Search

Significant achievements in personalization of diffusion models have been witnessed. Conventional tuning-free methods mostly encode multiple reference images by averaging their image embeddings as the injection condition, but such an image-independent operation cannot perform interaction among images to capture consistent visual elements within multiple references. Although the tuning-based Low-Rank Adaptation (LoRA) can effectively extract consistent elements within multiple images through the training process, it necessitates specific finetuning for each distinct image group. This paper introduces EasyRef, a novel plug-and-play adaptation method that enables diffusion models to be conditioned on multiple reference images and the text prompt. To effectively exploit consistent visual elements within multiple images, we leverage the multi-image comprehension and instruction-following capabilities of the multimodal large language model (MLLM), prompting it to capture consistent visual elements based on the instruction. Besides, injecting the MLLM's representations into the diffusion process through adapters can easily generalize to unseen domains, mining the consistent visual elements within unseen data. To mitigate computational costs and enhance fine-grained detail preservation, we introduce an efficient reference aggregation strategy and a progressive training scheme. Finally, we introduce MRBench, a new multi-reference image generation benchmark. Experimental results demonstrate EasyRef surpasses both tuning-free methods like IP-Adapter and tuning-based methods like LoRA, achieving superior aesthetic quality and robust zero-shot generalization across diverse domains., Comment: Tech report

We investigate the absorption and transmission properties of a weak probe field in an atom opto-magnomechanics system. The system comprises an assembly of two-level atoms and a magnon mode within a ferrimagnetic crystal, which directly interacts with an optical cavity mode through the crystal's deformation displacement. We observe optomechanically induced transparency (OMIT) via radiation pressure and a magnomechanically induced transparency (MMIT) due to the nonlinear magnon-phonon interaction. In addition, due to the coupling of the atom to the detected and signal light, the system's width transparency window is divided into two narrow windows. Additionally, we demonstrate that the group delay is contingent upon the tunability of the magnon-phonon coupling strength. Our solution possesses significant in the field of quantum precision measurement.

Significant advances have been made in the sampling efficiency of diffusion models and flow matching models, driven by Consistency Distillation (CD), which trains a student model to mimic the output of a teacher model at a later timestep. However, we found that the learning complexity of the student model varies significantly across different timesteps, leading to suboptimal performance in CD.To address this issue, we propose the Curriculum Consistency Model (CCM), which stabilizes and balances the learning complexity across timesteps. Specifically, we regard the distillation process at each timestep as a curriculum and introduce a metric based on Peak Signal-to-Noise Ratio (PSNR) to quantify the learning complexity of this curriculum, then ensure that the curriculum maintains consistent learning complexity across different timesteps by having the teacher model iterate more steps when the noise intensity is low. Our method achieves competitive single-step sampling Fr\'echet Inception Distance (FID) scores of 1.64 on CIFAR-10 and 2.18 on ImageNet 64x64.Moreover, we have extended our method to large-scale text-to-image models and confirmed that it generalizes well to both diffusion models (Stable Diffusion XL) and flow matching models (Stable Diffusion 3). The generated samples demonstrate improved image-text alignment and semantic structure, since CCM enlarges the distillation step at large timesteps and reduces the accumulated error.

The rising demand for high-performance computing (HPC) has made full-chip dynamic thermal simulation in many-core GPUs critical for optimizing performance and extending device lifespans. Proper orthogonal decomposition (POD) with Galerkin projection (GP) has shown to offer high accuracy and massive runtime improvements over direct numerical simulation (DNS). However, previous implementations of POD-GP use MPI-based libraries like PETSc and FEniCS and face significant runtime bottlenecks. We propose a $\textbf{Py}$Torch-based $\textbf{POD-GP}$ library (PyPOD-GP), a GPU-optimized library for chip-level thermal simulation. PyPOD-GP achieves over $23.4\times$ speedup in training and over $10\times$ speedup in inference on a GPU with over 13,000 cores, with just $1.2\%$ error over the device layer., Comment: 8 pages, 3 figures

While recent works on blind face image restoration have successfully produced impressive high-quality (HQ) images with abundant details from low-quality (LQ) input images, the generated content may not accurately reflect the real appearance of a person. To address this problem, incorporating well-shot personal images as additional reference inputs could be a promising strategy. Inspired by the recent success of the Latent Diffusion Model (LDM), we propose ReF-LDM, an adaptation of LDM designed to generate HQ face images conditioned on one LQ image and multiple HQ reference images. Our model integrates an effective and efficient mechanism, CacheKV, to leverage the reference images during the generation process. Additionally, we design a timestep-scaled identity loss, enabling our LDM-based model to focus on learning the discriminating features of human faces. Lastly, we construct FFHQ-Ref, a dataset consisting of 20,405 high-quality (HQ) face images with corresponding reference images, which can serve as both training and evaluation data for reference-based face restoration models., Comment: NeurIPS 2024, project page https://chiweihsiao.github.io/refldm.github.io/

In this paper, we focus on the gravitational waves emitted by a stellar-mass object in a quasi-circular inspiral orbit around a central supermassive polymerized black hole in loop quantum gravity. Treating the stellar-mass object as a massive test particle, we derive its equations of motion and the corresponding radial effective potential. We find that the peak of the radial effective potential decreases with the quantum parameter $\hat{k}$. We also examine the impact of quantum corrections on the properties of stable circular orbits around the polymerized black hole. Given that gravitational radiation induces changes in the energy and orbital angular momentum of the smaller object, we model its trajectory as an adiabatic evolution along stable circular orbits. The corresponding gravitational waveforms are generated using the numerical kludge method, revealing that quantum corrections cause phase advances in the gravitational waveforms. We further analyze the potential constraints on the quantum parameter $\hat{k}$ from future space-based gravitational wave observations, concluding that these observations will likely impose stronger constraints on $\hat{k}$ than those obtained from black hole shadow measurements., Comment: 13 pages, 9 figures. arXiv admin note: text overlap with arXiv:2407.00283

We present The Matrix, the first foundational realistic world simulator capable of generating continuous 720p high-fidelity real-scene video streams with real-time, responsive control in both first- and third-person perspectives, enabling immersive exploration of richly dynamic environments. Trained on limited supervised data from AAA games like Forza Horizon 5 and Cyberpunk 2077, complemented by large-scale unsupervised footage from real-world settings like Tokyo streets, The Matrix allows users to traverse diverse terrains -- deserts, grasslands, water bodies, and urban landscapes -- in continuous, uncut hour-long sequences. Operating at 16 FPS, the system supports real-time interactivity and demonstrates zero-shot generalization, translating virtual game environments to real-world contexts where collecting continuous movement data is often infeasible. For example, The Matrix can simulate a BMW X3 driving through an office setting--an environment present in neither gaming data nor real-world sources. This approach showcases the potential of AAA game data to advance robust world models, bridging the gap between simulations and real-world applications in scenarios with limited data.

