Search

Over the past year, there has been a notable rise in the use of large language models (LLMs) for academic research and industrial practices within the cybersecurity field. However, it remains a lack of comprehensive and publicly accessible benchmarks to evaluate the performance of LLMs on cybersecurity tasks. To address this gap, we introduce CS-Eval, a publicly accessible, comprehensive and bilingual LLM benchmark specifically designed for cybersecurity. CS-Eval synthesizes the research hotspots from academia and practical applications from industry, curating a diverse set of high-quality questions across 42 categories within cybersecurity, systematically organized into three cognitive levels: knowledge, ability, and application. Through an extensive evaluation of a wide range of LLMs using CS-Eval, we have uncovered valuable insights. For instance, while GPT-4 generally excels overall, other models may outperform it in certain specific subcategories. Additionally, by conducting evaluations over several months, we observed significant improvements in many LLMs' abilities to solve cybersecurity tasks. The benchmarks are now publicly available at https://github.com/CS-EVAL/CS-Eval.

In the past few years, channel-wise and spatial-wise attention blocks have been widely adopted as supplementary modules in deep neural networks, enhancing network representational abilities while introducing low complexity. Most attention modules follow a squeeze-and-excitation paradigm. However, to design such attention modules, requires a substantial amount of experiments and computational resources. Neural Architecture Search (NAS), meanwhile, is able to automate the design of neural networks and spares the numerous experiments required for an optimal architecture. This motivates us to design a search architecture that can automatically find near-optimal attention modules through NAS. We propose SASE, a Searching Architecture for Squeeze and Excitation operations, to form a plug-and-play attention block by searching within certain search space. The search space is separated into 4 different sets, each corresponds to the squeeze or excitation operation along the channel or spatial dimension. Additionally, the search sets include not only existing attention blocks but also other operations that have not been utilized in attention mechanisms before. To the best of our knowledge, SASE is the first attempt to subdivide the attention search space and search for architectures beyond currently known attention modules. The searched attention module is tested with extensive experiments across a range of visual tasks. Experimental results indicate that visual backbone networks (ResNet-50/101) using the SASE attention module achieved the best performance compared to those using the current state-of-the-art attention modules. Codes are included in the supplementary material, and they will be made public later.

Model library is an effective tool for improving the performance of single-model Out-of-Distribution (OoD) detector, mainly through model selection and detector fusion. However, existing methods in the literature do not provide uncertainty quantification for model selection results. Additionally, the model ensemble process primarily focuses on controlling the True Positive Rate (TPR) while neglecting the False Positive Rate (FPR). In this paper, we emphasize the significance of the proportion of models in the library that identify the test sample as an OoD sample. This proportion holds crucial information and directly influences the error rate of OoD detection.To address this, we propose inverting the commonly-used sequential p-value strategies. We define the rejection region initially and then estimate the error rate. Furthermore, we introduce a novel perspective from change-point detection and propose an approach for proportion estimation with automatic hyperparameter selection. We name the proposed approach as DOS-Storey-based Detector Ensemble (DSDE). Experimental results on CIFAR10 and CIFAR100 demonstrate the effectiveness of our approach in tackling OoD detection challenges. Specifically, the CIFAR10 experiments show that DSDE reduces the FPR from 11.07% to 3.31% compared to the top-performing single-model detector., Comment: 16 pages, 2 figures

Parameter-efficient fine-tuning (PEFT) significantly reduces memory costs when adapting large language models (LLMs) for downstream applications. However, traditional first-order (FO) fine-tuning algorithms incur substantial memory overhead due to the need to store activation values for back-propagation during gradient computation, particularly in long-context fine-tuning tasks. Zeroth-order (ZO) algorithms offer a promising alternative by approximating gradients using finite differences of function values, thus eliminating the need for activation storage. Nevertheless, existing ZO methods struggle to capture the low-rank gradient structure common in LLM fine-tuning, leading to suboptimal performance. This paper proposes a low-rank ZO gradient estimator and introduces a novel low-rank ZO algorithm (LOZO) that effectively captures this structure in LLMs. We provide convergence guarantees for LOZO by framing it as a subspace optimization method. Additionally, its low-rank nature enables LOZO to integrate with momentum techniques while incurring negligible extra memory costs. Extensive experiments across various model sizes and downstream tasks demonstrate that LOZO and its momentum-based variant outperform existing ZO methods and closely approach the performance of FO algorithms.

