arXiv subjects

Hao Chen

Publications and source records attributed to Hao Chen.

At least 883 records · Page 49Linked to original sources

arXiv2024

Codebook-enabled Generative End-to-end Semantic Communication Powered by Transformer

Codebook-based generative semantic communication attracts increasing attention, since only indices are required to be transmitted when the codebook is shared between transmitter and receiver. However, due to the fact that the semantic relations among code vectors are not necessarily related to the distance of the corresponding code indices, the performance of the codebook-enabled semantic communication system is susceptible to the channel noise. Thus, how to improve the system robustness against the noise requires careful design. This paper proposes a robust codebook-assisted image semantic communication system, where semantic codec and codebook are first jointly constructed, and then vector-to-index transformer is designed guided by the codebook to eliminate the effects of channel noise, and achieve image generation. Thanks to the assistance of the high-quality codebook to the Transformer, the generated images at the receiver outperform those of the compared methods in terms of visual perception. In the end, numerical results and generated images demonstrate the advantages of the generative semantic communication method over JPEG+LDPC and traditional joint source channel coding (JSCC) methods.

cs.IT↗

arXiv2024

PI-AstroDeconv: A Physics-Informed Unsupervised Learning Method for Astronomical Image Deconvolution

In the imaging process of an astronomical telescope, the deconvolution of its beam or Point Spread Function (PSF) is a crucial task. However, deconvolution presents a classical and challenging inverse computation problem. In scenarios where the beam or PSF is complex or inaccurately measured, such as in interferometric arrays and certain radio telescopes, the resultant blurry images are often challenging to interpret visually or analyze using traditional physical detection methods. We argue that traditional methods frequently lack specific prior knowledge, thereby leading to suboptimal performance. To address this issue and achieve image deconvolution and reconstruction, we propose an unsupervised network architecture that incorporates prior physical information. The network adopts an encoder-decoder structure while leveraging the telescope's PSF as prior knowledge. During network training, we introduced accelerated Fast Fourier Transform (FFT) convolution to enable efficient processing of high-resolution input images and PSFs. We explored various classic regression networks, including autoencoder (AE) and U-Net, and conducted a comprehensive performance evaluation through comparative analysis.

astro-ph.IM↗

arXiv2024

BronchoCopilot: Towards Autonomous Robotic Bronchoscopy via Multimodal Reinforcement Learning

Bronchoscopy plays a significant role in the early diagnosis and treatment of lung diseases. This process demands physicians to maneuver the flexible endoscope for reaching distal lesions, particularly requiring substantial expertise when examining the airways of the upper lung lobe. With the development of artificial intelligence and robotics, reinforcement learning (RL) method has been applied to the manipulation of interventional surgical robots. However, unlike human physicians who utilize multimodal information, most of the current RL methods rely on a single modality, limiting their performance. In this paper, we propose BronchoCopilot, a multimodal RL agent designed to acquire manipulation skills for autonomous bronchoscopy. BronchoCopilot specifically integrates images from the bronchoscope camera and estimated robot poses, aiming for a higher success rate within challenging airway environment. We employ auxiliary reconstruction tasks to compress multimodal data and utilize attention mechanisms to achieve an efficient latent representation of this data, serving as input for the RL module. This framework adopts a stepwise training and fine-tuning approach to mitigate the challenges of training difficulty. Our evaluation in the realistic simulation environment reveals that BronchoCopilot, by effectively harnessing multimodal information, attains a success rate of approximately 90\% in fifth generation airways with consistent movements. Additionally, it demonstrates a robust capacity to adapt to diverse cases.

cs.RO↗

arXiv2024

Boosting Box-supervised Instance Segmentation with Pseudo Depth

The realm of Weakly Supervised Instance Segmentation (WSIS) under box supervision has garnered substantial attention, showcasing remarkable advancements in recent years. However, the limitations of box supervision become apparent in its inability to furnish effective information for distinguishing foreground from background within the specified target box. This research addresses this challenge by introducing pseudo-depth maps into the training process of the instance segmentation network, thereby boosting its performance by capturing depth differences between instances. These pseudo-depth maps are generated using a readily available depth predictor and are not necessary during the inference stage. To enable the network to discern depth features when predicting masks, we integrate a depth prediction layer into the mask prediction head. This innovative approach empowers the network to simultaneously predict masks and depth, enhancing its ability to capture nuanced depth-related information during the instance segmentation process. We further utilize the mask generated in the training process as supervision to distinguish the foreground from the background. When selecting the best mask for each box through the Hungarian algorithm, we use depth consistency as one calculation cost item. The proposed method achieves significant improvements on Cityscapes and COCO dataset.