Generative models, particularly diffusion models, have achieved remarkable success in density estimation for multimodal data, drawing significant interest from the reinforcement learning (RL) community, especially in policy modeling in continuous action spaces. However, existing works exhibit significant variations in training schemes and RL optimization objectives, and some methods are only applicable to diffusion models. In this study, we compare and analyze various generative policy training and deployment techniques, identifying and validating effective designs for generative policy algorithms. Specifically, we revisit existing training objectives and classify them into two categories, each linked to a simpler approach. The first approach, Generative Model Policy Optimization (GMPO), employs a native advantage-weighted regression formulation as the training objective, which is significantly simpler than previous methods. The second approach, Generative Model Policy Gradient (GMPG), offers a numerically stable implementation of the native policy gradient method. We introduce a standardized experimental framework named GenerativeRL. Our experiments demonstrate that the proposed methods achieve state-of-the-art performance on various offline-RL datasets, offering a unified and practical guideline for training and deploying generative policies.

Recent generative models based on score matching and flow matching have significantly advanced generation tasks, but their potential in discriminative tasks remains underexplored. Previous approaches, such as generative classifiers, have not fully leveraged the capabilities of these models for discriminative tasks due to their intricate designs. We propose Pretrained Reversible Generation (PRG), which extracts unsupervised representations by reversing the generative process of a pretrained continuous flow model. PRG effectively reuses unsupervised generative models, leveraging their high capacity to serve as robust and generalizable feature extractors for downstream tasks. Our method consistently outperforms prior approaches across multiple benchmarks, achieving state-of-the-art performance among generative model-based methods, including 78\% top-1 accuracy on ImageNet. Extensive ablation studies further validate the effectiveness of our approach.

This paper introduces a novel framework for categorizing the Lebesgue integral with variable upper limits, utilizing normed modules over finite-dimensional $k$-algebras $\mathit{\Lambda}$ and the category $\mathscr{A}^p$ of $\mathit{\Lambda}$. We redefine the integration process by incorporating integral partial ordered set, which provide a categorification of integral with variable upper limits. Moreover, we provide two applications for this categorification in Chapters 5 and 6., Comment: 32 pages

Surface electromyography (sEMG) recordings can be contaminated by electrocardiogram (ECG) signals when the monitored muscle is closed to the heart. Traditional signal-processing-based approaches, such as high-pass filtering and template subtraction, have been used to remove ECG interference but are often limited in their effectiveness. Recently, neural-network-based methods have shown greater promise for sEMG denoising, but they still struggle to balance both efficiency and effectiveness. In this study, we introduce MSEMG, a novel system that integrates the Mamba State Space Model with a convolutional neural network to serve as a lightweight sEMG denoising model. We evaluated MSEMG using sEMG data from the Non-Invasive Adaptive Prosthetics database and ECG signals from the MIT-BIH Normal Sinus Rhythm Database. The results show that MSEMG outperforms existing methods, generating higher-quality sEMG signals with fewer parameters. The source code for MSEMG is available at https://github.com/tonyliu0910/MSEMG., Comment: This paper is under review of 2025 ICASSP

Understanding coronal structure and dynamics can be facilitated by analyzing green-line emission, which enables the investigation of diverse coronal structures such as coronal loops, streamers, coronal holes, and various eruptions in the solar atmosphere. In this study, we investigated the spatiotemporal behaviors of green-line emissions in both low and high latitudes across nine solar cycles, ranging from cycle 17 to the current cycle 25, using the Modified Homogeneous Data Set (MHDS). We employed methodologies such as cross-correlation, power spectral density (PSD), and wavelet transform techniques for this analysis. We found distinct behaviors in green line energy across various latitudinal distributions in the solar atmosphere. The trends observed at higher latitudes differ from those at lower latitudes. The emission behaviors show a close association with other solar phenomena like solar flares, sunspots, and coronal mass ejections (CMEs) throughout the solar cycles. The observed variations exhibit harmonic periods. The emission activity is significantly higher in the low latitudes, accounting for over 70 percent of the emissions, while the higher latitudes contribute less than 30 percent. The emissions exhibit asymmetric behavior between the northern and southern hemispheres, leading to a 44-year cycle of solar hemispheric dominance shifts. Various factors, such as Alfv\'en waves, solar magnetic fields, sunspots, differential rotation, and reconnection events, influence the observed differences in behavior between lower and higher latitudes, suggesting the existence of potential underlying phenomena contributing to deviations in properties, intensity, temporal dynamics, and spatiotemporal lifetime., Comment: 21 pages, 13 figures, 6 ables, Published in the Astrophysical Journal Supplement Series, 275:3 (21pp), 2024 November

To demonstrate supremacy of quantum computing, increasingly large-scale superconducting quantum computing chips are being designed and fabricated, sparking the demand for electronic design automation in pursuit of better efficiency and effectiveness. However, the complexity of simulating quantum systems poses a significant challenge to computer-aided design of quantum chips. Harnessing the scalability of graph neural networks (GNNs), we here propose a parameter designing algorithm for large-scale superconducting quantum circuits. The algorithm depends on the so-called 'three-stair scaling' mechanism, which comprises two neural-network models: an evaluator supervisedly trained on small-scale circuits for applying to medium-scale circuits, and a designer unsupervisedly trained on medium-scale circuits for applying to large-scale ones. We demonstrate our algorithm in mitigating quantum crosstalk errors, which are commonly present and closely related to the graph structures and parameter assignments of superconducting quantum circuits. Parameters for both single- and two-qubit gates are considered simultaneously. Numerical results indicate that the well-trained designer achieves notable advantages not only in efficiency but also in effectiveness, especially for large-scale circuits. For example, in superconducting quantum circuits consisting of around 870 qubits, the trained designer requires only 27 seconds to complete the frequency designing task which necessitates 90 minutes for the traditional Snake algorithm. More importantly, the crosstalk errors using our algorithm are only 51% of those produced by the Snake algorithm. Overall, this study initially demonstrates the advantages of applying graph neural networks to design parameters in quantum processors, and provides insights for systems where large-scale numerical simulations are challenging in electronic design automation.

