arXiv subjects

Han Zhang

Publications and source records attributed to Han Zhang.

At least 289 records · Page 16Linked to original sources

arXiv2024

Memory-based Cross-modal Semantic Alignment Network for Radiology Report Generation

Generating radiology reports automatically reduces the workload of radiologists and helps the diagnoses of specific diseases. Many existing methods take this task as modality transfer process. However, since the key information related to disease accounts for a small proportion in both image and report, it is hard for the model to learn the latent relation between the radiology image and its report, thus failing to generate fluent and accurate radiology reports. To tackle this problem, we propose a memory-based cross-modal semantic alignment model (MCSAM) following an encoder-decoder paradigm. MCSAM includes a well initialized long-term clinical memory bank to learn disease-related representations as well as prior knowledge for different modalities to retrieve and use the retrieved memory to perform feature consolidation. To ensure the semantic consistency of the retrieved cross modal prior knowledge, a cross-modal semantic alignment module (SAM) is proposed. SAM is also able to generate semantic visual feature embeddings which can be added to the decoder and benefits report generation. More importantly, to memorize the state and additional information while generating reports with the decoder, we use learnable memory tokens which can be seen as prompts. Extensive experiments demonstrate the promising performance of our proposed method which generates state-of-the-art performance on the MIMIC-CXR dataset.

cs.CV↗

arXiv2024

COPR: Continual Learning Human Preference through Optimal Policy Regularization

The technique of Reinforcement Learning from Human Feedback (RLHF) is a commonly employed method to improve pre-trained Language Models (LM), enhancing their ability to conform to human preferences. Nevertheless, the current RLHF-based LMs necessitate full retraining each time novel queries or feedback are introduced, which becomes a challenging task because human preferences can vary between different domains or tasks. Retraining LMs poses practical difficulties in many real-world situations due to the significant time and computational resources required, along with concerns related to data privacy. To address this limitation, we propose a new method called Continual Optimal Policy Regularization (COPR), in which we compute the distribution of optimal policy bypassing the partition function and then regularize the current policy based on the historically optimal distribution to mitigate Catastrophic Forgetting (CF). COPR involves a single learning phase and doesn't necessitate complex reinforcement learning. Importantly, it shares the capability with RLHF to learn from unlabeled data by maintaining a scoring module, similar to reward model, making it flexible for continually learning without human feedback. Our experimental results show that COPR outperforms strong Continuous Learning (CL) baselines when it comes to consistently aligning with human preferences on incremental tasks and domains.

cs.LG↗

arXiv2024

Revisiting Trimaximal TM2 mixing in two $A_4$ modular symmetries

We discuss a minimal lepton flavour model with two modular $A_4$ symmetries, one acting on neutrinos and the other acting on charged leptons. Two corresponding moduli fields are restricted at stabilisers. To avoid vanishing or degenerate lepton masses, the stabiliser in the charged lepton sector always preserves a $Z_3$ symmetry, and that in the neutrino preserves a $Z_2$ symmetry. By scanning all viable stabilisers, a unique Trimaximal TM2 mixing is predicted. However, the prediction of the lightest neutrino mass and the mass parameter in neutrinoless double beta decay, as well as two Majorana phases, are different and classified into three cases.

hep-ph↗

arXiv2024

Generation of True Quantum Random Numbers with On-Demand Probability Distributions via Single-Photon Quantum Walks

Random numbers are at the heart of diverse fields, ranging from simulations of stochastic processes to classical and quantum cryptography. The requirement for true randomness in these applications has motivated various proposals for generating random numbers based on the inherent randomness of quantum systems. The generation of true random numbers with arbitrarily defined probability distributions is highly desirable for applications, but it is very challenging. Here we show that single-photon quantum walks can generate multi-bit random numbers with on-demand probability distributions, when the required ``coin'' parameters are found with the gradient descent (GD) algorithm. Our theoretical and experimental results exhibit high fidelity for various selected distributions. This GD-enhanced single-photon system provides a convenient way for building flexible and reliable quantum random number generators. Multi-bit random numbers are a necessary resource for high-dimensional quantum key distribution.

quant-ph↗

arXiv2024

Statistically consistent inverse optimal control for discrete-time indefinite linear-quadratic systems

The Inverse Optimal Control (IOC) problem is a structured system identification problem that aims to identify the underlying objective function based on observed optimal trajectories. This provides a data-driven way to model experts' behavior. In this paper, we consider the case of discrete-time finite-horizon linear-quadratic problems where: the quadratic cost term in the objective is not necessarily positive semi-definite; the planning horizon is a random variable; we have both process noise and observation noise; the dynamics can have a drift term; and where we can have a linear cost term in the objective. In this setting, we first formulate the necessary and sufficient conditions for when the forward optimal control problem is solvable. Next, we show that the corresponding IOC problem is identifiable. Using the conditions for existence of an optimum of the forward problem, we then formulate an estimator for the parameters in the objective function of the forward problem as the globally optimal solution to a convex optimization problem, and prove that the estimator is statistical consistent. Finally, the performance of the algorithm is demonstrated on two numerical examples.

