arXiv subjects

Xiao Sun

Publications and source records attributed to Xiao Sun.

At least 73 records · Page 4Linked to original sources

arXiv2025

PEARL: Parallel Speculative Decoding with Adaptive Draft Length

Speculative decoding (SD), where an extra draft model is employed to provide multiple draft tokens first, and then the original target model verifies these tokens in parallel, has shown great power for LLM inference acceleration. However, existing SD methods suffer from the mutual waiting problem, i.e., the target model gets stuck when the draft model is guessing tokens, and vice versa. This problem is directly incurred by the asynchronous execution of the draft model and the target model and is exacerbated due to the fixed draft length in speculative decoding. To address these challenges, we propose a conceptually simple, flexible, and general framework to boost speculative decoding, namely Parallel spEculative decoding with Adaptive dRaft Length (PEARL). Specifically, PEARL proposes pre-verify to verify the first draft token in advance during the drafting phase, and post-verify to generate more draft tokens during the verification phase. PEARL parallels the drafting phase and the verification phase via applying the two strategies, and achieves adaptive draft length for different scenarios, which effectively alleviates the mutual waiting problem. Experiments on various text generation benchmarks demonstrate the effectiveness of our PEARL, leading to a superior speed up performance up to 4.43$\times$ and 1.50$\times$, compared to auto-regressive decoding and vanilla speculative decoding, respectively. Our code is available at https://github.com/smart-lty/ParallelSpeculativeDecoding.

cs.CL↗

arXiv2025

Multi-Class Segmentation of Aortic Branches and Zones in Computed Tomography Angiography: The AortaSeg24 Challenge

Multi-class segmentation of the aorta in computed tomography angiography (CTA) scans is essential for diagnosing and planning complex endovascular treatments for patients with aortic dissections. However, existing methods reduce aortic segmentation to a binary problem, limiting their ability to measure diameters across different branches and zones. Furthermore, no open-source dataset is currently available to support the development of multi-class aortic segmentation methods. To address this gap, we organized the AortaSeg24 MICCAI Challenge, introducing the first dataset of 100 CTA volumes annotated for 23 clinically relevant aortic branches and zones. This dataset was designed to facilitate both model development and validation. The challenge attracted 121 teams worldwide, with participants leveraging state-of-the-art frameworks such as nnU-Net and exploring novel techniques, including cascaded models, data augmentation strategies, and custom loss functions. We evaluated the submitted algorithms using the Dice Similarity Coefficient (DSC) and Normalized Surface Distance (NSD), highlighting the approaches adopted by the top five performing teams. This paper presents the challenge design, dataset details, evaluation metrics, and an in-depth analysis of the top-performing algorithms. The annotated dataset, evaluation code, and implementations of the leading methods are publicly available to support further research. All resources can be accessed at https://aortaseg24.grand-challenge.org.

eess.IV↗

arXiv2025

Heterogeneous-free narrow linewidth semiconductor laser with optical injection locking

Narrow linewidth lasers are indispensable for coherent optical systems, including communications, metrology, and sensing. Although compact semiconductor lasers with narrow linewidths and low noise have been demonstrated, their spectral purity typically relies on hybrid or heterogeneous external cavity feedback. Here, we present a theoretical and experimental demonstration of a heterogeneous free optical injection locking (HF OIL) semiconductor laser. By integrating a topological interface state extended (TISE) laser with a micro ring resonator (MRR) on an AlGaInAs multiple quantum well platform,we achieve monolithic photon injection and phase locking, thereby reducing the optical linewidth. We fabricated and characterized a 1550 nm sidewall HF OIL laser, achieving stable single mode operation over a broad current range (65 to 300 mA) and a side mode suppression ratio (SMSR) over 50 dB. Under injection locking, the devices Voigt fitted linewidth narrowed from over 1.7 MHz (free running) to 4.2 kHz, representing a three order of magnitude improvement over conventional distributed feedback lasers. The intrinsic linewidth of 1.4 kHz is measured by correlated delayed self-heterodyne frequency noise power spectrum density (FN PSD) method. Moreover, the HF OIL laser demonstrated high phase stability and the ability to transition from a random phased to a phase locked state. These results underscore the potential of HF-OIL lasers in advancing coherent optical communications and phase encoders in quantum key distribution (QKD) systems.