Rapid progress in aberration corrected electron microscopy necessitates development of robust methods for the identification of phases, ferroic variants, and other pertinent aspects of materials structure from imaging data. While unsupervised methods for clustering and classification are widely used for these tasks, their performance can be sensitive to hyperparameter selection in the analysis workflow. In this study, we explore the effects of descriptors and hyperparameters on the capability of unsupervised ML methods to distill local structural information, exemplified by discovery of polarization and lattice distortion in Sm doped BiFeO3 (BFO) thin films. We demonstrate that a reward-driven approach can be used to optimize these key hyperparameters across the full workflow, where rewards were designed to reflect domain wall continuity and straightness, ensuring that the analysis aligns with the material's physical behavior. This approach allows us to discover local descriptors that are best aligned with the specific physical behavior, providing insight into the fundamental physics of materials. We further extend the reward driven workflows to disentangle structural factors of variation via optimized variational autoencoder (VAE). Finally, the importance of well-defined rewards was explored as a quantifiable measure of success of the workflow., Comment: 19 pages, 6 figures

We investigate the spin-density wave (SDW) behavior and the potential for superconductivity (SC) in La$_4$Ni$_3$O$_{10}$ under ambient pressure using a multi-orbital random-phase approximation (RPA). Starting with a twelve-orbital tight-binding model derived from density functional theory (DFT) calculations, we explore the influence of Hubbard interactions on SDW formation. Our analysis reveals a stripe-like SDW characterized by an incommensurate wave vector, $Q\approx(\pm 0.7\pi,0)$, suggesting a possible density wave instability in agreement with recent experiments. This configuration is driven by nesting of outer-layer Ni $d_{z^2}$ orbitals and exhibits interlayer antiferromagnetic ordering between the top and bottom NiO layers, with the middle layer serving as a node. We demonstrate that the Hund's coupling $J_H$ is the primary driver of the observed SDW. While superconductivity is absent in the undoped system under ambient pressure, it becomes attainable with appropriate hole doping ($\delta=-0.4$), resulting in a SC gap structure similar to the high-pressure phase. Our study identifies the specific conditions for realizing the ambient pressure stripe density wave: $J_H>0.16U$. Additionally, when doping leads to sufficient nesting at (0,0), the system's magnetic fluctuations transition into a stable Neel-type antiferromagnetic state, analogous to the high-pressure case., Comment: 6 pages, 7 figures

Reconstructing 3D models from single-view images is a long-standing problem in computer vision. The latest advances for single-image 3D reconstruction extract a textual description from the input image and further utilize it to synthesize 3D models. However, existing methods focus on capturing a single key attribute of the image (e.g., object type, artistic style) and fail to consider the multi-perspective information required for accurate 3D reconstruction, such as object shape and material properties. Besides, the reliance on Neural Radiance Fields hinders their ability to reconstruct intricate surfaces and texture details. In this work, we propose MTFusion, which leverages both image data and textual descriptions for high-fidelity 3D reconstruction. Our approach consists of two stages. First, we adopt a novel multi-word textual inversion technique to extract a detailed text description capturing the image's characteristics. Then, we use this description and the image to generate a 3D model with FlexiCubes. Additionally, MTFusion enhances FlexiCubes by employing a special decoder network for Signed Distance Functions, leading to faster training and finer surface representation. Extensive evaluations demonstrate that our MTFusion surpasses existing image-to-3D methods on a wide range of synthetic and real-world images. Furthermore, the ablation study proves the effectiveness of our network designs., Comment: PRCV 2024

Dynamic spectroscopies in Scanning Probe Microscopy (SPM) are critical for probing material properties, such as force interactions, mechanical properties, polarization switching, and electrochemical reactions and ionic dynamics. However, the practical implementation of these measurements is constrained by the need to balance imaging time and data quality. Signal to noise requirements favor long acquisition times and high frequencies to improve signal fidelity. However, these are limited on the low end by contact resonant frequency and photodiode sensitivity, and on the high end by the time needed to acquire high-resolution spectra, or the propensity for samples degradation under high field excitation over long times. The interdependence of key parameters such as instrument settings, acquisition times, and sampling rates makes manual tuning labor-intensive and highly dependent on user expertise, often yielding operator-dependent results. These limitations are prominent in techniques like Dual Amplitude Resonance Tracking (DART) in Piezoresponse Force Microscopy (PFM) that utilize multiple concurrent feedback loops for topography and resonance frequency tracking. Here, a reward-driven workflow is proposed that automates the tuning process, adapting experimental conditions in real time to optimize data quality. This approach significantly reduces the complexity and time required for manual adjustments and can be extended to other SPM spectroscopic methods, enhancing overall efficiency and reproducibility., Comment: 15 pages, 5 figures

Unconventional superconductors that spontaneously break space-group symmetries of their underlying crystal lattice are distinguished by spatial modulations of the superconducting order parameter. These states have recently captured significant attention in various strongly correlated materials, where the breaking of translational or intra-unit-cell symmetries results in the emergence of pair density waves with wavelengths extending across one or multiple unit cells. Here, we employ a spectroscopic-imaging scanning tunneling microscope to identify robust half-unit-cell modulations of the superconducting gap magnitude, coherence strength and subgap states in tunable 1T$^{\prime}$-MoTe$_2$ monolayer. The modulations are oriented perpendicular to the zigzag Mo chains and coexist with three-unit-cell primary pair density wave modulations along the Mo chains, both of which attenuate with increasing temperature and the application of external magnetic fields. Importantly, we find that the superconductivity modulations are strongly linked to unconventional electron pairing mechanisms, which significantly deviate from the Cooper pairing observed in traditional Bardeen-Cooper-Schrieffer superconductors. Our results advance the knowledge of Cooper-pair density modulations and the intricate interplay with other symmetry-breaking states in strongly correlated superconductors., Comment: 31 pages,4 figures

Infrared and visible (IR-VIS) image fusion has gained significant attention for its broad application value. However, existing methods often neglect the complementary role of infrared image in restoring visible image features under hazy conditions. To address this, we propose a joint learning framework that utilizes infrared image for the restoration and fusion of hazy IR-VIS images. To mitigate the adverse effects of feature diversity between IR-VIS images, we introduce a prompt generation mechanism that regulates modality-specific feature incompatibility. This creates a prompt selection matrix from non-shared image information, followed by prompt embeddings generated from a prompt pool. These embeddings help generate candidate features for dehazing. We further design an infrared-assisted feature restoration mechanism that selects candidate features based on haze density, enabling simultaneous restoration and fusion within a single-stage framework. To enhance fusion quality, we construct a multi-stage prompt embedding fusion module that leverages feature supplementation from the prompt generation module. Our method effectively fuses IR-VIS images while removing haze, yielding clear, haze-free fusion results. In contrast to two-stage methods that dehaze and then fuse, our approach enables collaborative training in a single-stage framework, making the model relatively lightweight and suitable for practical deployment. Experimental results validate its effectiveness and demonstrate advantages over existing methods.