In vision-language models (VLMs), visual tokens usually consume a significant amount of computational overhead, despite their sparser information density compared to text tokens. To address this, most existing methods learn a network to prune redundant visual tokens and require additional training data. Differently, we propose an efficient training-free token optimization mechanism dubbed SparseVLM without extra parameters or fine-tuning costs. Concretely, given that visual tokens complement text tokens in VLMs for linguistic reasoning, we select visual-relevant text tokens to rate the significance of vision tokens within the self-attention matrix extracted from the VLMs. Then we progressively prune irrelevant tokens. To maximize sparsity while retaining essential information, we introduce a rank-based strategy to adaptively determine the sparsification ratio for each layer, alongside a token recycling method that compresses pruned tokens into more compact representations. Experimental results show that our SparseVLM improves the efficiency of various VLMs across a range of image and video understanding tasks. In particular, LLaVA equipped with SparseVLM reduces 61% to 67% FLOPs with a compression ratio of 78% while maintaining 93% of the accuracy. Our code is available at https://github.com/Gumpest/SparseVLMs., Comment: 17 pages

Soundscape appropriateness (SA) provides supplemental information on the matching degree between auditory information and the surrounding scene in soundscape perception. This indicator has been integrated into the standard ISO process for collecting soundscape data, forming a component of the sound quality assessment questionnaire. However, its role in soundscape quality assessment has not been fully understood. Herein, we present the findings from soundscape data collected from Beiling Park in Shenyang, China. A method was developed that integrates mediation effect models with multiscale geographically weighted regression models to explore the mediating role of SA in the impact of sound source types on soundscape quality, as well as the spatial heterogeneity of this mediation effect. The results confirm that SA does mediates the influence of sound source types on acoustics comfort (AC). Specifically, natural sounds (indirect effect/total effect = .19/.19), traffic sounds (indirect effect/total effect = -.46/-.65), and commercial sounds (indirect effect/total effect = -.25/-.12) impact the perception of AC by either enhancing or reducing SA. Moreover, the relationships among variables depicted in this model demonstrate spatial heterogeneity, demonstrating that in urban open spaces with complex constructures, local spatial models may be needed for soundscape assessment. The research reaffirms the significance of SA in urban open spaces. In terms of practical implications for urban and landscape planners, when sound sources cannot be controlled or altered, coordinating between the sound and the surrounding environment through landscape optimisation could also improve the quality of the soundscape through enhancing SA and help achieve the goal of creating healthy urban open spaces., Comment: Accepted by Journal of Environmental Management

Image matching is a fundamental and critical task of multisource remote sensing image applications. However, remote sensing images are susceptible to various noises. Accordingly, how to effectively achieve accurate matching in noise images is a challenging problem. To solve this issue, we propose a robust multisource remote sensing image matching method utilizing attention and feature enhancement against noise interference. In the first stage, we combine deep convolution with the attention mechanism of transformer to perform dense feature extraction, constructing feature descriptors with higher discriminability and robustness. Subsequently, we employ a coarse-to-fine matching strategy to achieve dense matches. In the second stage, we introduce an outlier removal network based on a binary classification mechanism, which can establish effective and geometrically consistent correspondences between images; through weighting for each correspondence, inliers vs. outliers classification are performed, as well as removing outliers from dense matches. Ultimately, we can accomplish more efficient and accurate matches. To validate the performance of the proposed method, we conduct experiments using multisource remote sensing image datasets for comparison with other state-of-the-art methods under different scenarios, including noise-free, additive random noise, and periodic stripe noise. Comparative results indicate that the proposed method has a more well-balanced performance and robustness. The proposed method contributes a valuable reference for solving the difficult problem of noise image matching., Comment: 21 pages, 13 figures

The research on weak magnetic field detection is of great significance in advancing the development of bioscience, aerospace, chip manufacturing and other fields. However, the weak magnetic detecting still face some problems, including the large size of the detectors and the limited detection scale. To contribute to the detection of weak magnetic fields, the Co-CsPbBr3 colloidal quantum dots (QDs) composite magnetic material was synthesised on the basis of the theory of room temperature ferromagnetism, molecular polarisation and vibration level of chemical bond. The synthesis involved the mixing of Co2+ into CsPbBr3, an all-inorganic perovskite with activated ions. Subsequently, a weak magnetic field measurement system was devised, comprising working medium samples and a vibration level detection optical path. Following the acquisition, comparison, processing and analysis of multiple data sets, a Stokes displacement function model was established under different magnetic field sizes and the weak magnetic field intensity range of Pitsla (pT) was measured. The Pitsla weak magnetic field measurement system proposed in this paper provides a reference for the development of non-contact weak magnetic measurement methods and for the advancement of intelligent and low-dimensional weak signal measurement applications.

Given a connected isotropic reductive not necessarily split $k$-group $\mathcal{G}$ with irreducible relative root system, we construct root group data (RGD) system of affine type for significant subgroups of $\mathcal{G}(k[t,t^{-1}])$, which can be extended to the whole group $\mathcal{G}(k[t,t^{-1}])$ under certain additional requirements. We rely on the relative pinning maps from paper "Elementary subgroups of isotropic reductive groups" by V. Petrov and A. Stavrova to construct the affine root groups. To verify the RGD axioms, we utilize the properties of the affine root groups, and the properties of reflections associated with the $k$-roots of $\mathcal{G}$., Comment: 25 pages

Vision-and-Language Navigation (VLN) tasks require an agent to follow textual instructions to navigate through 3D environments. Traditional approaches use supervised learning methods, relying heavily on domain-specific datasets to train VLN models. Recent methods try to utilize closed-source large language models (LLMs) like GPT-4 to solve VLN tasks in zero-shot manners, but face challenges related to expensive token costs and potential data breaches in real-world applications. In this work, we introduce Open-Nav, a novel study that explores open-source LLMs for zero-shot VLN in the continuous environment. Open-Nav employs a spatial-temporal chain-of-thought (CoT) reasoning approach to break down tasks into instruction comprehension, progress estimation, and decision-making. It enhances scene perceptions with fine-grained object and spatial knowledge to improve LLM's reasoning in navigation. Our extensive experiments in both simulated and real-world environments demonstrate that Open-Nav achieves competitive performance compared to using closed-source LLMs.