cs.CV↗

arXiv2024

Data-efficient Event Camera Pre-training via Disentangled Masked Modeling

In this paper, we present a new data-efficient voxel-based self-supervised learning method for event cameras. Our pre-training overcomes the limitations of previous methods, which either sacrifice temporal information by converting event sequences into 2D images for utilizing pre-trained image models or directly employ paired image data for knowledge distillation to enhance the learning of event streams. In order to make our pre-training data-efficient, we first design a semantic-uniform masking method to address the learning imbalance caused by the varying reconstruction difficulties of different regions in non-uniform data when using random masking. In addition, we ease the traditional hybrid masked modeling process by explicitly decomposing it into two branches, namely local spatio-temporal reconstruction and global semantic reconstruction to encourage the encoder to capture local correlations and global semantics, respectively. This decomposition allows our selfsupervised learning method to converge faster with minimal pre-training data. Compared to previous approaches, our self-supervised learning method does not rely on paired RGB images, yet enables simultaneous exploration of spatial and temporal cues in multiple scales. It exhibits excellent generalization performance and demonstrates significant improvements across various tasks with fewer parameters and lower computational costs.

cs.CV↗

arXiv2024

Anatomy-guided fiber trajectory distribution estimation for cranial nerves tractography

Diffusion MRI tractography is an important tool for identifying and analyzing the intracranial course of cranial nerves (CNs). However, the complex environment of the skull base leads to ambiguous spatial correspondence between diffusion directions and fiber geometry, and existing diffusion tractography methods of CNs identification are prone to producing erroneous trajectories and missing true positive connections. To overcome the above challenge, we propose a novel CNs identification framework with anatomy-guided fiber trajectory distribution, which incorporates anatomical shape prior knowledge during the process of CNs tracing to build diffusion tensor vector fields. We introduce higher-order streamline differential equations for continuous flow field representations to directly characterize the fiber trajectory distribution of CNs from the tract-based level. The experimental results on the vivo HCP dataset and the clinical MDM dataset demonstrate that the proposed method reduces false-positive fiber production compared to competing methods and produces reconstructed CNs (i.e. CN II, CN III, CN V, and CN VII/VIII) that are judged to better correspond to the known anatomy.

eess.IV↗

arXiv2024

Prototypical Information Bottlenecking and Disentangling for Multimodal Cancer Survival Prediction

Multimodal learning significantly benefits cancer survival prediction, especially the integration of pathological images and genomic data. Despite advantages of multimodal learning for cancer survival prediction, massive redundancy in multimodal data prevents it from extracting discriminative and compact information: (1) An extensive amount of intra-modal task-unrelated information blurs discriminability, especially for gigapixel whole slide images (WSIs) with many patches in pathology and thousands of pathways in genomic data, leading to an ``intra-modal redundancy" issue. (2) Duplicated information among modalities dominates the representation of multimodal data, which makes modality-specific information prone to being ignored, resulting in an ``inter-modal redundancy" issue. To address these, we propose a new framework, Prototypical Information Bottlenecking and Disentangling (PIBD), consisting of Prototypical Information Bottleneck (PIB) module for intra-modal redundancy and Prototypical Information Disentanglement (PID) module for inter-modal redundancy. Specifically, a variant of information bottleneck, PIB, is proposed to model prototypes approximating a bunch of instances for different risk levels, which can be used for selection of discriminative instances within modality. PID module decouples entangled multimodal data into compact distinct components: modality-common and modality-specific knowledge, under the guidance of the joint prototypical distribution. Extensive experiments on five cancer benchmark datasets demonstrated our superiority over other methods.