The primary value of infrared and visible image fusion technology lies in applying the fusion results to downstream tasks. However, existing methods face challenges such as increased training complexity and significantly compromised performance of individual tasks when addressing multiple downstream tasks simultaneously. To tackle this, we propose Task-Oriented Adaptive Regulation (T-OAR), an adaptive mechanism specifically designed for multi-task environments. Additionally, we introduce the Task-related Dynamic Prompt Injection (T-DPI) module, which generates task-specific dynamic prompts from user-input text instructions and integrates them into target representations. This guides the feature extraction module to produce representations that are more closely aligned with the specific requirements of downstream tasks. By incorporating the T-DPI module into the T-OAR framework, our approach generates fusion images tailored to task-specific requirements without the need for separate training or task-specific weights. This not only reduces computational costs but also enhances adaptability and performance across multiple tasks. Experimental results show that our method excels in object detection, semantic segmentation, and salient object detection, demonstrating its strong adaptability, flexibility, and task specificity. This provides an efficient solution for image fusion in multi-task environments, highlighting the technology's potential across diverse applications., Comment: 10 pages, 7 figures

The MUltiplexed Survey Telescope (MUST) is a 6.5-meter telescope under development. Dedicated to highly-multiplexed, wide-field spectroscopic surveys, MUST observes over 20,000 targets simultaneously using 6.2-mm pitch positioning robots within a ~5 deg2 field of view. MUST aims to carry out the first Stage-V spectroscopic survey in the 2030s to map the 3D Universe with over 100 million galaxies and quasars, spanning from the nearby Universe to redshift z~5.5, corresponding to around 1 billion years after the Big Bang. To cover this extensive redshift range, we present an initial conceptual target selection algorithm for different types of galaxies, from local bright galaxies, luminous red galaxies, and emission line galaxies to high-redshift (2 < z < 5.5) Lyman-break galaxies. Using Fisher forecasts, we demonstrate that MUST can address fundamental questions in cosmology, including the nature of dark energy, test of gravity theories, and investigations into primordial physics. This is the first paper in the series of science white papers for MUST, with subsequent developments focusing on additional scientific cases such as galaxy and quasar evolution, Milky Way physics, and dynamic phenomena in the time-domain Universe., Comment: To be submitted to SCPMA

Kolmogorov-Arnold Networks(KANs), as a theoretically efficient neural network architecture, have garnered attention for their potential in capturing complex patterns. However, their application in computer vision remains relatively unexplored. This study first analyzes the potential of KAN in computer vision tasks, evaluating the performance of KAN and its convolutional variants in image classification and semantic segmentation. The focus is placed on examining their characteristics across varying data scales and noise levels. Results indicate that while KAN exhibits stronger fitting capabilities, it is highly sensitive to noise, limiting its robustness. To address this challenge, we propose a smoothness regularization method and introduce a Segment Deactivation technique. Both approaches enhance KAN's stability and generalization, demonstrating its potential in handling complex visual data tasks.

Variational Autoencoder (VAE) aims to compress pixel data into low-dimensional latent space, playing an important role in OpenAI's Sora and other latent video diffusion generation models. While most of existing video VAEs inflate a pretrained image VAE into the 3D causal structure for temporal-spatial compression, this paper presents two astonishing findings: (1) The initialization from a well-trained image VAE with the same latent dimensions suppresses the improvement of subsequent temporal compression capabilities. (2) The adoption of causal reasoning leads to unequal information interactions and unbalanced performance between frames. To alleviate these problems, we propose a keyframe-based temporal compression (KTC) architecture and a group causal convolution (GCConv) module to further improve video VAE (IV-VAE). Specifically, the KTC architecture divides the latent space into two branches, in which one half completely inherits the compression prior of keyframes from a lower-dimension image VAE while the other half involves temporal compression through 3D group causal convolution, reducing temporal-spatial conflicts and accelerating the convergence speed of video VAE. The GCConv in above 3D half uses standard convolution within each frame group to ensure inter-frame equivalence, and employs causal logical padding between groups to maintain flexibility in processing variable frame video. Extensive experiments on five benchmarks demonstrate the SOTA video reconstruction and generation capabilities of the proposed IV-VAE (https://wpy1999.github.io/IV-VAE/).

By representing knowledge in a primary triple associated with additional attribute-value qualifiers, hyper-relational knowledge graph (HKG) that generalizes triple-based knowledge graph (KG) has been attracting research attention recently. Compared with KG, HKG is enriched with the semantic qualifiers as well as the hyper-relational graph structure. However, to model HKG, existing studies mainly focus on either semantic information or structural information therein, which however fail to capture both simultaneously. To tackle this issue, in this paper, we generalize the hyperedge expansion in hypergraph learning and propose an equivalent transformation for HKG modeling, referred to as TransEQ. Specifically, the equivalent transformation transforms a HKG to a KG, which considers both semantic and structural characteristics. Then an encoder-decoder framework is developed to bridge the modeling research between KG and HKG. In the encoder part, KG-based graph neural networks are leveraged for structural modeling; while in the decoder part, various HKG-based scoring functions are exploited for semantic modeling. Especially, we design the sharing embedding mechanism in the encoder-decoder framework with semantic relatedness captured. We further theoretically prove that TransEQ preserves complete information in the equivalent transformation, and also achieves full expressivity. Finally, extensive experiments on three benchmarks demonstrate the superior performance of TransEQ in terms of both effectiveness and efficiency. On the largest benchmark WikiPeople, TransEQ significantly improves the state-of-the-art models by 15\% on MRR.

