autonomous driving. This work presents an innovative real-time streaming perception method, Transtreaming, which addresses the challenge of real-time object detection with dynamic computational delay. The core innovation of Transtreaming lies in its adaptive delay-aware transformer, which can concurrently predict multiple future frames and select the output that best matches the real-world present time, compensating for any system-induced computation delays. The proposed model outperforms the existing state-of-the-art methods, even in single-frame detection scenarios, by leveraging a transformer-based methodology. It demonstrates robust performance across a range of devices, from powerful V100 to modest 2080Ti, achieving the highest level of perceptual accuracy on all platforms. Unlike most state-of-the-art methods that struggle to complete computation within a single frame on less powerful devices, Transtreaming meets the stringent real-time processing requirements on all kinds of devices. The experimental results emphasize the system's adaptability and its potential to significantly improve the safety and reliability for many real-world systems, such as autonomous driving.

cs.CV↗

arXiv2024

Fine-Grained Building Function Recognition from Street-View Images via Geometry-Aware Semi-Supervised Learning

In this work, we propose a geometry-aware semi-supervised framework for fine-grained building function recognition, utilizing geometric relationships among multi-source data to enhance pseudo-label accuracy in semi-supervised learning, broadening its applicability to various building function categorization systems. Firstly, we design an online semi-supervised pre-training stage, which facilitates the precise acquisition of building facade location information in street-view images. In the second stage, we propose a geometry-aware coarse annotation generation module. This module effectively combines GIS data and street-view data based on the geometric relationships, improving the accuracy of pseudo annotations. In the third stage, we combine the newly generated coarse annotations with the existing labeled dataset to achieve fine-grained functional recognition of buildings across multiple cities at a large scale. Extensive experiments demonstrate that our proposed framework exhibits superior performance in fine-grained functional recognition of buildings. Within the same categorization system, it achieves improvements of 7.6\% and 4.8\% compared to fully-supervised methods and state-of-the-art semi-supervised methods, respectively. Additionally, our method also performs well in cross-city scenarios, i.e., extending the model trained on OmniCity (New York) to new cities (i.e., Los Angeles and Boston) with different building function categorization systems. This study offers a new solution for large-scale multi-city applications with minimal annotation requirements, facilitating more efficient data updates and resource allocation in urban management.

cs.CV↗

arXiv2024

A Hybrid Vectorized Merge Sort on ARM NEON

Sorting algorithms are the most extensively researched topics in computer science and serve for numerous practical applications. Although various sorts have been proposed for efficiency, different architectures offer distinct flavors to the implementation of parallel sorting. In this paper, we propose a hybrid vectorized merge sort on ARM NEON, named NEON Merge Sort for short (NEON-MS). In detail, according to the granted register functions, we first identify the optimal register number to avoid the register-to-memory access, due to the write-back of intermediate outcomes. More importantly, following the generic merge sort framework that primarily uses sorting network for column sort and merging networks for three types of vectorized merge, we further improve their structures for high efficiency in an unified asymmetry way: 1) it makes the optimal sorting networks with few comparators become possible; 2) hybrid implementation of both serial and vectorized merges incurs the pipeline with merge instructions highly interleaved. Experiments on a single FT2000+ core show that NEON-MS is 3.8 and 2.1 times faster than std::sort and boost::block\_sort, respectively, on average. Additionally, as compared to the parallel version of the latter, NEON-MS gains an average speedup of 1.25.

cs.DC↗

arXiv2024

In-Hand Following of Deformable Linear Objects Using Dexterous Fingers with Tactile Sensing

Most research on deformable linear object (DLO) manipulation assumes rigid grasping. However, beyond rigid grasping and re-grasping, in-hand following is also an essential skill that humans use to dexterously manipulate DLOs, which requires continuously changing the grasp point by in-hand sliding while holding the DLO to prevent it from falling. Achieving such a skill is very challenging for robots without using specially designed but not versatile end-effectors. Previous works have attempted using generic parallel grippers, but their robustness is unsatisfactory owing to the conflict between following and holding, which is hard to balance with a one-degree-of-freedom gripper. In this work, inspired by how humans use fingers to follow DLOs, we explore the usage of a generic dexterous hand with tactile sensing to imitate human skills and achieve robust in-hand DLO following. To enable the hardware system to function in the real world, we develop a framework that includes Cartesian-space arm-hand control, tactile-based in-hand 3-D DLO pose estimation, and task-specific motion design. Experimental results demonstrate the significant superiority of our method over using parallel grippers, as well as its great robustness, generalizability, and efficiency.

cs.RO↗

arXiv2024

FacialPulse: An Efficient RNN-based Depression Detection via Temporal Facial Landmarks