cs.CV↗

arXiv2024

Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey

Transformer-based Large Language Models (LLMs) have been applied in diverse areas such as knowledge bases, human interfaces, and dynamic agents, and marking a stride towards achieving Artificial General Intelligence (AGI). However, current LLMs are predominantly pretrained on short text snippets, which compromises their effectiveness in processing the long-context prompts that are frequently encountered in practical scenarios. This article offers a comprehensive survey of the recent advancement in Transformer-based LLM architectures aimed at enhancing the long-context capabilities of LLMs throughout the entire model lifecycle, from pre-training through to inference. We first delineate and analyze the problems of handling long-context input and output with the current Transformer-based models. We then provide a taxonomy and the landscape of upgrades on Transformer architecture to solve these problems. Afterwards, we provide an investigation on wildly used evaluation necessities tailored for long-context LLMs, including datasets, metrics, and baseline models, as well as optimization toolkits such as libraries, frameworks, and compilers to boost the efficacy of LLMs across different stages in runtime. Finally, we discuss the challenges and potential avenues for future research. A curated repository of relevant literature, continuously updated, is available at https://github.com/Strivin0311/long-llms-learning.

cs.CL↗

arXiv2024

Cyclic and Negacyclic Codes with Optimal and Best Known Minimum Distances

In this paper, we construct a new family of distance-optimal binary cyclic codes with the minimum distance $6$ and a new family of distance-optimal quaternary cyclic codes with the minimum distance $4$. We also construct several families of cyclic and negacyclic codes over ${\bf F}_2$, ${\bf F}_3$, ${\bf F}_4$, ${\bf F}_5$, ${\bf F}_7$ and ${\bf F}_9$ with good parameters $n,\,k,\,d$, such that the maximal possible minimum distance $d_{max}$ of a linear $[n, k]_q$ code is at most $d_{max} \leq d+8$. The first codes in these families have optimal or best known minimum distances. $145$ optimal or best known codes are constructed as cyclic codes, negacyclic codes, their shortening codes and punctured codes. All optimal or best known codes constructed in this paper are not equivalent to the presently best known codes. Several infinite families of negacyclic $[n,\frac{n+1}{2}, d]_q$ codes or $[n, \frac{n}{2}, d]_q$ codes, such that their minimum distances satisfy $d\approx O(\frac{n}{\log_q n})$, are also constructed. These are first several families of such negacyclic codes.

cs.IT↗

arXiv2024

Quasi-Perfect and Distance-Optimal Codes Sum-Rank Codes

Constructions of distance-optimal codes and quasi-perfect codes are challenging problems and have attracted many attentions. In this paper, we give the following three results. 1) If $λ|q^{sm}-1$ and $λ<\sqrt{\frac{(q^s-1)}{2(q-1)^2(1+ε)}}$, an infinite family of distance-optimal $q$-ary cyclic sum-rank codes with the block length $t=\frac{q^{sm}-1}λ$, the matrix size $s \times s$, the cardinality $q^{s^2t-s(2m+3)}$ and the minimum sum-rank distance four is constructed. 2) Block length $q^4-1$ and the matrix size $2 \times 2$ distance-optimal sum-rank codes with the minimum sum-rank distance four and the Singleton defect four are constructed. These sum-rank codes are close to the sphere packing bound , the Singleton-like bound and have much larger block length $q^4-1>>q-1$. 3) For given positive integers $m$ satisfying $2 \leq m$, an infinite family of quasi-perfect sum-rank codes with the matrix size $2 \times m$, and the minimum sum-rank distance three is also constructed. Quasi-perfect binary sum-rank codes with the minimum sum-rank distance four are also given. Almost MSRD $q$-ary codes with the block lengths up to $q^2$ are given. We show that more distance-optimal binary sum-rank codes can be obtained from the Plotkin sum.

cs.IT↗

arXiv2024

Deep Rib Fracture Instance Segmentation and Classification from CT on the RibFrac Challenge