physics.optics↗

arXiv2025

DEFormer: DCT-driven Enhancement Transformer for Low-light Image and Dark Vision

Low-light image enhancement restores the colors and details of a single image and improves high-level visual tasks. However, restoring the lost details in the dark area is still a challenge relying only on the RGB domain. In this paper, we delve into frequency as a new clue into the model and propose a DCT-driven enhancement transformer (DEFormer) framework. First, we propose a learnable frequency branch (LFB) for frequency enhancement contains DCT processing and curvature-based frequency enhancement (CFE) to represent frequency features. Additionally, we propose a cross domain fusion (CDF) to reduce the differences between the RGB domain and the frequency domain. Our DEFormer has achieved superior results on the LOL and MIT-Adobe FiveK datasets, improving the dark detection performance.

cs.CV↗

arXiv2024

GRPose: Learning Graph Relations for Human Image Generation with Pose Priors

Recent methods using diffusion models have made significant progress in human image generation with various control signals such as pose priors. However, existing efforts are still struggling to generate high-quality images with consistent pose alignment, resulting in unsatisfactory output. In this paper, we propose a framework that delves into the graph relations of pose priors to provide control information for human image generation. The main idea is to establish a graph topological structure between the pose priors and latent representation of diffusion models to capture the intrinsic associations between different pose parts. A Progressive Graph Integrator (PGI) is designed to learn the spatial relationships of the pose priors with the graph structure, adopting a hierarchical strategy within an Adapter to gradually propagate information across different pose parts. Besides, a pose perception loss is introduced based on a pretrained pose estimation network to minimize the pose differences. Extensive qualitative and quantitative experiments conducted on the Human-Art and LAION-Human datasets clearly demonstrate that our model can achieve significant performance improvement over the latest benchmark models. The code is available at \url{https://xiangchenyin.github.io/GRPose/}.

cs.CV↗

arXiv2024

Temporal-Frequency State Space Duality: An Efficient Paradigm for Speech Emotion Recognition

Speech Emotion Recognition (SER) plays a critical role in enhancing user experience within human-computer interaction. However, existing methods are overwhelmed by temporal domain analysis, overlooking the valuable envelope structures of the frequency domain that are equally important for robust emotion recognition. To overcome this limitation, we propose TF-Mamba, a novel multi-domain framework that captures emotional expressions in both temporal and frequency dimensions.Concretely, we propose a temporal-frequency mamba block to extract temporal- and frequency-aware emotional features, achieving an optimal balance between computational efficiency and model expressiveness. Besides, we design a Complex Metric-Distance Triplet (CMDT) loss to enable the model to capture representative emotional clues for SER. Extensive experiments on the IEMOCAP and MELD datasets show that TF-Mamba surpasses existing methods in terms of model size and latency, providing a more practical solution for future SER applications.

cs.SD↗

arXiv2024

PsycoLLM: Enhancing LLM for Psychological Understanding and Evaluation

Mental health has attracted substantial attention in recent years and LLM can be an effective technology for alleviating this problem owing to its capability in text understanding and dialogue. However, existing research in this domain often suffers from limitations, such as training on datasets lacking crucial prior knowledge and evidence, and the absence of comprehensive evaluation methods. In this paper, we propose a specialized psychological large language model (LLM), named PsycoLLM, trained on a proposed high-quality psychological dataset, including single-turn QA, multi-turn dialogues and knowledge-based QA. Specifically, we construct multi-turn dialogues through a three-step pipeline comprising multi-turn QA generation, evidence judgment, and dialogue refinement. We augment this process with real-world psychological case backgrounds extracted from online platforms, enhancing the relevance and applicability of the generated data. Additionally, to compare the performance of PsycoLLM with other LLMs, we develop a comprehensive psychological benchmark based on authoritative psychological counseling examinations in China, which includes assessments of professional ethics, theoretical proficiency, and case analysis. The experimental results on the benchmark illustrate the effectiveness of PsycoLLM, which demonstrates superior performance compared to other LLMs.

cs.CL↗

arXiv2024

A new fidelity of quantum channel evolution and its geometric interpretation

Fidelity is crucial for characterizing transformations of quantum states under various quantum channels, which can be served as a fundamental tool in resource theories. Firstly, we define an $α$-$z$-fidelity as a significant quantity in quantum information theory and give the properties of the fidelity with orders $α$ and $z$. Secondly, by analyzing the $α$-$z$-fidelity under the evolution of different types of quantum channels (single orbit, all quantum channels, unitary quantum channels, and mixed unitary quantum channels), we propose a limit formula for the maximum and the minimum of the $α$-$z$-fidelity. In addition, we have extended the $α$-$z$-Rényi relative entropy, providing new insights into its relevance for resource quantification. Finally, we offer a geometric interpretation for measuring the distance between quantum states, contributing to the broader understanding of the operational and transformative power of dynamical quantum resources across various physical settings.

