arXiv subjects

Wei Fang

Publications and source records attributed to Wei Fang.

At least 37 records · Page 2Linked to original sources

arXiv2025

Multiplication-Free Parallelizable Spiking Neurons with Efficient Spatio-Temporal Dynamics

Spiking Neural Networks (SNNs) are distinguished from Artificial Neural Networks (ANNs) for their complex neuronal dynamics and sparse binary activations (spikes) inspired by the biological neural system. Traditional neuron models use iterative step-by-step dynamics, resulting in serial computation and slow training speed of SNNs. Recently, parallelizable spiking neuron models have been proposed to fully utilize the massive parallel computing ability of graphics processing units to accelerate the training of SNNs. However, existing parallelizable spiking neuron models involve dense floating operations and can only achieve high long-term dependencies learning ability with a large order at the cost of huge computational and memory costs. To solve the dilemma of performance and costs, we propose the mul-free channel-wise Parallel Spiking Neuron, which is hardware-friendly and suitable for SNNs' resource-restricted application scenarios. The proposed neuron imports the channel-wise convolution to enhance the learning ability, induces the sawtooth dilations to reduce the neuron order, and employs the bit-shift operation to avoid multiplications. The algorithm for the design and implementation of acceleration methods is discussed extensively. Our methods are validated in neuromorphic Spiking Heidelberg Digits voices, sequential CIFAR images, and neuromorphic DVS-Lip vision datasets, achieving superior performance over SOTA spiking neurons. Training speed results demonstrate the effectiveness of our acceleration methods, providing a practical reference for future research. Our code is available at \href{https://github.com/PengXue0812/Multiplication-Free-Parallelizable-Spiking-Neurons-with-Efficient-Spatio-Temporal-Dynamics}{Github}.

cs.NE↗

arXiv2025

Instanton Theory for Nonadiabatic Tunneling through Near-Barrier Crossings

Many reactions in chemistry and biology involve multiple electronic states, rendering them nonadiabatic in nature. These reactions can be formally described using Fermi's golden rule (FGR) in the weak-coupling limit. Nonadiabatic instanton theory presents a semiclassical approximation to FGR, which is directly applicable to molecular systems. However, there are cases where the theory has not yet been formulated. For instance, in many real-world reactions including spin-crossover or proton-coupled electron transfer, the crossing occurs near a barrier on a diabatic state. This scenario gives rise to competing nonadiabatic reaction pathways, some of which involve tunneling through a diabatic barrier while simultaneously switching electronic states. To date, no rate theory is available for describing tunneling via these unconventional pathways. Here we extend instanton theory to model this class of processes, which we term the ``non-convex'' regime. Benchmark tests on model systems show that the rates predicted by instanton theory are in excellent agreement with quantum-mechanical FGR calculations. Furthermore, the method offers new insights into multi-step tunneling reactions and the competition between sequential and concerted nonadiabatic tunneling pathways.

physics.chem-ph↗

arXiv2025

Anatomy-Aware Low-Dose CT Denoising via Pretrained Vision Models and Semantic-Guided Contrastive Learning

To reduce radiation exposure and improve the diagnostic efficacy of low-dose computed tomography (LDCT), numerous deep learning-based denoising methods have been developed to mitigate noise and artifacts. However, most of these approaches ignore the anatomical semantics of human tissues, which may potentially result in suboptimal denoising outcomes. To address this problem, we propose ALDEN, an anatomy-aware LDCT denoising method that integrates semantic features of pretrained vision models (PVMs) with adversarial and contrastive learning. Specifically, we introduce an anatomy-aware discriminator that dynamically fuses hierarchical semantic features from reference normal-dose CT (NDCT) via cross-attention mechanisms, enabling tissue-specific realism evaluation in the discriminator. In addition, we propose a semantic-guided contrastive learning module that enforces anatomical consistency by contrasting PVM-derived features from LDCT, denoised CT and NDCT, preserving tissue-specific patterns through positive pairs and suppressing artifacts via dual negative pairs. Extensive experiments conducted on two LDCT denoising datasets reveal that ALDEN achieves the state-of-the-art performance, offering superior anatomy preservation and substantially reducing over-smoothing issue of previous work. Further validation on a downstream multi-organ segmentation task (encompassing 117 anatomical structures) affirms the model's ability to maintain anatomical awareness.