Rib fractures are a common and potentially severe injury that can be challenging and labor-intensive to detect in CT scans. While there have been efforts to address this field, the lack of large-scale annotated datasets and evaluation benchmarks has hindered the development and validation of deep learning algorithms. To address this issue, the RibFrac Challenge was introduced, providing a benchmark dataset of over 5,000 rib fractures from 660 CT scans, with voxel-level instance mask annotations and diagnosis labels for four clinical categories (buckle, nondisplaced, displaced, or segmental). The challenge includes two tracks: a detection (instance segmentation) track evaluated by an FROC-style metric and a classification track evaluated by an F1-style metric. During the MICCAI 2020 challenge period, 243 results were evaluated, and seven teams were invited to participate in the challenge summary. The analysis revealed that several top rib fracture detection solutions achieved performance comparable or even better than human experts. Nevertheless, the current rib fracture classification solutions are hardly clinically applicable, which can be an interesting area in the future. As an active benchmark and research resource, the data and online evaluation of the RibFrac Challenge are available at the challenge website. As an independent contribution, we have also extended our previous internal baseline by incorporating recent advancements in large-scale pretrained networks and point-based rib segmentation techniques. The resulting FracNet+ demonstrates competitive performance in rib fracture detection, which lays a foundation for further research and development in AI-assisted rib fracture detection and diagnosis.

eess.IV↗

arXiv2024

Physics-Informed Neural Networks with Hard Linear Equality Constraints

Surrogate modeling is used to replace computationally expensive simulations. Neural networks have been widely applied as surrogate models that enable efficient evaluations over complex physical systems. Despite this, neural networks are data-driven models and devoid of any physics. The incorporation of physics into neural networks can improve generalization and data efficiency. The physics-informed neural network (PINN) is an approach to leverage known physical constraints present in the data, but it cannot strictly satisfy them in the predictions. This work proposes a novel physics-informed neural network, KKT-hPINN, which rigorously guarantees hard linear equality constraints through projection layers derived from KKT conditions. Numerical experiments on Aspen models of a continuous stirred-tank reactor (CSTR) unit, an extractive distillation subsystem, and a chemical plant demonstrate that this model can further enhance the prediction accuracy.

cs.LG↗

arXiv2024

Time Series Supplier Allocation via Deep Black-Litterman Model

Time Series Supplier Allocation (TSSA) poses a complex NP-hard challenge, aimed at refining future order dispatching strategies to satisfy order demands with maximum supply efficiency fully. Traditionally derived from financial portfolio management, the Black-Litterman (BL) model offers a new perspective for the TSSA scenario by balancing expected returns against insufficient supply risks. However, its application within TSSA is constrained by the reliance on manually constructed perspective matrices and spatio-temporal market dynamics, coupled with the absence of supervisory signals and data unreliability inherent to supplier information. To solve these limitations, we introduce the pioneering Deep Black-Litterman Model (DBLM), which innovatively adapts the BL model from financial roots to supply chain context. Leveraging the Spatio-Temporal Graph Neural Networks (STGNNS), DBLM automatically generates future perspective matrices for TSSA, by integrating spatio-temporal dependency. Moreover, a novel Spearman rank correlation distinctively supervises our approach to address the lack of supervisory signals, specifically designed to navigate through the complexities of supplier risks and interactions. This is further enhanced by a masking mechanism aimed at counteracting the biases from unreliable data, thereby improving the model's precision and reliability. Extensive experimentation on two datasets unequivocally demonstrates DBLM's enhanced performance in TSSA, setting new standards for the field. Our findings and methodology are made available for community access and further development.

cs.LG↗

arXiv2024

Multi-Collinear Splitting Kernels for Track Function Evolution

Jets and their substructure play a central role in many analyses at the Large Hadron Collider (LHC). To improve the precision of measurements, as well as to enable measurement of jet substructure at increasingly small angular scales, tracking information is often used due to its superior angular resolution and robustness to pile-up. Calculations of track-based observables involve non-perturbative track functions, that absorb infrared divergences in perturbative calculations and describe the transition to charged hadrons. The infrared divergences are directly related to the renormalization group evolution (RGE), and can be systematically computed in perturbation theory. Unlike the standard DGLAP evolution, the RGE of the track functions is non-linear, encoding correlations in the fragmentation process. We compute the next-to-leading order (NLO) evolution of the track functions, which involves in its kernel the full $1\rightarrow3$ splitting function. We discuss in detail how how we implement the evolution equation numerically, and illustrate the size of the NLO corrections. We also show that our equation can be viewed as a master equation for collinear evolution at NLO, by illustrating that by integrating out specific terms, one can derive the evolution for any $N$-hadron fragmentation function. Our results provide a crucial ingredient for obtaining track-based predictions for generic measurements at the LHC, and for improving the description of the collinear dynamics of jets.