math.OC↗

arXiv2024

Freshness-aware Resource Allocation for Non-orthogonal Wireless-powered IoT Networks

This paper investigates a wireless-powered Internet of Things (IoT) network comprising a hybrid access point (HAP) and two devices. The HAP facilitates downlink wireless energy transfer (WET) for device charging and uplink wireless information transfer (WIT) to collect status updates from the devices. To keep the information fresh, concurrent WET and WIT are allowed, and orthogonal multiple access (OMA) and non-orthogonal multiple access (NOMA) are adaptively scheduled for WIT. Consequently, we formulate an expected weighted sum age of information (EWSAoI) minimization problem to adaptively schedule the transmission scheme, choosing from WET, OMA, NOMA, and WET+OMA, and to allocate transmit power. To address this, we reformulate the problem as a Markov decision process (MDP) and develop an optimal policy based on instantaneous AoI and remaining battery power to determine scheme selection and transmit power allocation. Extensive results demonstrate the effectiveness of the proposed policy, and the optimal policy has a distinct decision boundary-switching property, providing valuable insights for practical system design.

cs.IT↗

arXiv2024

Cas-DiffCom: Cascaded diffusion model for infant longitudinal super-resolution 3D medical image completion

Early infancy is a rapid and dynamic neurodevelopmental period for behavior and neurocognition. Longitudinal magnetic resonance imaging (MRI) is an effective tool to investigate such a crucial stage by capturing the developmental trajectories of the brain structures. However, longitudinal MRI acquisition always meets a serious data-missing problem due to participant dropout and failed scans, making longitudinal infant brain atlas construction and developmental trajectory delineation quite challenging. Thanks to the development of an AI-based generative model, neuroimage completion has become a powerful technique to retain as much available data as possible. However, current image completion methods usually suffer from inconsistency within each individual subject in the time dimension, compromising the overall quality. To solve this problem, our paper proposed a two-stage cascaded diffusion model, Cas-DiffCom, for dense and longitudinal 3D infant brain MRI completion and super-resolution. We applied our proposed method to the Baby Connectome Project (BCP) dataset. The experiment results validate that Cas-DiffCom achieves both individual consistency and high fidelity in longitudinal infant brain image completion. We further applied the generated infant brain images to two downstream tasks, brain tissue segmentation and developmental trajectory delineation, to declare its task-oriented potential in the neuroscience field.

eess.IV↗

arXiv2024

Muon mass correction in partial wave analyses of charmed meson semi-leptonic decays

We derive the parameterization formula for partial wave analyses of charmed meson semi-leptonic decays with consideration of the effects caused by the lepton mass. As the proposed super-tau-charm factory will reach much enhanced luminosity and BESIII is taking $ψ(3770)\to D\bar{D}$ data, our results are helpful to improve the measurement precision of future partial wave analyses of charmed meson semi-muonic decays.

hep-ph↗

arXiv2024

Federated Learning with Dual Attention for Robust Modulation Classification under Attacks

Federated learning (FL) allows distributed participants to train machine learning models in a decentralized manner. It can be used for radio signal classification with multiple receivers due to its benefits in terms of privacy and scalability. However, the existing FL algorithms usually suffer from slow and unstable convergence and are vulnerable to poisoning attacks from malicious participants. In this work, we aim to design a versatile FL framework that simultaneously promotes the performance of the model both in a secure system and under attack. To this end, we leverage attention mechanisms as a defense against attacks in FL and propose a robust FL algorithm by integrating the attention mechanisms into the global model aggregation step. To be more specific, two attention models are combined to calculate the amount of attention cast on each participant. It will then be used to determine the weights of local models during the global aggregation. The proposed algorithm is verified on a real-world dataset and it outperforms existing algorithms, both in secure systems and in systems under data poisoning attacks.

eess.SP↗

arXiv2024

The Theoretical Limit of Radar Target Detection

In this paper, we solve the optimal target detection problem employing the thoughts and methodologies of Shannon's information theory. Introducing a target state variable into a general radar system model, an equivalent detection channel is derived, and the a posteriori probability distribution is given accordingly. Detection information (DI) is proposed for measuring system performance, which holds for any specific detection method. Moreover, we provide an analytic expression for the false alarm probability concerning the a priori probability. In particular, for a sufficiently large observation interval, the false alarm probability equals the a priori probability of the existing state. A stochastic detection method, the sampling a posteriori probability, is also proposed. The target detection theorem is proved mathematically, which indicates that DI is an achievable theoretical limit of target detection. Specifically, when empirical DI is gained from the sampling a posteriori detection method approaches the DI, the probability of failed decisions tends to be zero. Conversely, there is no detector whose empirical DI is more than DI. Numerical simulations are performed to verify the correctness of the theorems. The results demonstrate that the maximum a posteriori and the Neyman-Pearson detection methods are upper bounded by the theoretical limit.