For any arbitrary string almost gentle algebra, we consider specific subsets of its quiver's arrow set, denoted by $\mathcal{R}$. For each such $\mathcal{R}$, we introduce the finitely generated module $M_{\mathcal{R}}$ and define its associated $\mathcal{R}$-endomorphism algebra $A_{\mathcal{R}}$. In this paper, we show that the representation type of a string gentle algebra $A$, the representation type of the $\mathcal{R}$-endomorphism algebra $A_{\mathcal{R}}$ for some $\mathcal{R}$, the representation types of all $\mathcal{R}$-algebras, and the representation type of the Cohen-Macaulay Auslander algebra $A^{\mathrm{CMA}}$ of $A$ are equivalent. The results presented here reveal a deep structural connection between different classes of algebras derived from string gentle algebras. By showing the equivalence of representation types, this work offers new insights into the nature of endomorphism algebras and Cohen-Macaulay Auslander algebras, contributing to a broader understanding of their algebraic properties and classification., Comment: 22 pages, 8 figures

Continual learning methods based on pre-trained models (PTM) have recently gained attention which adapt to successive downstream tasks without catastrophic forgetting. These methods typically refrain from updating the pre-trained parameters and instead employ additional adapters, prompts, and classifiers. In this paper, we from a novel perspective investigate the benefit of sparse orthogonal parameters for continual learning. We found that merging sparse orthogonality of models learned from multiple streaming tasks has great potential in addressing catastrophic forgetting. Leveraging this insight, we propose a novel yet effective method called SoTU (Sparse Orthogonal Parameters TUning). We hypothesize that the effectiveness of SoTU lies in the transformation of knowledge learned from multiple domains into the fusion of orthogonal delta parameters. Experimental evaluations on diverse CL benchmarks demonstrate the effectiveness of the proposed approach. Notably, SoTU achieves optimal feature representation for streaming data without necessitating complex classifier designs, making it a Plug-and-Play solution.

In this paper we present a conditional KRnet (cKRnet) based domain decomposed uncertainty quantification (CKR-DDUQ) approach to propagate uncertainties across different physical domains in models governed by partial differential equations (PDEs) with random inputs. This approach is based on the domain decomposed uncertainty quantification (DDUQ) method presented in [Q. Liao and K. Willcox, SIAM J. Sci. Comput., 37 (2015), pp. A103--A133], which suffers a bottleneck of density estimation for local joint input distributions in practice. In this work, we reformulate the required joint distributions as conditional distributions, and propose a new conditional normalizing flow model, called cKRnet, to efficiently estimate the conditional probability density functions. We present the general framework of CKR-DDUQ, conduct its convergence analysis, validate its accuracy and demonstrate its efficiency with numerical experiments.

Most incremental learners excessively prioritize coarse classes of objects while neglecting various kinds of states (e.g. color and material) attached to the objects. As a result, they are limited in the ability to reason fine-grained compositionality of state-object pairs. To remedy this limitation, we propose a novel task called Compositional Incremental Learning (composition-IL), enabling the model to recognize state-object compositions as a whole in an incremental learning fashion. Since the lack of suitable benchmarks, we re-organize two existing datasets and make them tailored for composition-IL. Then, we propose a prompt-based Composition Incremental Learner (CompILer), to overcome the ambiguous composition boundary problem which challenges composition-IL largely. Specifically, we exploit multi-pool prompt learning, which is regularized by inter-pool prompt discrepancy and intra-pool prompt diversity. Besides, we devise object-injected state prompting by using object prompts to guide the selection of state prompts. Furthermore, we fuse the selected prompts by a generalized-mean strategy, to eliminate irrelevant information learned in the prompts. Extensive experiments on two datasets exhibit state-of-the-art performance achieved by CompILer., Comment: NeurIPS 2024

Aside from regular beamline experiments at light sources, the preparation steps before these experiments are also worth systematic consideration in terms of automation; a representative category in these steps is attitude tuning, which typically appears in names like beam focusing, sample alignment etc. With the goal of saving time and manpower in both writing and using in mind, a Mamba-based attitude-tuning framework is created. It supports flexible input/output ports, easy integration of diverse evaluation functions, and free selection of optimisation algorithms; with the help from Mamba's infrastructure, machine learning (ML) and artificial intelligence (AI) technologies can also be readily integrated. The tuning of a polycapillary lens and of an X-ray emission spectrometer are given as examples for the general use of this framework, featuring powerful command-line interfaces (CLIs) and friendly graphical user interfaces (GUIs) that allow comfortable human-in-the-loop control. The tuning of a Raman spectrometer demonstrates more specialised use of the framework with customised optimisation algorithms. With similar applications in mind, our framework is estimated to be capable of fulfilling a majority of attitude-tuning needs. Also reported is a virtual-beamline mechanism based on easily customisable simulated detectors and motors, which facilitates both testing for developers and training for users., Comment: 12 pages, 8 figures

Architectural deficiencies in EPICS lead to inefficiency in the development and application of EPICS input/output controllers (IOCs). An unintrusive solution is replacing EPICS IOCs with more maintainable and flexible Python IOCs, only reusing the Channel Access (CA) protocol of EPICS. After a digression about GUI development inspired by EPICS operator interfaces (OPIs), the structural similarity between standalone GUI backends, the Mamba backend, EPICS IOCs and other server programs is analysed. By combining the caproto library and event loops like those in these server programs, the QueueIOC framework for Python IOCs is created, which has the potential to systematically replace most EPICS IOCs currently used. Examples are first given for workalikes of StreamDevice and asyn; examples for seq-like applications include monochromators, motor anti-bumping and motor multiplexing. Also shown is software to use with the ~/iocBoot convention which addresses some issues with a similar solution based on procServ, along with a workalike of procServControl. A QueueIOC-based framework for detector integration, which overcomes areaDetector's limitations in performance and architecture, is presented in an accompanying paper., Comment: 14 pages, 8 figures

At least 25 kinds of detector-like devices need to be integrated in Phase I of the High Energy Photon Source (HEPS), and the work needs to be carefully planned to maximise productivity with highly limited human resources. After a systematic analysis on the actual work involved in detector integration, a separation of concerns between collaborating groups of personnel is established to minimise the duplication of efforts. To facilitate software development for detector integration, the ADGenICam library, which abstracts repeated code in EPICS modules for cameras, is extended to support a much wider range of detectors. An increasingly considerable fraction of detectors, both inside and outside HEPS, offer performance that exceed capabilities of the areaDetector framework in EPICS. Given this background, areaDetector's limitations in performance and architecture are analysed, and a QueueIOC -based framework that overcomes these limitations is introduced. A simple, flexible ZeroMQ-based protocol is used for data transport in this framework, while RDMA transport and multi-node readout will be explored for higher data throughputs. By calling C/C++ libraries from within Python, the performance of the former and the expressiveness of the latter can coexist nicely; the expressiveness allows for much higher efficiency in the implementation and use of integration modules functionally comparable to their EPICS counterparts., Comment: 11 pages, 3 figures