Depression is a prevalent mental health disorder that significantly impacts individuals' lives and well-being. Early detection and intervention are crucial for effective treatment and management of depression. Recently, there are many end-to-end deep learning methods leveraging the facial expression features for automatic depression detection. However, most current methods overlook the temporal dynamics of facial expressions. Although very recent 3DCNN methods remedy this gap, they introduce more computational cost due to the selection of CNN-based backbones and redundant facial features. To address the above limitations, by considering the timing correlation of facial expressions, we propose a novel framework called FacialPulse, which recognizes depression with high accuracy and speed. By harnessing the bidirectional nature and proficiently addressing long-term dependencies, the Facial Motion Modeling Module (FMMM) is designed in FacialPulse to fully capture temporal features. Since the proposed FMMM has parallel processing capabilities and has the gate mechanism to mitigate gradient vanishing, this module can also significantly boost the training speed. Besides, to effectively use facial landmarks to replace original images to decrease information redundancy, a Facial Landmark Calibration Module (FLCM) is designed to eliminate facial landmark errors to further improve recognition accuracy. Extensive experiments on the AVEC2014 dataset and MMDA dataset (a depression dataset) demonstrate the superiority of FacialPulse on recognition accuracy and speed, with the average MAE (Mean Absolute Error) decreased by 21% compared to baselines, and the recognition speed increased by 100% compared to state-of-the-art methods. Codes are released at https://github.com/volatileee/FacialPulse.

cs.CV↗

arXiv2024

Wireless-Powered Mobile Crowdsensing Enhanced by UAV-Mounted RIS: Joint Transmission, Compression, and Trajectory Design

Mobile crowdsensing (MCS) enables data collection from massive devices to achieve a wide sensing range. Wireless power transfer (WPT) is a promising paradigm for prolonging the operation time of MCS systems by sustainably transferring power to distributed devices. However, the efficiency of WPT significantly deteriorates when the channel conditions are poor. Unmanned aerial vehicles (UAVs) and reconfigurable intelligent surfaces (RISs) can serve as active or passive relays to enhance the efficiency of WPT in unfavourable propagation environments. Therefore, to explore the potential of jointly deploying UAVs and RISs to enhance transmission efficiency, we propose a novel transmission framework for the WPT-assisted MCS systems, which is enhanced by a UAV-mounted RIS. Subsequently, under different compression schemes, two optimization problems are formulated to maximize the weighted sum of the data uploaded by the user equipments (UEs) by jointly designing the WPT and uploading time, the beamforming matrics, the CPU cycles, and the UAV trajectory. A block coordinate descent (BCD) algorithm based on the closed-form beamforming designs and the successive convex approximation (SCA) algorithm is proposed to solve the formulated problems. Furthermore, to highlight the insight of the gains brought by the compression schemes, we analyze the energy efficiencies of compression schemes and confirm that the gains gradually reduce with the increasing power used for compression. Simulation results demonstrate that the amount of collected data can be effectively increased in wireless-powered MCS systems.

eess.SP↗

arXiv2024

Stephanie: Step-by-Step Dialogues for Mimicking Human Interactions in Social Conversations

In the rapidly evolving field of natural language processing, dialogue systems primarily employ a single-step dialogue paradigm. Although this paradigm is efficient, it lacks the depth and fluidity of human interactions and does not appear natural. We introduce a novel \textbf{Step}-by-Step Dialogue Paradigm (Stephanie), designed to mimic the ongoing dynamic nature of human conversations. By employing a dual learning strategy and a further-split post-editing method, we generated and utilized a high-quality step-by-step dialogue dataset to fine-tune existing large language models, enabling them to perform step-by-step dialogues. We thoroughly present Stephanie. Tailored automatic and human evaluations are conducted to assess its effectiveness compared to the traditional single-step dialogue paradigm. We will release code, Stephanie datasets, and Stephanie LLMs to facilitate the future of chatbot eras.

cs.CL↗

arXiv2024

Guidelines for Augmentation Selection in Contrastive Learning for Time Series Classification

Self-supervised contrastive learning has become a key technique in deep learning, particularly in time series analysis, due to its ability to learn meaningful representations without explicit supervision. Augmentation is a critical component in contrastive learning, where different augmentations can dramatically impact performance, sometimes influencing accuracy by over 30%. However, the selection of augmentations is predominantly empirical which can be suboptimal, or grid searching that is time-consuming. In this paper, we establish a principled framework for selecting augmentations based on dataset characteristics such as trend and seasonality. Specifically, we construct 12 synthetic datasets incorporating trend, seasonality, and integration weights. We then evaluate the effectiveness of 8 different augmentations across these synthetic datasets, thereby inducing generalizable associations between time series characteristics and augmentation efficiency. Additionally, we evaluated the induced associations across 6 real-world datasets encompassing domains such as activity recognition, disease diagnosis, traffic monitoring, electricity usage, mechanical fault prognosis, and finance. These real-world datasets are diverse, covering a range from 1 to 12 channels, 2 to 10 classes, sequence lengths of 14 to 1280, and data frequencies from 250 Hz to daily intervals. The experimental results show that our proposed trend-seasonality-based augmentation recommendation algorithm can accurately identify the effective augmentations for a given time series dataset, achieving an average Recall@3 of 0.667, outperforming baselines. Our work provides guidance for studies employing contrastive learning in time series analysis, with wide-ranging applications. All the code, datasets, and analysis results will be released at https://github.com/DL4mHealth/TS-Contrastive-Augmentation-Recommendation.

cs.LG↗