cs.IT↗

arXiv2024

Fundamental Limitation of Semantic Communications: Neural Estimation for Rate-Distortion

This paper studies the fundamental limit of semantic communications over the discrete memoryless channel. We consider the scenario to send a semantic source consisting of an observation state and its corresponding semantic state, both of which are recovered at the receiver. To derive the performance limitation, we adopt the semantic rate-distortion function (SRDF) to study the relationship among the minimum compression rate, observation distortion, semantic distortion, and channel capacity. For the case with unknown semantic source distribution, while only a set of the source samples is available, we propose a neural-network-based method by leveraging the generative networks to learn the semantic source distribution. Furthermore, for a special case where the semantic state is a deterministic function of the observation, we design a cascade neural network to estimate the SRDF. For the case with perfectly known semantic source distribution, we propose a general Blahut-Arimoto algorithm to effectively compute the SRDF. Finally, experimental results validate our proposed algorithms for the scenarios with ideal Gaussian semantic source and some practical datasets.

cs.IT↗

arXiv2023

Uncertainty-Penalized Reinforcement Learning from Human Feedback with Diverse Reward LoRA Ensembles

Reinforcement learning from human feedback (RLHF) emerges as a promising paradigm for aligning large language models (LLMs). However, a notable challenge in RLHF is overoptimization, where beyond a certain threshold, the pursuit of higher rewards leads to a decline in human preferences. In this paper, we observe the weakness of KL regularization which is commonly employed in existing RLHF methods to address overoptimization. To mitigate this limitation, we scrutinize the RLHF objective in the offline dataset and propose uncertainty-penalized RLHF (UP-RLHF), which incorporates uncertainty regularization during RL-finetuning. To enhance the uncertainty quantification abilities for reward models, we first propose a diverse low-rank adaptation (LoRA) ensemble by maximizing the nuclear norm of LoRA matrix concatenations. Then we optimize policy models utilizing penalized rewards, determined by both rewards and uncertainties provided by the diverse reward LoRA ensembles. Our experimental results, based on two real human preference datasets, showcase the effectiveness of diverse reward LoRA ensembles in quantifying reward uncertainty. Additionally, uncertainty regularization in UP-RLHF proves to be pivotal in mitigating overoptimization, thereby contributing to the overall performance.

cs.LG↗

arXiv2023

Errors Dynamics in Affine Group Systems

Errors dynamics captures the evolution of the state errors between two distinct trajectories, that are governed by the same system rule but initiated or perturbed differently. In particular, state observer error dynamics analysis in matrix Lie group is fundamental in practice. In this paper, we focus on the error dynamics analysis for an affine group system under external disturbances or random noises. To this end, we first discuss the connections between the notions of affine group systems and linear group systems. We provide two equivalent characterizations of a linear group system. Such characterizations are based on the homeomorphism of its transition flow and linearity of its Lie algebra counterpart, respectively. Next, we investigate the evolution of a linear group system and we assume it is diffused by a Brownian motion in tangent spaces. We further show that the dynamics projected in the Lie algebra is governed by a stochastic differential equation with a linear drift term. We apply these findings in analyzing the error dynamics. Under differentiable disturbance, we derive an ordinary differential equation characterizing the evolution of the projected errors in the Lie algebra. In addition, the counterpart with stochastic disturbances is derived for the projected errors in terms of a stochastic differential equation. Explicit and accurate derivation of error dynamics is provided for matrix group $SE_N(3)$, which plays a vital role especially in robotic applications.

eess.SY↗

arXiv2023

9DTact: A Compact Vision-Based Tactile Sensor for Accurate 3D Shape Reconstruction and Generalizable 6D Force Estimation