eess.IV↗

arXiv2025

Differential Coding for Training-Free ANN-to-SNN Conversion

Spiking Neural Networks (SNNs) exhibit significant potential due to their low energy consumption. Converting Artificial Neural Networks (ANNs) to SNNs is an efficient way to achieve high-performance SNNs. However, many conversion methods are based on rate coding, which requires numerous spikes and longer time-steps compared to directly trained SNNs, leading to increased energy consumption and latency. This article introduces differential coding for ANN-to-SNN conversion, a novel coding scheme that reduces spike counts and energy consumption by transmitting changes in rate information rather than rates directly, and explores its application across various layers. Additionally, the threshold iteration method is proposed to optimize thresholds based on activation distribution when converting Rectified Linear Units (ReLUs) to spiking neurons. Experimental results on various Convolutional Neural Networks (CNNs) and Transformers demonstrate that the proposed differential coding significantly improves accuracy while reducing energy consumption, particularly when combined with the threshold iteration method, achieving state-of-the-art performance. The source codes of the proposed method are available at https://github.com/h-z-h-cell/ANN-to-SNN-DCGS.

cs.CV↗

arXiv2025

PLAY2PROMPT: Zero-shot Tool Instruction Optimization for LLM Agents via Tool Play

Large language models (LLMs) are increasingly integrated with specialized external tools, yet many tasks demand zero-shot tool usage with minimal or noisy documentation. Existing solutions rely on manual rewriting or labeled data for validation, making them inapplicable in true zero-shot settings. To address these challenges, we propose PLAY2PROMPT, an automated framework that systematically "plays" with each tool to explore its input-output behaviors. Through this iterative trial-and-error process, PLAY2PROMPT refines tool documentation and generates usage examples without any labeled data. These examples not only guide LLM inference but also serve as validation to further enhance tool utilization. Extensive experiments on real-world tasks demonstrate that PLAY2PROMPT significantly improves zero-shot tool performance across both open and closed models, offering a scalable and effective solution for domain-specific tool integration.

cs.CL↗

arXiv2025

Dynamical analysis of the H^2 + H^-2 Dark Energy model considering viscosity and interaction

In this study, we further developed and investigated the dual parameter phenomenological dark energy model (H^2 + H^-2 dark energy model) derived from Kaniadakis holographic dark energy. On the theoretical basis of the original H^2 + H^-2 dark energy model (HHDE), four types of viscosities and seven types of interactions were introduced. These were combined pairwise, and a dynamical analysis was conducted on a total of 35 Modified H^2 + H^-2 Viscous Interacting Dark Energy (MHH-VIDE) models. The advantage of the HHDE model and MHH-VIDE models is that these models can greatly relieve the Hubble tension and cicumventing the potential issue of a 'big rip', and the dark energy is Quintom-like. In this article, we performed a three-dimensional dynamical analysis of the aforementioned models with interactions and viscosity, testing their viability. The results suggest that the nature of this dark energy is closer to a property of spacetime than a cosmological component. The phase diagram analysis reveals a modified radiation-dominated epoch, a transitional matter-dominated phase, and a late-time attractor corresponding to the dark-energy-driven acceleration phase.

astro-ph.CO↗

arXiv2025

Mamba-3D as Masked Autoencoders for Accurate and Data-Efficient Analysis of Medical Ultrasound Videos

Ultrasound videos are an important form of clinical imaging data, and deep learning-based automated analysis can improve diagnostic accuracy and clinical efficiency. However, the scarcity of labeled data and the inherent challenges of video analysis have impeded the advancement of related methods. In this work, we introduce E-ViM$^3$, a data-efficient Vision Mamba network that preserves the 3D structure of video data, enhancing long-range dependencies and inductive biases to better model space-time correlations. With our design of Enclosure Global Tokens (EGT), the model captures and aggregates global features more effectively than competing methods. To further improve data efficiency, we employ masked video modeling for self-supervised pre-training, with the proposed Spatial-Temporal Chained (STC) masking strategy designed to adapt to various video scenarios. Experiments demonstrate that E-ViM$^3$ performs as the state-of-the-art in two high-level semantic analysis tasks across four datasets of varying sizes: EchoNet-Dynamic, CAMUS, MICCAI-BUV, and WHBUS. Furthermore, our model achieves competitive performance with limited labels, highlighting its potential impact on real-world clinical applications.