quant-ph↗

arXiv2024

DIR: Retrieval-Augmented Image Captioning with Comprehensive Understanding

Image captioning models often suffer from performance degradation when applied to novel datasets, as they are typically trained on domain-specific data. To enhance generalization in out-of-domain scenarios, retrieval-augmented approaches have garnered increasing attention. However, current methods face two key challenges: (1) image features used for retrieval are often optimized based on ground-truth (GT) captions, which represent the image from a specific perspective and are influenced by annotator biases, and (2) they underutilize the full potential of retrieved text, typically relying on raw captions or parsed objects, which fail to capture the full semantic richness of the data. In this paper, we propose Dive Into Retrieval (DIR), a method designed to enhance both the image-to-text retrieval process and the utilization of retrieved text to achieve a more comprehensive understanding of the visual content. Our approach introduces two key innovations: (1) diffusion-guided retrieval enhancement, where a pretrained diffusion model guides image feature learning by reconstructing noisy images, allowing the model to capture more comprehensive and fine-grained visual information beyond standard annotated captions; and (2) a high-quality retrieval database, which provides comprehensive semantic information to enhance caption generation, especially in out-of-domain scenarios. Extensive experiments demonstrate that DIR not only maintains competitive in-domain performance but also significantly improves out-of-domain generalization, all without increasing inference costs.

cs.CV↗

arXiv2024

X as Supervision: Contending with Depth Ambiguity in Unsupervised Monocular 3D Pose Estimation

Recent unsupervised methods for monocular 3D pose estimation have endeavored to reduce dependence on limited annotated 3D data, but most are solely formulated in 2D space, overlooking the inherent depth ambiguity issue. Due to the information loss in 3D-to-2D projection, multiple potential depths may exist, yet only some of them are plausible in human structure. To tackle depth ambiguity, we propose a novel unsupervised framework featuring a multi-hypothesis detector and multiple tailored pretext tasks. The detector extracts multiple hypotheses from a heatmap within a local window, effectively managing the multi-solution problem. Furthermore, the pretext tasks harness 3D human priors from the SMPL model to regularize the solution space of pose estimation, aligning it with the empirical distribution of 3D human structures. This regularization is partially achieved through a GCN-based discriminator within the discriminative learning, and is further complemented with synthetic images through rendering, ensuring plausible estimations. Consequently, our approach demonstrates state-of-the-art unsupervised 3D pose estimation performance on various human datasets. Further evaluations on data scale-up and one animal dataset highlight its generalization capabilities. Code will be available at https://github.com/Charrrrrlie/X-as-Supervision.

cs.CV↗

arXiv2024

HRRPGraphNet: Make HRRPs to Be Graphs for Efficient Target Recognition

High Resolution Range Profiles (HRRP) have become a key area of focus in the domain of Radar Automatic Target Recognition (RATR). Despite the success of deep learning based HRRP recognition, these methods needs a large amount of training samples to generate good performance, which could be a severe challenge under non-cooperative circumstances. Currently, deep learning based models treat HRRP as sequences, which may lead to ignorance of the internal relationship of range cells. This letter introduces HRRPGraphNet, whose pivotal innovation is the transformation of HRRP data into a novel graph structure, utilizing a range cell amplitude(hyphen)based node vector and a range(hyphen)relative adjacency matrix. This graph(hyphen)based approach facilitates both local feature extraction via one(hyphen)dimensional convolution layers, global feature extraction through a graph convolution layer and a attention module. Experiments on the aircraft electromagnetic simulation dataset confirmed HRRPGraphNet superior accuracy and robustness, particularly in limited training sample environments, underscoring the potential of graph(hyphen)driven innovations in HRRP(hyphen)based RATR.

eess.SP↗

arXiv2024

Multi-Wavelength DFB Laser Based on Sidewall Third Order Four Phase-Shifted Sampled Bragg Grating with Uniform Wavelength Spacing

We present the first demonstration of a 1550 nm multi-wavelength distributed feedback (MW-DFB) laser employing a third-order, four-phase-shifted sampled sidewall grating. By utilizing linearly chirped sampled gratings and incorporating multiple true π-phase shifts within the cavity, we achieved and experimentally validated a four-wavelength laser with a channel spacing of 0.4 nm. The device operates stably and uniformly across a wide range of injection currents from 280 mA to 350 mA. The average wavelength spacing was measured at 0.401 nm with a standard deviation of 0.0081 nm. Additionally, we demonstrated a 0.3 nm MW-DFB laser with a seven-channel output, achieving a wavelength spacing of 0.274 nm and a standard deviation of 0.0055 nm. This MW-DFB laser features a ridge waveguide with sidewall gratings, requiring only one metalorganic vapor-phase epitaxy (MOVPE) step and a single III-V material etching process. This streamlined fabrication approach simplifies device manufacturing and is well-suited for dense wavelength division multiplexing (DWDM) systems.