hep-ph↗

arXiv2024

UniTSyn: A Large-Scale Dataset Capable of Enhancing the Prowess of Large Language Models for Program Testing

The remarkable capability of large language models (LLMs) in generating high-quality code has drawn increasing attention in the software testing community. However, existing code LLMs often demonstrate unsatisfactory capabilities in generating accurate and complete tests since they were trained on code snippets collected without differentiating between code for testing purposes and other code. In this paper, we present a large-scale dataset UniTSyn, which is capable of enhancing the prowess of LLMs for Unit Test Synthesis. Associating tests with the tested functions is crucial for LLMs to infer the expected behavior and the logic paths to be verified. By leveraging Language Server Protocol, UniTSyn achieves the challenging goal of collecting focal-test pairs without per-project execution setups or per-language heuristics that tend to be fragile and difficult to scale. It contains 2.7 million focal-test pairs across five mainstream programming languages, making it possible to be utilized for enhancing the test generation ability of LLMs. The details of UniTSyn can be found in Table 1. Our experiments demonstrate that, by building an autoregressive model based on UniTSyn, we can achieve significant benefits in learning and understanding unit test representations, resulting in improved generation accuracy and code coverage across all evaluated programming languages. Code and data will be publicly available.

cs.SE↗

arXiv2024

Completing Visual Objects via Bridging Generation and Segmentation

This paper presents a novel approach to object completion, with the primary goal of reconstructing a complete object from its partially visible components. Our method, named MaskComp, delineates the completion process through iterative stages of generation and segmentation. In each iteration, the object mask is provided as an additional condition to boost image generation, and, in return, the generated images can lead to a more accurate mask by fusing the segmentation of images. We demonstrate that the combination of one generation and one segmentation stage effectively functions as a mask denoiser. Through alternation between the generation and segmentation stages, the partial object mask is progressively refined, providing precise shape guidance and yielding superior object completion results. Our experiments demonstrate the superiority of MaskComp over existing approaches, e.g., ControlNet and Stable Diffusion, establishing it as an effective solution for object completion.

cs.CV↗

arXiv2024

Uncertainty-Aware Explainable Recommendation with Large Language Models

Providing explanations within the recommendation system would boost user satisfaction and foster trust, especially by elaborating on the reasons for selecting recommended items tailored to the user. The predominant approach in this domain revolves around generating text-based explanations, with a notable emphasis on applying large language models (LLMs). However, refining LLMs for explainable recommendations proves impractical due to time constraints and computing resource limitations. As an alternative, the current approach involves training the prompt rather than the LLM. In this study, we developed a model that utilizes the ID vectors of user and item inputs as prompts for GPT-2. We employed a joint training mechanism within a multi-task learning framework to optimize both the recommendation task and explanation task. This strategy enables a more effective exploration of users' interests, improving recommendation effectiveness and user satisfaction. Through the experiments, our method achieving 1.59 DIV, 0.57 USR and 0.41 FCR on the Yelp, TripAdvisor and Amazon dataset respectively, demonstrates superior performance over four SOTA methods in terms of explainability evaluation metric. In addition, we identified that the proposed model is able to ensure stable textual quality on the three public datasets.

cs.IR↗

arXiv2024

Uncertainty Quantification via Spatial-Temporal Tweedie Model for Zero-inflated and Long-tail Travel Demand Prediction

Understanding Origin-Destination (O-D) travel demand is crucial for transportation management. However, traditional spatial-temporal deep learning models grapple with addressing the sparse and long-tail characteristics in high-resolution O-D matrices and quantifying prediction uncertainty. This dilemma arises from the numerous zeros and over-dispersed demand patterns within these matrices, which challenge the Gaussian assumption inherent to deterministic deep learning models. To address these challenges, we propose a novel approach: the Spatial-Temporal Tweedie Graph Neural Network (STTD). The STTD introduces the Tweedie distribution as a compelling alternative to the traditional 'zero-inflated' model and leverages spatial and temporal embeddings to parameterize travel demand distributions. Our evaluations using real-world datasets highlight STTD's superiority in providing accurate predictions and precise confidence intervals, particularly in high-resolution scenarios.

cs.LG↗