The advancements in vision-based tactile sensors have boosted the aptitude of robots to perform contact-rich manipulation, particularly when precise positioning and contact state of the manipulated objects are crucial for successful execution. In this work, we present 9DTact, a straightforward yet versatile tactile sensor that offers 3D shape reconstruction and 6D force estimation capabilities. Conceptually, 9DTact is designed to be highly compact, robust, and adaptable to various robotic platforms. Moreover, it is low-cost and easy-to-fabricate, requiring minimal assembly skills. Functionally, 9DTact builds upon the optical principles of DTact and is optimized to achieve 3D shape reconstruction with enhanced accuracy and efficiency. Remarkably, we leverage the optical and deformable properties of the translucent gel so that 9DTact can perform 6D force estimation without the participation of auxiliary markers or patterns on the gel surface. More specifically, we collect a dataset consisting of approximately 100,000 image-force pairs from 175 complex objects and train a neural network to regress the 6D force, which can generalize to unseen objects. To promote the development and applications of vision-based tactile sensors, we open-source both the hardware and software of 9DTact, along with a comprehensive video tutorial, all of which are available at https://linchangyi1.github.io/9DTact.

cs.RO↗

arXiv2023

VideoLCM: Video Latent Consistency Model

Consistency models have demonstrated powerful capability in efficient image generation and allowed synthesis within a few sampling steps, alleviating the high computational cost in diffusion models. However, the consistency model in the more challenging and resource-consuming video generation is still less explored. In this report, we present the VideoLCM framework to fill this gap, which leverages the concept of consistency models from image generation to efficiently synthesize videos with minimal steps while maintaining high quality. VideoLCM builds upon existing latent video diffusion models and incorporates consistency distillation techniques for training the latent consistency model. Experimental results reveal the effectiveness of our VideoLCM in terms of computational efficiency, fidelity and temporal consistency. Notably, VideoLCM achieves high-fidelity and smooth video synthesis with only four sampling steps, showcasing the potential for real-time synthesis. We hope that VideoLCM can serve as a simple yet effective baseline for subsequent research. The source code and models will be publicly available.

cs.CV↗

arXiv2023

An Incentive Mechanism for Federated Learning Based on Multiple Resource Exchange

Federated Learning (FL) is a distributed machine learning paradigm that addresses privacy concerns in machine learning and still guarantees high test accuracy. However, achieving the necessary accuracy by having all clients participate in FL is impractical, given the constraints of client local computing resource. In this paper, we introduce a multi-user collaborative computing framework, categorizing users into two roles: model owners (MOs) and data owner (DOs). Without resorting to monetary incentives, an MO can encourage more DOs to join in FL by allowing the DOs to offload extra local computing tasks to the MO for execution. This exchange of "data" for "computing resources" streamlines the incentives for clients to engage more effectively in FL. We formulate the interaction between MO and DOs as an optimization problem, and the objective is to effectively utilize the communication and computing resource of the MO and DOs to minimize the time to complete an FL task. The proposed problem is a mixed integer nonlinear programming (MINLP) with high computational complexity. We first decompose it into two distinct subproblems, namely the client selection problem and the resource allocation problem to segregate the integer variables from the continuous variables. Then, an effective iterative algorithm is proposed to solve problem. Simulation results demonstrate that the proposed collaborative computing framework can achieve an accuracy of more than 95\% while minimizing the overall time to complete an FL task.

cs.LG↗

arXiv2023

CCM: Adding Conditional Controls to Text-to-Image Consistency Models

Consistency Models (CMs) have showed a promise in creating visual content efficiently and with high quality. However, the way to add new conditional controls to the pretrained CMs has not been explored. In this technical report, we consider alternative strategies for adding ControlNet-like conditional control to CMs and present three significant findings. 1) ControlNet trained for diffusion models (DMs) can be directly applied to CMs for high-level semantic controls but struggles with low-level detail and realism control. 2) CMs serve as an independent class of generative models, based on which ControlNet can be trained from scratch using Consistency Training proposed by Song et al. 3) A lightweight adapter can be jointly optimized under multiple conditions through Consistency Training, allowing for the swift transfer of DMs-based ControlNet to CMs. We study these three solutions across various conditional controls, including edge, depth, human pose, low-resolution image and masked image with text-to-image latent consistency models.

cs.CV↗

arXiv2023

Investigating $Z_{cs}(3985)$ and $Z_{cs}(4000)$ exotic states in $Λ_b\to Z^-_{cs}p$ decays

We study the $Z_{cs}(3985)$ and $Z_{cs}(4000)$ exotic states in the decays of $Λ_b$ baryons through a molecular scenario. In the final state interaction, the $Λ_b\to Λ_c^+ D_s^{(*)-}$ decays are followed by the $Λ_c^+ D_s^{(*)-}$ to $Z^-_{cs}p$ rescatterings via exchange of a $D^{(*)}$ meson. We predict a branching fraction of $(3.1^{+1.4}_{-2.6})\times 10^{-4}$ for $Λ_b\to Z^-_{cs}p$, which can be measured in the $Λ_b\to J/ψK^{(*)-}p$ decay. This study proposes a new approach to test the molecular model, and guides future experimental searches for the $Z_{cs}(3985)$ and $Z_{cs}(4000)$.

hep-ph↗