Quantum annealers offer a promising approach to solve Quadratic Unconstrained Binary Optimization (QUBO) problems, which have a wide range of applications. However, when a user submits its QUBO problem to a third-party quantum annealer, the problem itself may disclose the user's private information to the quantum annealing service provider. To mitigate this risk, we introduce a privacy-preserving QUBO framework and propose a novel solution method. Our approach employs a combination of digit-wise splitting and matrix permutation to obfuscate the QUBO problem's model matrix $Q$, effectively concealing the matrix elements. In addition, based on the solution to the obfuscated version of the QUBO problem, we can reconstruct the solution to the original problem with high accuracy. Theoretical analysis and empirical tests confirm the efficacy and efficiency of our proposed technique, demonstrating its potential for preserving user privacy in quantum annealing services., Comment: 8 pages, 3 figures, QCE 2024

This paper investigates the structural functional observability (SFO) and structural output controllability (SOC) of a class of systems with generically diagonalizable state matrices and explores the associated minimal sensor and actuator placement problems. The verification of SOC and the corresponding sensor and actuator placement problems, i.e., the problems of determining the minimum number of outputs and inputs required to achieve SFO and SOC, respectively, are yet open for general systems, which motivates our focus on a class of systems enabling polynomial-time solutions. In this line, we first define and characterize generically diagonalizable systems, referring to structured systems for which almost all realizations of the state matrices are diagonalizable. We then develop computationally efficient criteria for SFO and SOC within the context of generically diagonalizable systems. Our work expands the class of systems amenable to polynomial-time SOC verification. Thanks to the simplicity of the obtained criteria, we derive closed-form solutions for determining the minimal sensor placement to achieve SFO and the minimal actuator deployment to achieve SOC in such systems, along with efficient weighted maximum matching based and weighted maximum flow based algorithms. For more general systems to achieve SFO, an upper bound is given by identifying a non-decreasing property of SFO with respect to a specific class of edge additions, which is shown to be optimal under certain circumstances., Comment: Under review in a Journal

The "criticality hypothesis", based on observed scale-free correlations in neural activity, suggests that the animal brain operates at a critical point of transition between two phases. However, what these phases are, or whether such a hypothesis is at all valid, is still debated. Here, using a cortical dynamics model based on the work of Wilson and Cowan, we provide both analytical and numerical evidence that a phase of long-range order (LRO) in neural activity may be induced simply by memory (time non-locality) without invoking criticality. The cortical dynamics model contains two distinct time scales: a fast time scale that governs the neural dynamics and a slow one that controls the amount of available resources, acting as the system's memory. When the resource timescale is sufficiently long compared to the activity timescale, we observe an LRO phase, which manifests in avalanche size and duration distributions which follow scale-free probability distributions and satisfy finite-size scaling. When the slow and fast time scales are no longer sufficiently distinct, LRO is destroyed. Since this LRO phase spans a wide range of parameters, it is robust against perturbations, a desirable property not shared by critical systems., Comment: Main Text: 7 pages, 4 figures; Supplemental Material: 6 pages, 4 figures

The efficacy of deep learning-based Computer-Aided Diagnosis (CAD) methods for skin diseases relies on analyzing multiple data modalities (i.e., clinical+dermoscopic images, and patient metadata) and addressing the challenges of multi-label classification. Current approaches tend to rely on limited multi-modal techniques and treat the multi-label problem as a multiple multi-class problem, overlooking issues related to imbalanced learning and multi-label correlation. This paper introduces the innovative Skin Lesion Classifier, utilizing a Multi-modal Multi-label TransFormer-based model (SkinM2Former). For multi-modal analysis, we introduce the Tri-Modal Cross-attention Transformer (TMCT) that fuses the three image and metadata modalities at various feature levels of a transformer encoder. For multi-label classification, we introduce a multi-head attention (MHA) module to learn multi-label correlations, complemented by an optimisation that handles multi-label and imbalanced learning problems. SkinM2Former achieves a mean average accuracy of 77.27% and a mean diagnostic accuracy of 77.85% on the public Derm7pt dataset, outperforming state-of-the-art (SOTA) methods., Comment: Accepted by WACV2025