cs.CV↗

arXiv2025

MaRS: A Fast Sampler for Mean Reverting Diffusion based on ODE and SDE Solvers

In applications of diffusion models, controllable generation is of practical significance, but is also challenging. Current methods for controllable generation primarily focus on modifying the score function of diffusion models, while Mean Reverting (MR) Diffusion directly modifies the structure of the stochastic differential equation (SDE), making the incorporation of image conditions simpler and more natural. However, current training-free fast samplers are not directly applicable to MR Diffusion. And thus MR Diffusion requires hundreds of NFEs (number of function evaluations) to obtain high-quality samples. In this paper, we propose a new algorithm named MaRS (MR Sampler) to reduce the sampling NFEs of MR Diffusion. We solve the reverse-time SDE and the probability flow ordinary differential equation (PF-ODE) associated with MR Diffusion, and derive semi-analytical solutions. The solutions consist of an analytical function and an integral parameterized by a neural network. Based on this solution, we can generate high-quality samples in fewer steps. Our approach does not require training and supports all mainstream parameterizations, including noise prediction, data prediction and velocity prediction. Extensive experiments demonstrate that MR Sampler maintains high sampling quality with a speedup of 10 to 20 times across ten different image restoration tasks. Our algorithm accelerates the sampling procedure of MR Diffusion, making it more practical in controllable generation.

cs.CV↗

arXiv2024

Polarization-entangled photon pairs generation from a single lithium niobate waveguide with single poling period

Polarization-entangled photon pairs are essential sources for photonic quantum information processing. However, generating entangled photon pairs with large detuning via spontaneous parametric down-conversion (SPDC) often requires complex configurations to compensate for phase matching. Here, we propose a simple and efficient scheme to generate polarization-entangled photon pairs based on type-0 SPDC in a thin-film lithium niobate waveguide with a single poling period. By utilizing the strong dispersion engineering capabilities of thin-film waveguides, we can achieve both degenerate and highly detuned entangled photon pairs. Furthermore, we demonstrate on-chip temporal compensation using an integrated waveguide structure. Our approach offers a compact and scalable solution for integrated quantum photonic circuits.

physics.optics↗

arXiv2024

Thermodynamics of the $H^2 + H^{-2}$ Dark Energy model

In this study, we introduced a phenomenological dark energy model $H^{2}+H^{-2}$ model) that incorporates the first-order approximation of Kaniadakis holographic entropy dark energy and utilizes the Hubble horizon, $1/H$ as the infrared cutoff. The advantage of this model is that it can relieve the Hubble tension issue and cicumventing the potential issue of a "big rip". In this article, we will study the thermodynamics of the model and obtain the corrected temperature. In addition, we found that the model modified the entropy area relationship by adding an area cubic term in addition to the area term.

gr-qc↗

arXiv2024

All-optical ultrafast arbitrary rotation of hole orbital qubits with direct phase control

Complete quantum control of a stationary quantum bit embedded in a quantum emitter is crucial for photonic quantum information technologies. Recently, the orbital degree of freedom in optically active quantum dots has emerged as a promising candidate. However, the essential ability to perform arbitrary rotations on orbital qubits remains elusive. Here, we demonstrate arbitrary rotation of a hole orbital qubit with direct phase control using picosecond optical pulses. This is achieved by successfully inducing stimulated Raman transitions within $Λ$ systems coupled via radiative Auger processes. The new capability enables direct control of polar and azimuth angles of the Bloch vector without requiring timed precession. Our results establish orbital states in solid-state quantum emitters as a viable resource for applications in high-speed quantum information processing.

quant-ph↗

arXiv2024

Acceleration of the Universe without the Hubble tension with Kaniadakis holographic dark energy using the Hubble horizon as the IR cut-off