Reconstructing a continuous surface from a raw 3D point cloud is a challenging task. Recent methods usually train neural networks to overfit on single point clouds to infer signed distance functions (SDFs). However, neural networks tend to smooth local details due to the lack of ground truth signed distances or normals, which limits the performance of overfitting-based methods in reconstruction tasks. To resolve this issue, we propose a novel method, named MultiPull, to learn multi-scale implicit fields from raw point clouds by optimizing accurate SDFs from coarse to fine. We achieve this by mapping 3D query points into a set of frequency features, which makes it possible to leverage multi-level features during optimization. Meanwhile, we introduce optimization constraints from the perspective of spatial distance and normal consistency, which play a key role in point cloud reconstruction based on multi-scale optimization strategies. Our experiments on widely used object and scene benchmarks demonstrate that our method outperforms the state-of-the-art methods in surface reconstruction., Comment: Accepted by NeurIPS 2024. Project page: https://takeshie.github.io/MultiPull/

Recent research arXiv:2410.15027 has explored the use of diffusion transformers (DiTs) for task-agnostic image generation by simply concatenating attention tokens across images. However, despite substantial computational resources, the fidelity of the generated images remains suboptimal. In this study, we reevaluate and streamline this framework by hypothesizing that text-to-image DiTs inherently possess in-context generation capabilities, requiring only minimal tuning to activate them. Through diverse task experiments, we qualitatively demonstrate that existing text-to-image DiTs can effectively perform in-context generation without any tuning. Building on this insight, we propose a remarkably simple pipeline to leverage the in-context abilities of DiTs: (1) concatenate images instead of tokens, (2) perform joint captioning of multiple images, and (3) apply task-specific LoRA tuning using small datasets (e.g., 20~100 samples) instead of full-parameter tuning with large datasets. We name our models In-Context LoRA (IC-LoRA). This approach requires no modifications to the original DiT models, only changes to the training data. Remarkably, our pipeline generates high-fidelity image sets that better adhere to prompts. While task-specific in terms of tuning data, our framework remains task-agnostic in architecture and pipeline, offering a powerful tool for the community and providing valuable insights for further research on product-level task-agnostic generation systems. We release our code, data, and models at https://github.com/ali-vilab/In-Context-LoRA, Comment: Tech report. Project page: https://ali-vilab.github.io/In-Context-LoRA-Page/

The communications and interrelations between different locations on the Earth's surface have far-reaching implications for both social and natural systems. Effective spatial analytics ideally require a spatial representation, where geographic principles are succinctly expressed within a defined metric space. However, common spatial representations, including map-based or network-based approaches, fall short by incompletely or inaccurately defining this metric space. Here we show, by introducing an inverse friction factor that captures the spatial constraints in spatial networks, that a homogeneous, low-dimensional spatial representation - termed the Geographic Manifold - can be achieved. We illustrate the effectiveness of the Geographic Manifold in two classic scenarios of spatial analytics - location choice and propagation, where the otherwise complicated analyses are reduced to straightforward regular partitioning and concentric diffusing, respectively on the manifold with a high degree of accuracy. We further empirically explain and formally prove the general existence of the Geographic Manifold, which is grounded in the intrinsic Euclidean low-dimensional statistical physics properties of geographic phenomena. This work represents a step towards formalizing Tobler's famous First Law of Geography from a geometric approach, where a regularized geospace thereby yielded is expected to contribute in learning abstract spatial structure representations for understanding and optimization purposes.

The fast development of location-based social networks (LBSNs) has led to significant changes in society, resulting in popular studies of using LBSN data for socioeconomic prediction, e.g., regional population and commercial activity estimation. Existing studies design various graphs to model heterogeneous LBSN data, and further apply graph representation learning methods for socioeconomic prediction. However, these approaches heavily rely on heuristic ideas and expertise to extract task-relevant knowledge from diverse data, which may not be optimal for specific tasks. Additionally, they tend to overlook the inherent relationships between different indicators, limiting the prediction accuracy. Motivated by the remarkable abilities of large language models (LLMs) in commonsense reasoning, embedding, and multi-agent collaboration, in this work, we synergize LLM agents and knowledge graph for socioeconomic prediction. We first construct a location-based knowledge graph (LBKG) to integrate multi-sourced LBSN data. Then we leverage the reasoning power of LLM agent to identify relevant meta-paths in the LBKG for each type of socioeconomic prediction task, and design a semantic-guided attention module for knowledge fusion with meta-paths. Moreover, we introduce a cross-task communication mechanism to further enhance performance by enabling knowledge sharing across tasks at both LLM agent and KG levels. On the one hand, the LLM agents for different tasks collaborate to generate more diverse and comprehensive meta-paths. On the other hand, the embeddings from different tasks are adaptively merged for better socioeconomic prediction. Experiments on two datasets demonstrate the effectiveness of the synergistic design between LLM and KG, providing insights for information sharing across socioeconomic prediction tasks.

Many current visual object tracking benchmarks such as OTB100, NfS, UAV123, LaSOT, and GOT-10K, predominantly contain day-time scenarios while the challenges posed by the night-time has been less investigated. It is primarily because of the lack of a large-scale, well-annotated night-time benchmark for rigorously evaluating tracking algorithms. To this end, this paper presents NT-VOT211, a new benchmark tailored for evaluating visual object tracking algorithms in the challenging night-time conditions. NT-VOT211 consists of 211 diverse videos, offering 211,000 well-annotated frames with 8 attributes including camera motion, deformation, fast motion, motion blur, tiny target, distractors, occlusion and out-of-view. To the best of our knowledge, it is the largest night-time tracking benchmark to-date that is specifically designed to address unique challenges such as adverse visibility, image blur, and distractors inherent to night-time tracking scenarios. Through a comprehensive analysis of results obtained from 42 diverse tracking algorithms on NT-VOT211, we uncover the strengths and limitations of these algorithms, highlighting opportunities for enhancements in visual object tracking, particularly in environments with suboptimal lighting. Besides, a leaderboard for revealing performance rankings, annotation tools, comprehensive meta-information and all the necessary code for reproducibility of results is made publicly available. We believe that our NT-VOT211 benchmark will not only be instrumental in facilitating field deployment of VOT algorithms, but will also help VOT enhancements and it will unlock new real-world tracking applications. Our dataset and other assets can be found at: {https://github.com/LiuYuML/NV-VOT211., Comment: Oral Acceptance at the Asian Conference on Computer Vision (ACCV) 2024, Hanoi, Vietnam

RGB video object tracking is a fundamental task in computer vision. Its effectiveness can be improved using depth information, particularly for handling motion-blurred target. However, depth information is often missing in commonly used tracking benchmarks. In this work, we propose a new framework that leverages monocular depth estimation to counter the challenges of tracking targets that are out of view or affected by motion blur in RGB video sequences. Specifically, our work introduces following contributions. To the best of our knowledge, we are the first to propose a depth attention mechanism and to formulate a simple framework that allows seamlessly integration of depth information with state of the art tracking algorithms, without RGB-D cameras, elevating accuracy and robustness. We provide extensive experiments on six challenging tracking benchmarks. Our results demonstrate that our approach provides consistent gains over several strong baselines and achieves new SOTA performance. We believe that our method will open up new possibilities for more sophisticated VOT solutions in real-world scenarios. Our code and models are publicly released: https://github.com/LiuYuML/Depth-Attention., Comment: Oral Acceptance at the Asian Conference on Computer Vision (ACCV) 2024, Hanoi, Vietnam