Endometriosis, affecting about 10% of individuals assigned female at birth, is challenging to diagnose and manage. Diagnosis typically involves the identification of various signs of the disease using either laparoscopic surgery or the analysis of T1/T2 MRI images, with the latter being quicker and cheaper but less accurate. A key diagnostic sign of endometriosis is the obliteration of the Pouch of Douglas (POD). However, even experienced clinicians struggle with accurately classifying POD obliteration from MRI images, which complicates the training of reliable AI models. In this paper, we introduce the Human-AI Collaborative Multi-modal Multi-rater Learning (HAICOMM) methodology to address the challenge above. HAICOMM is the first method that explores three important aspects of this problem: 1) multi-rater learning to extract a cleaner label from the multiple "noisy" labels available per training sample; 2) multi-modal learning to leverage the presence of T1/T2 MRI images for training and testing; and 3) human-AI collaboration to build a system that leverages the predictions from clinicians and the AI model to provide more accurate classification than standalone clinicians and AI models. Presenting results on the multi-rater T1/T2 MRI endometriosis dataset that we collected to validate our methodology, the proposed HAICOMM model outperforms an ensemble of clinicians, noisy-label learning models, and multi-rater learning methods.

We study the harmonic measure (i.e. the limit of the hitting distribution of a simple random walk starting from a distant point) on three canonical two-dimensional lattices: the square lattice $\mathbb{Z}^2$, the triangular lattice $\mathscr{T}$ and the hexagonal lattice $\mathscr{H}$. In particular, for the least positive value of the harmonic measure of any $n$-point set, denoted by $\mathscr{M}_n(\mathscr{G})$, we prove in this paper that $$[\lambda(\mathscr{G})]^{-n+c\sqrt{n}} \le \mathscr{M}_n(\mathscr{G})\le [\lambda(\mathscr{G})]^{-n+C\sqrt{n}},$$ where $\lambda(\mathbb{Z}^2)=(2+\sqrt{3})^2$, $\lambda(\mathscr{T})=3+2\sqrt{2}$ and $\lambda(\mathscr{H})=(\tfrac{3+\sqrt{5}}{2})^3$. Our results confirm a stronger version of the conjecture proposed by Calvert, Ganguly and Hammond (2023) which predicts the asymptotic of the exponent of $\mathscr{M}_n(\mathbb{Z}^2)$. Moreover, these estimates also significantly extend the findings in our previous paper with Kozma (2023) that $\mathscr{M}_n(\mathscr{G})$ decays exponentially for a large family of graphs $\mathscr{G}$ including $\mathscr{T}$, $\mathscr{H}$ and $\mathbb{Z}^d$ for all $d\ge 2$.

Facial recognition systems are susceptible to both physical and digital attacks, posing significant security risks. Traditional approaches often treat these two attack types separately due to their distinct characteristics. Thus, when being combined attacked, almost all methods could not deal. Some studies attempt to combine the sparse data from both types of attacks into a single dataset and try to find a common feature space, which is often impractical due to the space is difficult to be found or even non-existent. To overcome these challenges, we propose a novel approach that uses the sparse model to handle sparse data, utilizing different parameter groups to process distinct regions of the sparse feature space. Specifically, we employ the Mixture of Experts (MoE) framework in our model, expert parameters are matched to tokens with varying weights during training and adaptively activated during testing. However, the traditional MoE struggles with the complex and irregular classification boundaries of this problem. Thus, we introduce a flexible self-adapting weighting mechanism, enabling the model to better fit and adapt. In this paper, we proposed La-SoftMoE CLIP, which allows for more flexible adaptation to the Unified Attack Detection (UAD) task, significantly enhancing the model's capability to handle diversity attacks. Experiment results demonstrate that our proposed method has SOTA performance.

This paper addresses the problem of selecting the minimum number of dedicated sensors to achieve observability in the presence of unknown inputs, namely, the state and input observability, for linear time-invariant systems. We assume that the only available information is the zero-nonzero structure of system matrices, and approach this problem within a structured system model. We revisit the concept of state and input observability for structured systems, providing refined necessary and sufficient conditions for placing dedicated sensors via the Dulmage-Mendelsohn decomposition. Based on these conditions, we prove that determining the minimum number of dedicated sensors to achieve generic state and input observability is NP-hard, which contrasts sharply with the polynomial-time complexity of the corresponding problem with known inputs. We also demonstrate that this problem is hard to approximate within a factor of $(1-o(1)){\rm{log}}(n)$, where $n$ is the state dimension. Notwithstanding, we propose nontrivial upper and lower bounds that can be computed in polynomial time, which confine the optimal value of this problem to an interval with length being the number of inputs. We further present a special case for which the exact optimal value can be determined in polynomial time. Additionally, we propose a two-stage algorithm to solve this problem approximately. Each stage of the algorithm is either optimal or suboptimal and can be completed in polynomial time., Comment: 12 pages, 6 figures