physics.optics↗

arXiv2024

Continuous Phase Modulation Technology Based on Grating Period Interval for High Grating Coupling Efficiency and Precise Wavelength Control

A novel grating modulation technique for laser arrays is proposed and demonstrated. This method modifies the initial phase within each grating period, applying a total phase shift that increments in an arithmetic progression, ensuring equal channel spacing across the array. Despite the varying phase shifts, the device maintains coupling efficiency comparable to traditional uniform grating structures. Furthermore, the continuous phase modulation enhances the stability of the lasing wavelength of the primary mode, reducing sensitivity to fabrication errors. This improved tolerance to manufacturing inaccuracies represents a significant technological advancement, making this approach highly promising for applications requiring precise and stable wavelength control.

physics.optics↗

arXiv2024

Prior Knowledge Distillation Network for Face Super-Resolution

The purpose of face super-resolution (FSR) is to reconstruct high-resolution (HR) face images from low-resolution (LR) inputs. With the continuous advancement of deep learning technologies, contemporary prior-guided FSR methods initially estimate facial priors and then use this information to assist in the super-resolution reconstruction process. However, ensuring the accuracy of prior estimation remains challenging, and straightforward cascading and convolutional operations often fail to fully leverage prior knowledge. Inaccurate or insufficiently utilized prior information inevitably degrades FSR performance. To address this issue, we propose a prior knowledge distillation network (PKDN) for FSR, which involves transferring prior information from the teacher network to the student network. This approach enables the network to learn priors during the training stage while relying solely on low-resolution facial images during the testing stage, thus mitigating the adverse effects of prior estimation inaccuracies. Additionally, we incorporate robust attention mechanisms to design a parsing map fusion block that effectively utilizes prior information. To prevent feature loss, we retain multi-scale features during the feature extraction stage and employ them in the subsequent super-resolution reconstruction process. Experimental results on benchmark datasets demonstrate that our PKDN approach surpasses existing FSR methods in generating high-quality face images.

cs.CV↗

arXiv2024

Narrow Linewidth Distributed Feedback Lasers Utilizing Distributed Phase Shift

This study proposes and experimentally demonstrates a distributed feedback (DFB) laser with a distributed phase shift (DPS) region at the center of the DFB cavity. By modeling the field intensity distribution in the cavity and the output spectrum, the DPS region length and phase shift values have been optimized. Experimental comparisons with lasers using traditional π-phase shifts confirm that DFB lasers with optimized DPS lengths and larger phase shifts (up to 15π) achieve stable single longitudinal mode operation over a broader current range, with lower threshold current, higher power slope efficiency, and a higher side mode suppression ratio (SMSR). Furthermore, the minimum optical linewidth is reduced significantly, from 1.3 MHz to 220 kHz.

physics.optics↗

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

Compound Expression Recognition via Multi Model Ensemble for the ABAW7 Challenge

Compound Expression Recognition (CER) is vital for effective interpersonal interactions. Human emotional expressions are inherently complex due to the presence of compound expressions, requiring the consideration of both local and global facial cues for accurate judgment. In this paper, we propose an ensemble learning-based solution to address this complexity. Our approach involves training three distinct expression classification models using convolutional networks, Vision Transformers, and multiscale local attention networks. By employing late fusion for model ensemble, we combine the outputs of these models to predict the final results. Our method demonstrates high accuracy on the RAF-DB datasets and is capable of recognizing expressions in certain portions of the C-EXPR-DB through zero-shot learning.

cs.CV↗

arXiv2024

Facial Affect Recognition based on Multi Architecture Encoder and Feature Fusion for the ABAW7 Challenge

In this paper, we present our approach to addressing the challenges of the 7th ABAW competition. The competition comprises three sub-challenges: Valence Arousal (VA) estimation, Expression (Expr) classification, and Action Unit (AU) detection. To tackle these challenges, we employ state-of-the-art models to extract powerful visual features. Subsequently, a Transformer Encoder is utilized to integrate these features for the VA, Expr, and AU sub-challenges. To mitigate the impact of varying feature dimensions, we introduce an affine module to align the features to a common dimension. Overall, our results significantly outperform the baselines.

cs.CV↗