In this article we reframe the classic problem of massive location choice for retail chains, introducing an alternative approach. Traditional methodologies of massive location choice models encounter limitations rooted in assumptions such as power-law distance decay and oversimplified travel patterns. In response, we present a spatial operations research model aimed at maximizing customer coverage, using massive individual trajectories as a "sampling" of human flows, and thus the model is robust. Formulating the retail location selection problem as a set-covering problem, we propose a greedy solution. Through a case study in Shenzhen utilizing real-world individual trajectory data, our approach demonstrates substantial improvements over prevailing location choices., Comment: 17 pages, 4 figures

Nonlocal interactions between photonic waveguide and giant atoms have attracted extensive attentions. Researchers have studied how to optimize and control quantum states via giant atoms. We here study the dynamical scattering of a single-photon wave packet by a giant atom coupled to a two-dimensional photonic waveguide via multiple spatial points. We show that arbitrary target scattering single-photon wave packets can be generated by adjusting the coupling strength between the giant atom and different lattice sites of the waveguide. Furthermore, the dynamical scattering of the wave packets enables us to study the propagating properties of the target scattering wave packets and observe the excitation of giant atoms. Our study provides alternative way for photon state control based on giant atoms., Comment: 13 pages, 6 figure

It is important to estimate an accurate signed distance function (SDF) from a point cloud in many computer vision applications. The latest methods learn neural SDFs using either a data-driven based or an overfitting-based strategy. However, these two kinds of methods are with either poor generalization or slow convergence, which limits their capability under challenging scenarios like highly noisy point clouds. To resolve this issue, we propose a method to promote pros of both data-driven based and overfitting-based methods for better generalization, faster inference, and higher accuracy in learning neural SDFs. We introduce a novel statistical reasoning algorithm in local regions which is able to finetune data-driven based priors without signed distance supervision, clean point cloud, or point normals. This helps our method start with a good initialization, and converge to a minimum in a much faster way. Our numerical and visual comparisons with the state-of-the-art methods show our superiority over these methods in surface reconstruction and point cloud denoising on widely used shape and scene benchmarks. The code is available at https://github.com/chenchao15/LocalN2NM., Comment: Accepted by NeurlPS 2024. Project page: https://chenchao15.github.io/LocalN2NM/

3D Gaussian Splatting (3DGS) has shown convincing performance in rendering speed and fidelity, yet the generation of Gaussian Splatting remains a challenge due to its discreteness and unstructured nature. In this work, we propose DiffGS, a general Gaussian generator based on latent diffusion models. DiffGS is a powerful and efficient 3D generative model which is capable of generating Gaussian primitives at arbitrary numbers for high-fidelity rendering with rasterization. The key insight is to represent Gaussian Splatting in a disentangled manner via three novel functions to model Gaussian probabilities, colors and transforms. Through the novel disentanglement of 3DGS, we represent the discrete and unstructured 3DGS with continuous Gaussian Splatting functions, where we then train a latent diffusion model with the target of generating these Gaussian Splatting functions both unconditionally and conditionally. Meanwhile, we introduce a discretization algorithm to extract Gaussians at arbitrary numbers from the generated functions via octree-guided sampling and optimization. We explore DiffGS for various tasks, including unconditional generation, conditional generation from text, image, and partial 3DGS, as well as Point-to-Gaussian generation. We believe that DiffGS provides a new direction for flexibly modeling and generating Gaussian Splatting., Comment: Accepted by NeurIPS 2024. Project page: https://junshengzhou.github.io/DiffGS

Novel view synthesis from sparse inputs is a vital yet challenging task in 3D computer vision. Previous methods explore 3D Gaussian Splatting with neural priors (e.g. depth priors) as an additional supervision, demonstrating promising quality and efficiency compared to the NeRF based methods. However, the neural priors from 2D pretrained models are often noisy and blurry, which struggle to precisely guide the learning of radiance fields. In this paper, We propose a novel method for synthesizing novel views from sparse views with Gaussian Splatting that does not require external prior as supervision. Our key idea lies in exploring the self-supervisions inherent in the binocular stereo consistency between each pair of binocular images constructed with disparity-guided image warping. To this end, we additionally introduce a Gaussian opacity constraint which regularizes the Gaussian locations and avoids Gaussian redundancy for improving the robustness and efficiency of inferring 3D Gaussians from sparse views. Extensive experiments on the LLFF, DTU, and Blender datasets demonstrate that our method significantly outperforms the state-of-the-art methods., Comment: Accepted by NeurIPS 2024. Project page: https://hanl2010.github.io/Binocular3DGS/

In this paper, we provide an overview of our attempts to harness data physicalizations as pedagogical tools for enhancing the understanding of visual channels. We first elaborate the research goals that we have crafted for the physicalization prototype, shedding light on the key principles that guided our design choices. Then we detail the materials and datasets we employed for nine channels on our physicalization prototype. A preliminary pilot study is followed to validate its effectiveness. In the end, we present our upcoming research initiatives, including a comparative study for assessing the usability of the physicalization system. In general, the main purpose of our work is to stimulate a wider engagement among visualization educators and researchers, encouraging them to delve into the potentialities of data physicalization as an innovative addition to contemporary teaching methodologies., Comment: 2 pages, 1 figure, IEEE VIS 2023 Poster

Traditional self-interference cancellation (SIC) methods are common in full-duplex (FD) integrated sensing and communication (ISAC) systems. However, exploring new SIC schemes is important due to the limitations of traditional approaches. With the challenging limitations of traditional SIC approaches, this paper proposes a novel simultaneous transmitting and reflecting reconfigurable intelligent surface (STAR-RIS)-enabled FD ISAC system, where STAR-RIS enhances simultaneous communication and target sensing and reduces self-interference (SI) to a level comparable to traditional SIC approaches. The optimization of maximizing the sensing signal-to-interference-plus-noise ratio (SINR) and the communication sum rate, both crucial for improving sensing accuracy and overall communication performance, presents significant challenges due to the non-convex nature of these problems. Therefore, we develop alternating optimization algorithms to iteratively tackle these problems. Specifically, we devise the semi-definite relaxation (SDR)-based algorithm for transmit beamformer design. For the reflecting and refracting coefficients design, we adopt the successive convex approximation (SCA) method and implement the SDR-based algorithm to tackle the quartic and quadratic constraints. Simulation results validate the effectiveness of the proposed algorithms and show that the proposed deployment can achieve better performance than that of the benchmark using the traditional SIC approach without STAR-RIS deployment.