Iris recognition is widely used in high-security scenarios due to its stability and distinctiveness. However, the acquisition of iris images typically requires near-infrared illumination and near-infrared band filters, leading to significant and consistent differences in imaging across devices. This underscores the importance of developing cross-domain capabilities in iris anti-spoofing methods. Despite this need, there is no dataset available that comprehensively evaluates the generalization ability of the iris anti-spoofing task. To address this gap, we propose the IrisGeneral dataset, which includes 10 subsets, belonging to 7 databases, published by 4 institutions, collected with 6 types of devices. IrisGeneral is designed with three protocols, aimed at evaluating average performance, cross-racial generalization, and cross-device generalization of iris anti-spoofing models. To tackle the challenge of integrating multiple sub-datasets in IrisGeneral, we employ multiple parameter sets to learn from the various subsets. Specifically, we utilize the Mixture of Experts (MoE) to fit complex data distributions using multiple sub-neural networks. To further enhance the generalization capabilities, we introduce a novel method Masked-MoE (MMoE). It randomly masks a portion of tokens for some experts and requires their outputs to be similar to the unmasked experts, which improves the generalization ability and effectively mitigates the overfitting issue produced by MoE. We selected ResNet50, VIT-B/16, CLIP, and FLIP as representative models and benchmarked them on the IrisGeneral dataset. Experimental results demonstrate that our proposed MMoE with CLIP achieves the best performance on IrisGeneral.

Radio map (RM) is a promising technology that can obtain pathloss based on only location, which is significant for 6G network applications to reduce the communication costs for pathloss estimation. However, the construction of RM in traditional is either computationally intensive or depends on costly sampling-based pathloss measurements. Although the neural network (NN)-based method can efficiently construct the RM without sampling, its performance is still suboptimal. This is primarily due to the misalignment between the generative characteristics of the RM construction problem and the discrimination modeling exploited by existing NN-based methods. Thus, to enhance RM construction performance, in this paper, the sampling-free RM construction is modeled as a conditional generative problem, where a denoised diffusion-based method, named RadioDiff, is proposed to achieve high-quality RM construction. In addition, to enhance the diffusion model's capability of extracting features from dynamic environments, an attention U-Net with an adaptive fast Fourier transform module is employed as the backbone network to improve the dynamic environmental features extracting capability. Meanwhile, the decoupled diffusion model is utilized to further enhance the construction performance of RMs. Moreover, a comprehensive theoretical analysis of why the RM construction is a generative problem is provided for the first time, from both perspectives of data features and NN training methods. Experimental results show that the proposed RadioDiff achieves state-of-the-art performance in all three metrics of accuracy, structural similarity, and peak signal-to-noise ratio. The code is available at https://github.com/UNIC-Lab/RadioDiff.

Selective exposure, individuals' inclination to seek out information that supports their beliefs while avoiding information that contradicts them, plays an important role in the emergence of polarization. In the political domain, selective exposure is usually measured on a left-right ideology scale, ignoring finer details. Here, we combine survey and Twitter data collected during the 2022 Brazilian Presidential Election and investigate selective exposure patterns between the survey respondents and political influencers. We analyze the followship network between survey respondents and political influencers and find a multilevel community structure that reveals a hierarchical organization more complex than a simple split between left and right. Moreover, depending on the level we consider, we find different associations between network indices of exposure patterns and 189 individual attributes of the survey respondents. For example, at finer levels, the number of influencer communities a survey respondent follows is associated with several factors, such as demographics, news consumption frequency, and incivility perception. In comparison, only their political ideology is a significant factor at coarser levels. Our work demonstrates that measuring selective exposure at a single level, such as left and right, misses important information necessary to capture this phenomenon correctly.

Mathematically, topological invariants arise from the parallel transport of eigenstates on the energy bands, which, in physics, correspond to the adiabatic dynamical evolution of transient states. It determines the presence of boundary states, while lacking direct measurements. Here, we develop time-varying programmable coupling circuits between acoustic cavities to mimic the Hamiltonians in the Brillouin zone, with which excitation and adiabatic evolution of bulk states are realized in a unit cell. By extracting the Berry phases of the bulk band, topological invariants, including the Zak phase for the SSH model and the Chern number for the AAH model, are obtained convincingly. The bulk state evolution also provides insight into the topological charges of our newly developed non-Abelian models, which are also verified by observing the adiabatic eigenframe rotation. Our work not only provides a general recipe for telling various topological invariants but also sheds light on transient acoustic wave manipulations., Comment: 16 pages, 4 figures

Scene text retrieval aims to find all images containing the query text from an image gallery. Current efforts tend to adopt an Optical Character Recognition (OCR) pipeline, which requires complicated text detection and/or recognition processes, resulting in inefficient and inflexible retrieval. Different from them, in this work we propose to explore the intrinsic potential of Contrastive Language-Image Pre-training (CLIP) for OCR-free scene text retrieval. Through empirical analysis, we observe that the main challenges of CLIP as a text retriever are: 1) limited text perceptual scale, and 2) entangled visual-semantic concepts. To this end, a novel model termed FDP (Focus, Distinguish, and Prompt) is developed. FDP first focuses on scene text via shifting the attention to the text area and probing the hidden text knowledge, and then divides the query text into content word and function word for processing, in which a semantic-aware prompting scheme and a distracted queries assistance module are utilized. Extensive experiments show that FDP significantly enhances the inference speed while achieving better or competitive retrieval accuracy compared to existing methods. Notably, on the IIIT-STR benchmark, FDP surpasses the state-of-the-art model by 4.37% with a 4 times faster speed. Furthermore, additional experiments under phrase-level and attribute-aware scene text retrieval settings validate FDP's particular advantages in handling diverse forms of query text. The source code will be publicly available at https://github.com/Gyann-z/FDP., Comment: Accepted by ACM MM 2024