We introduce a holographic dark energy model that incorporates the first-order approximate Kaniadaski entropy, utilizing the Hubble horizon, $1/H$, as the infrared cutoff. We investigate the cosmological evolution within this framework. The model introduces an extra parameter relative to the $Λ$CDM model. It posits a Universe that is initially dominated by dark matter, which then evolves to a phase where dark energy becomes the predominant component, with this transition occurring at a redshift of approximately $z \sim 0.419$. The energy density of dark energy is ultimately expected to become constant, thereby circumventing the potential issue of a "big rip". Employing the most recent Type Ia supernova and Hubble parameter data, we constrain the model's parameters and find a Hubble constant of $H_0=72.8$ km/s/Mpc, thereby resolving the Hubble tension issue. The estimated age of the Universe, based on the best-fit parameter values, is $14.2$ Gyr. Furthermore, we predict the number of strong gravitational lenses and conduct statefinder and $Om$ diagnostic analyses to validate and characterize the model.

astro-ph.CO↗

arXiv2024

StyleSeg V2: Towards Robust One-shot Segmentation of Brain Tissue via Optimization-free Registration Error Perception

One-shot segmentation of brain tissue requires training registration-segmentation (reg-seg) dual-model iteratively, where reg-model aims to provide pseudo masks of unlabeled images for seg-model by warping a carefully-labeled atlas. However, the imperfect reg-model induces image-mask misalignment, poisoning the seg-model subsequently. Recent StyleSeg bypasses this bottleneck by replacing the unlabeled images with their warped copies of atlas, but needs to borrow the diverse image patterns via style transformation. Here, we present StyleSeg V2, inherited from StyleSeg but granted the ability of perceiving the registration errors. The motivation is that good registration behaves in a mirrored fashion for mirrored images. Therefore, almost at no cost, StyleSeg V2 can have reg-model itself "speak out" incorrectly-aligned regions by simply mirroring (symmetrically flipping the brain) its input, and the registration errors are symmetric inconsistencies between the outputs of original and mirrored inputs. Consequently, StyleSeg V2 allows the seg-model to make use of correctly-aligned regions of unlabeled images and also enhances the fidelity of style-transformed warped atlas image by weighting the local transformation strength according to registration errors. The experimental results on three public datasets demonstrate that our proposed StyleSeg V2 outperforms other state-of-the-arts by considerable margins, and exceeds StyleSeg by increasing the average Dice by at least 2.4%.

cs.CV↗

arXiv2024

Wavelength-tunable high-fidelity entangled photon sources enabled by dual Stark effects

The construction of a large-scale quantum internet requires quantum repeaters containing multiple entangled photon sources with identical wavelengths. Semiconductor quantum dots can generate entangled photon pairs deterministically with high fidelity. However, realizing wavelength-matched quantum-dot entangled photon sources faces two difficulties: the non-uniformity of emission wavelength and exciton fine-structure splitting induced fidelity reduction. Typically, these two factors are not independently tunable, making it challenging to achieve simultaneous improvement. In this work, we demonstrate wavelength-tunable entangled photon sources based on droplet-etched GaAs quantum dots through the combined use of AC and quantum-confined Stark effects. The emission wavelength can be tuned by ~1 meV while preserving an entanglement fidelity f exceeding 0.955(1) in the entire tuning range. Based on this hybrid tuning scheme, we finally demonstrate multiple wavelength-matched entangled photon sources with f>0.919(3), paving a way towards robust and scalable on-demand entangled photon sources for quantum internet and integrated quantum optical circuits.

quant-ph↗

arXiv2024

CycleINR: Cycle Implicit Neural Representation for Arbitrary-Scale Volumetric Super-Resolution of Medical Data

In the realm of medical 3D data, such as CT and MRI images, prevalent anisotropic resolution is characterized by high intra-slice but diminished inter-slice resolution. The lowered resolution between adjacent slices poses challenges, hindering optimal viewing experiences and impeding the development of robust downstream analysis algorithms. Various volumetric super-resolution algorithms aim to surmount these challenges, enhancing inter-slice resolution and overall 3D medical imaging quality. However, existing approaches confront inherent challenges: 1) often tailored to specific upsampling factors, lacking flexibility for diverse clinical scenarios; 2) newly generated slices frequently suffer from over-smoothing, degrading fine details, and leading to inter-slice inconsistency. In response, this study presents CycleINR, a novel enhanced Implicit Neural Representation model for 3D medical data volumetric super-resolution. Leveraging the continuity of the learned implicit function, the CycleINR model can achieve results with arbitrary up-sampling rates, eliminating the need for separate training. Additionally, we enhance the grid sampling in CycleINR with a local attention mechanism and mitigate over-smoothing by integrating cycle-consistent loss. We introduce a new metric, Slice-wise Noise Level Inconsistency (SNLI), to quantitatively assess inter-slice noise level inconsistency. The effectiveness of our approach is demonstrated through image quality evaluations on an in-house dataset and a downstream task analysis on the Medical Segmentation Decathlon liver tumor dataset.