Object navigation is crucial for robots, but traditional methods require substantial training data and cannot be generalized to unknown environments. Zero-shot object navigation (ZSON) aims to address this challenge, allowing robots to interact with unknown objects without specific training data. Language-driven zero-shot object navigation (L-ZSON) is an extension of ZSON that incorporates natural language instructions to guide robot navigation and interaction with objects. In this paper, we propose a novel Vision Language model with a Tree-of-thought Network (VLTNet) for L-ZSON. VLTNet comprises four main modules: vision language model understanding, semantic mapping, tree-of-thought reasoning and exploration, and goal identification. Among these modules, Tree-of-Thought (ToT) reasoning and exploration module serves as a core component, innovatively using the ToT reasoning framework for navigation frontier selection during robot exploration. Compared to conventional frontier selection without reasoning, navigation using ToT reasoning involves multi-path reasoning processes and backtracking when necessary, enabling globally informed decision-making with higher accuracy. Experimental results on PASTURE and RoboTHOR benchmarks demonstrate the outstanding performance of our model in LZSON, particularly in scenarios involving complex natural language as target instructions., Comment: Accepted by the International Conference on Pattern Recognition (ICPR) for Oral presentation

In this work, we propose a unified representation for Super-Resolution (SR) and Image Compression, termed Factorized Fields, motivated by the shared principles between these two tasks. Both SISR and Image Compression require recovering and preserving fine image details--whether by enhancing resolution or reconstructing compressed data. Unlike previous methods that mainly focus on network architecture, our proposed approach utilizes a basis-coefficient decomposition to explicitly capture multi-scale visual features and structural components in images, addressing the core challenges of both tasks. We first derive our SR model, which includes a Coefficient Backbone and Basis Swin Transformer for generalizable Factorized Fields. Then, to further unify these two tasks, we leverage the strong information-recovery capabilities of the trained SR modules as priors in the compression pipeline, improving both compression efficiency and detail reconstruction. Additionally, we introduce a merged-basis compression branch that consolidates shared structures, further optimizing the compression process. Extensive experiments show that our unified representation delivers state-of-the-art performance, achieving an average relative improvement of 204.4% in PSNR over the baseline in Super-Resolution (SR) and 9.35% BD-rate reduction in Image Compression compared to the previous SOTA., Comment: Project page: https://jayisaking.github.io/FIPER/

This paper proposes an ultra-low power, mixed-bit-width sparse convolutional neural network (CNN) accelerator to accelerate ventricular arrhythmia (VA) detection. The chip achieves 50% sparsity in a quantized 1D CNN using a sparse processing element (SPE) architecture. Measurement on the prototype chip TSMC 40nm CMOS low-power (LP) process for the VA classification task demonstrates that it consumes 10.60 $\mu$W of power while achieving a performance of 150 GOPS and a diagnostic accuracy of 99.95%. The computation power density is only 0.57 $\mu$W/mm$^2$, which is 14.23X smaller than state-of-the-art works, making it highly suitable for implantable and wearable medical devices., Comment: 2 pages, accepted to The 30th Asia and South Pacific Design Automation Conference (ASP-DAC 2025)

We present SpectroMotion, a novel approach that combines 3D Gaussian Splatting (3DGS) with physically-based rendering (PBR) and deformation fields to reconstruct dynamic specular scenes. Previous methods extending 3DGS to model dynamic scenes have struggled to represent specular surfaces accurately. Our method addresses this limitation by introducing a residual correction technique for accurate surface normal computation during deformation, complemented by a deformable environment map that adapts to time-varying lighting conditions. We implement a coarse-to-fine training strategy that significantly enhances scene geometry and specular color prediction. It is the only existing 3DGS method capable of synthesizing photorealistic real-world dynamic specular scenes, outperforming state-of-the-art methods in rendering complex, dynamic, and specular scenes. See our project page for video results at https://cdfan0627.github.io/spectromotion/., Comment: Project page: https://cdfan0627.github.io/spectromotion/

Probabilistic Bit (P-Bit) device serves as the core hardware for implementing Ising computation. However, the severe intrinsic variations of stochastic P-Bit devices hinder the large-scale expansion of the P-Bit array, significantly limiting the practical usage of Ising computation. In this work, a behavioral model which attributes P-Bit variations to two parameters {\alpha} and {\Delta}V is proposed. Then the weight compensation method is introduced, which can mitigate {\alpha} and {\Delta}V of P-Bits device variations by rederiving the weight matrix, enabling them to compute as ideal identical PBits without the need for weights retraining. Accurately extracting the {\alpha} and {\Delta}V simultaneously from a large P-Bit array which is prerequisite for the weight compensation method is a crucial and challenging task. To solve this obstacle, we present the novel automatic variation extraction algorithm which can extract device variations of each P-Bit in a large array based on Boltzmann machine learning. In order for the accurate extraction of variations from an extendable P-Bit array, an Ising Hamiltonian based on 3D ferromagnetic model is constructed, achieving precise and scalable array variation extraction. The proposed Automatic Extraction and Compensation algorithm is utilized to solve both 16-city traveling salesman problem(TSP) and 21-bit integer factorization on a large P-Bit array with variation, demonstrating its accuracy, transferability, and scalability., Comment: 15 pages, 17 figures

Neural Radiance Fields (NeRF) face significant challenges in few-shot scenarios, primarily due to overfitting and long training times for high-fidelity rendering. Existing methods, such as FreeNeRF and SparseNeRF, use frequency regularization or pre-trained priors but struggle with complex scheduling and bias. We introduce FrugalNeRF, a novel few-shot NeRF framework that leverages weight-sharing voxels across multiple scales to efficiently represent scene details. Our key contribution is a cross-scale geometric adaptation scheme that selects pseudo ground truth depth based on reprojection errors across scales. This guides training without relying on externally learned priors, enabling full utilization of the training data. It can also integrate pre-trained priors, enhancing quality without slowing convergence. Experiments on LLFF, DTU, and RealEstate-10K show that FrugalNeRF outperforms other few-shot NeRF methods while significantly reducing training time, making it a practical solution for efficient and accurate 3D scene reconstruction., Comment: Project page: https://linjohnss.github.io/frugalnerf/