Recently, text-to-3D generation has attracted significant attention, resulting in notable performance enhancements. Previous methods utilize end-to-end 3D generation models to initialize 3D Gaussians, multi-view diffusion models to enforce multi-view consistency, and text-to-image diffusion models to refine details with score distillation algorithms. However, these methods exhibit two limitations. Firstly, they encounter conflicts in generation directions since different models aim to produce diverse 3D assets. Secondly, the issue of over-saturation in score distillation has not been thoroughly investigated and solved. To address these limitations, we propose PlacidDreamer, a text-to-3D framework that harmonizes initialization, multi-view generation, and text-conditioned generation with a single multi-view diffusion model, while simultaneously employing a novel score distillation algorithm to achieve balanced saturation. To unify the generation direction, we introduce the Latent-Plane module, a training-friendly plug-in extension that enables multi-view diffusion models to provide fast geometry reconstruction for initialization and enhanced multi-view images to personalize the text-to-image diffusion model. To address the over-saturation problem, we propose to view score distillation as a multi-objective optimization problem and introduce the Balanced Score Distillation algorithm, which offers a Pareto Optimal solution that achieves both rich details and balanced saturation. Extensive experiments validate the outstanding capabilities of our PlacidDreamer. The code is available at \url{https://github.com/HansenHuang0823/PlacidDreamer}., Comment: Accepted by ACM Multimedia 2024

Due to the fascinating generative performance of text-to-image diffusion models, growing text-to-3D generation works explore distilling the 2D generative priors into 3D, using the score distillation sampling (SDS) loss, to bypass the data scarcity problem. The existing text-to-3D methods have achieved promising results in realism and 3D consistency, but text-to-4D generation still faces challenges, including lack of realism and insufficient dynamic motions. In this paper, we propose a novel method for text-to-4D generation, which ensures the dynamic amplitude and authenticity through direct supervision provided by a video prior. Specifically, we adopt a text-to-video diffusion model to generate a reference video and divide 4D generation into two stages: static generation and dynamic generation. The static 3D generation is achieved under the guidance of the input text and the first frame of the reference video, while in the dynamic generation stage, we introduce a customized SDS loss to ensure multi-view consistency, a video-based SDS loss to improve temporal consistency, and most importantly, direct priors from the reference video to ensure the quality of geometry and texture. Moreover, we design a prior-switching training strategy to avoid conflicts between different priors and fully leverage the benefits of each prior. In addition, to enrich the generated motion, we further introduce a dynamic modeling representation composed of a deformation network and a topology network, which ensures dynamic continuity while modeling topological changes. Our method not only supports text-to-4D generation but also enables 4D generation from monocular videos. The comparison experiments demonstrate the superiority of our method compared to existing methods.

Model predictive control (MPC) has played a more crucial role in various robotic control tasks, but its high computational requirements are concerning, especially for nonlinear dynamical models. This paper presents a $\textbf{la}$tent $\textbf{l}$inear $\textbf{q}$uadratic $\textbf{r}$egulator (LaLQR) that maps the state space into a latent space, on which the dynamical model is linear and the cost function is quadratic, allowing the efficient application of LQR. We jointly learn this alternative system by imitating the original MPC. Experiments show LaLQR's superior efficiency and generalization compared to other baselines., Comment: Accepted at RSS 2024 workshop on Koopman Operators in Robotics

Nitrogen-vacancy (NV) centers in diamond have been successfully coupled to various optical structures to enhance their radiation by the Purcell effect. The participation of many NV centers in these studies may naturally lead to cooperative emission and superradiance, and our recent experimental study with a diamond membrane in a fiber-based ultra-narrow optical cavity demonstrated nonlinear radiation power and fast photon bunching which are signatures of such collective effects. In this theoretical article, we go beyond the simple model used in the previous study to address more phenomena, such as the appearance of bunching shoulders in the second-order correlation function, Rabi splitting in the steady-state spectrum, and population dynamics on excited Dicke states, which for moderate pumping explains the observed collective effects. Overall, our results can guide further experiments with NV centers, and they are also relevant for other solid-state color centers, such as silicon-vacancy centers in diamond and silicon carbide, boron-vacancy centers and carbon-related centers in hexagonal boron-nitride., Comment: 14 pages, 12 figures

The precise subtype classification of myeloproliferative neoplasms (MPNs) based on multimodal information, which assists clinicians in diagnosis and long-term treatment plans, is of great clinical significance. However, it remains a great challenging task due to the lack of diagnostic representativeness for local patches and the absence of diagnostic-relevant features from a single modality. In this paper, we propose a Dynamic Screening and Clinical-Enhanced Network (DSCENet) for the subtype classification of MPNs on the multimodal fusion of whole slide images (WSIs) and clinical information. (1) A dynamic screening module is proposed to flexibly adapt the feature learning of local patches, reducing the interference of irrelevant features and enhancing their diagnostic representativeness. (2) A clinical-enhanced fusion module is proposed to integrate clinical indicators to explore complementary features across modalities, providing comprehensive diagnostic information. Our approach has been validated on the real clinical data, achieving an increase of 7.91% AUC and 16.89% accuracy compared with the previous state-of-the-art (SOTA) methods. The code is available at https://github.com/yuanzhang7/DSCENet., Comment: Accepted by MICCAI2024