eess.IV↗

arXiv2024

Incorporating Graph Attention Mechanism into Geometric Problem Solving Based on Deep Reinforcement Learning

In the context of online education, designing an automatic solver for geometric problems has been considered a crucial step towards general math Artificial Intelligence (AI), empowered by natural language understanding and traditional logical inference. In most instances, problems are addressed by adding auxiliary components such as lines or points. However, adding auxiliary components automatically is challenging due to the complexity in selecting suitable auxiliary components especially when pivotal decisions have to be made. The state-of-the-art performance has been achieved by exhausting all possible strategies from the category library to identify the one with the maximum likelihood. However, an extensive strategy search have to be applied to trade accuracy for ef-ficiency. To add auxiliary components automatically and efficiently, we present deep reinforcement learning framework based on the language model, such as BERT. We firstly apply the graph attention mechanism to reduce the strategy searching space, called AttnStrategy, which only focus on the conclusion-related components. Meanwhile, a novel algorithm, named Automatically Adding Auxiliary Components using Reinforcement Learning framework (A3C-RL), is proposed by forcing an agent to select top strategies, which incorporates the AttnStrategy and BERT as the memory components. Results from extensive experiments show that the proposed A3C-RL algorithm can substantially enhance the average precision by 32.7% compared to the traditional MCTS. In addition, the A3C-RL algorithm outperforms humans on the geometric questions from the annual University Entrance Mathematical Examination of China.

cs.CY↗

arXiv2024

Research progress on intelligent optimization techniques for energy-efficient design of ship hull forms

The design optimization of ship hull form based on hydrodynamics theory and simulation-based design (SBD) technologies generally considers ship performance and energy efficiency performance as the design objective, which plays an important role in smart design and manufacturing of green ship. An optimal design of sustainable energy system requires multidisciplinary tools to build ships with the least resistance and energy consumption. Through a systematic approach, this paper presents the research progress of energy-efficient design of ship hull forms based on intelligent optimization techniques. We discuss different methods involved in the optimization procedure, especially the latest developments of intelligent optimization algorithms and surrogate models. Moreover, current development trends and technical challenges of multidisciplinary design optimization and surrogate-assisted evolutionary algorithms for ship design are further analyzed. We explore the gaps and potential future directions, so as to paving the way towards the design of the next generation of more energy-efficient ship hull form.

cs.CE↗

arXiv2024

Optimal ANN-SNN Conversion with Group Neurons

Spiking Neural Networks (SNNs) have emerged as a promising third generation of neural networks, offering unique characteristics such as binary outputs, high sparsity, and biological plausibility. However, the lack of effective learning algorithms remains a challenge for SNNs. For instance, while converting artificial neural networks (ANNs) to SNNs circumvents the need for direct training of SNNs, it encounters issues related to conversion errors and high inference time delays. In order to reduce or even eliminate conversion errors while decreasing inference time-steps, we have introduced a novel type of neuron called Group Neurons (GNs). One GN is composed of multiple Integrate-and-Fire (IF) neurons as members, and its neural dynamics are meticulously designed. Based on GNs, we have optimized the traditional ANN-SNN conversion framework. Specifically, we replace the IF neurons in the SNNs obtained by the traditional conversion framework with GNs. The resulting SNNs, which utilize GNs, are capable of achieving accuracy levels comparable to ANNs even within extremely short inference time-steps. The experiments on CIFAR10, CIFAR100, and ImageNet datasets demonstrate the superiority of the proposed methods in terms of both inference accuracy and latency. Code is available at https://github.com/Lyu6PosHao/ANN2SNN_GN.

cs.NE↗