Portrait Animation aims to synthesize a lifelike video from a single source image, using it as an appearance reference, with motion (i.e., facial expressions and head pose) derived from a driving video, audio, text, or generation. Instead of following mainstream diffusion-based methods, we explore and extend the potential of the implicit-keypoint-based framework, which effectively balances computational efficiency and controllability. Building upon this, we develop a video-driven portrait animation framework named LivePortrait with a focus on better generalization, controllability, and efficiency for practical usage. To enhance the generation quality and generalization ability, we scale up the training data to about 69 million high-quality frames, adopt a mixed image-video training strategy, upgrade the network architecture, and design better motion transformation and optimization objectives. Additionally, we discover that compact implicit keypoints can effectively represent a kind of blendshapes and meticulously propose a stitching and two retargeting modules, which utilize a small MLP with negligible computational overhead, to enhance the controllability. Experimental results demonstrate the efficacy of our framework even compared to diffusion-based methods. The generation speed remarkably reaches 12.8ms on an RTX 4090 GPU with PyTorch. The inference code and models are available at https://github.com/KwaiVGI/LivePortrait

The label scarcity problem is the main challenge that hinders the wide application of deep learning systems in automatic cardiovascular diseases (CVDs) detection using electrocardiography (ECG). Tuning pre-trained models alleviates this problem by transferring knowledge learned from large datasets to downstream small datasets. However, bottlenecks in computational efficiency and detection performance limit its clinical applications. It is difficult to improve the detection performance without significantly sacrificing the computational efficiency during model training. Here, we propose a computation-efficient semi-supervised learning paradigm (CE-SSL) for robust and computation-efficient CVDs detection using ECG. It enables a robust adaptation of pre-trained models on downstream datasets with limited supervision and high computational efficiency. First, a random-deactivation technique is developed to achieve robust and fast low-rank adaptation of pre-trained weights. Subsequently, we propose a one-shot rank allocation module to determine the optimal ranks for the update matrices of the pre-trained weights. Finally, a lightweight semi-supervised learning pipeline is introduced to enhance model performance by leveraging labeled and unlabeled data with high computational efficiency. Extensive experiments on four downstream datasets demonstrate that CE-SSL not only outperforms the state-of-the-art methods in multi-label CVDs detection but also consumes fewer GPU footprints, training time, and parameter storage space. As such, this paradigm provides an effective solution for achieving high computational efficiency and robust detection performance in the clinical applications of pre-trained models under limited supervision. Code and Supplementary Materials are available at https://github.com/KAZABANA/CE-SSL

An essential topic for multimodal large language models (MLLMs) is aligning vision and language concepts at a finer level. In particular, we devote efforts to encoding visual referential information for tasks such as referring and grounding. Existing methods, including proxy encoding and geometry encoding, incorporate additional syntax to encode the object's location, bringing extra burdens in training MLLMs to communicate between language and vision. This study presents ClawMachine, offering a new methodology that notates an entity directly using the visual tokens. It allows us to unify the prompt and answer of visual referential tasks without additional syntax. Upon a joint vision-language vocabulary, ClawMachine unifies visual referring and grounding into an auto-regressive format and learns with a decoder-only architecture. Experiments validate that our model achieves competitive performance across visual referring and grounding tasks with a reduced demand for training data. Additionally, ClawMachine demonstrates a native ability to integrate multi-source information for complex visual reasoning, which prior MLLMs can hardly perform without specific adaptions., Comment: Project page: https://github.com/martian422/ClawMachine

In this paper, we extend our earlier unique continuation results \cite{PZ2} for the Schr\"odinger-type inequality $ |\bar\partial u| \le V|u|$ on a domain in $\mathbb C^n$ by removing the smoothness assumption on solutions $u = (u_1, \ldots, u_N)$. More specifically, we establish the unique continuation property for $W_{loc}^{1,1}$ solutions when the potential $V\in L_{loc}^p $, $ p>2n$; and for $W_{loc}^{1,2n+\epsilon}$ solutions when $V\in L_{loc}^{2n}$ with $N=1$ or $n = 2$. Although the unique continuation property fails in general if $V\in L_{loc}^{p}, p<2n$, we show that the property still holds for $W_{loc}^{1,1}$ solutions when $V $ is a small constant multiple of $ \frac{1}{|z|}$., Comment: 10 pages

Near every point of a real-analytic set in $\mathbb R^n$, we make use of Hironaka's resolution of singularity theorem to construct a family of continuous functions in $W^{1, 1}_{loc}$ such that their weak derivatives have (removable) singularity precisely on that set., Comment: 9 pages

Videos carry rich visual information including object description, action, interaction, etc., but the existing multimodal large language models (MLLMs) fell short in referential understanding scenarios such as video-based referring. In this paper, we present Artemis, an MLLM that pushes video-based referential understanding to a finer level. Given a video, Artemis receives a natural-language question with a bounding box in any video frame and describes the referred target in the entire video. The key to achieving this goal lies in extracting compact, target-specific video features, where we set a solid baseline by tracking and selecting spatiotemporal features from the video. We train Artemis on the newly established VideoRef45K dataset with 45K video-QA pairs and design a computationally efficient, three-stage training procedure. Results are promising both quantitatively and qualitatively. Additionally, we show that \model can be integrated with video grounding and text summarization tools to understand more complex scenarios. Code and data are available at https://github.com/qiujihao19/Artemis., Comment: 19 pages, 14 figures. Code and data are available at https://github.com/qiujihao19/Artemis

Image captioning has long been regarded as a fundamental task in visual understanding. Recently, however, few large vision-language model (LVLM) research discusses model's image captioning performance because of the outdated short-caption benchmarks and unreliable evaluation metrics. In this work, we propose to benchmark detail image caption task by curating high-quality evaluation datasets annotated by human experts, GPT-4V and Gemini-1.5-Pro. We also design a more reliable caption evaluation metric called CAPTURE (CAPtion evaluation by exTracting and coUpling coRE information). CAPTURE extracts visual elements, e.g., objects, attributes and relations from captions, and then matches these elements through three stages, achieving the highest consistency with expert judgements over other rule-based or model-based caption metrics. The proposed benchmark and metric provide reliable evaluation for LVLM's detailed image captioning ability. Guided by this evaluation, we further explore to unleash LVLM's detail caption capabilities by synthesizing high-quality data through a five-stage data construction pipeline. Our pipeline only uses a given LVLM itself and other open-source tools, without any human or GPT-4V annotation in the loop. Experiments show that the proposed data construction strategy significantly improves model-generated detail caption data quality for LVLMs with leading performance, and the data quality can be further improved in a self-looping paradigm. All code and dataset will be publicly available at https://github.com/foundation-multimodal-models/CAPTURE.

Recent advancements in text-to-image generation have been propelled by the development of diffusion models and multi-modality learning. However, since text is typically represented sequentially in these models, it often falls short in providing accurate contextualization and structural control. So the generated images do not consistently align with human expectations, especially in complex scenarios involving multiple objects and relationships. In this paper, we introduce the Scene Graph Adapter(SG-Adapter), leveraging the structured representation of scene graphs to rectify inaccuracies in the original text embeddings. The SG-Adapter's explicit and non-fully connected graph representation greatly improves the fully connected, transformer-based text representations. This enhancement is particularly notable in maintaining precise correspondence in scenarios involving multiple relationships. To address the challenges posed by low-quality annotated datasets like Visual Genome, we have manually curated a highly clean, multi-relational scene graph-image paired dataset MultiRels. Furthermore, we design three metrics derived from GPT-4V to effectively and thoroughly measure the correspondence between images and scene graphs. Both qualitative and quantitative results validate the efficacy of our approach in controlling the correspondence in multiple relationships.

Large vision-language models (LVLMs) have recently achieved rapid progress, exhibiting great perception and reasoning abilities concerning visual information. However, when faced with prompts in different sizes of solution spaces, LVLMs fail to always give consistent answers regarding the same knowledge point. This inconsistency of answers between different solution spaces is prevalent in LVLMs and erodes trust. To this end, we provide a multi-modal benchmark ConBench, to intuitively analyze how LVLMs perform when the solution space of a prompt revolves around a knowledge point. Based on the ConBench tool, we are the first to reveal the tapestry and get the following findings: (1) In the discriminate realm, the larger the solution space of the prompt, the lower the accuracy of the answers. (2) Establish the relationship between the discriminative and generative realms: the accuracy of the discriminative question type exhibits a strong positive correlation with its Consistency with the caption. (3) Compared to open-source models, closed-source models exhibit a pronounced bias advantage in terms of Consistency. Eventually, we ameliorate the consistency of LVLMs by trigger-based diagnostic refinement, indirectly improving the performance of their caption. We hope this paper will accelerate the research community in better evaluating their models and encourage future advancements in the consistency domain. The project is available at https://github.com/foundation-multimodal-models/ConBench., Comment: Accepted by NeurIPS 2024

With rapid urbanisation and the accompanying increase in traffic density, traffic noise has become a major concern in urban planning. However, traditional grid noise mapping methods have limitations in terms of time consumption, software costs, and a lack of parameter integration interfaces. These limitations hinder their ability to meet the need for iterative updates and rapid performance feedback in the early design stages of street-scale urban planning. Herein, we developed a rapid urban traffic noise mapping technique that leverages generative adversarial networks (GANs) as a surrogate model. This approach enables the rapid assessment of urban traffic noise distribution by using urban elements such as roads and buildings as the input. The mean values for the mean squared error (RMSE) and structural similarity index (SSIM) are 0.3024 dB(A) and 0.8528, respectively, for the validation dataset. The trained model is integrated into Grasshopper as a tool, facilitating the rapid generation of traffic noise maps. This integration allows urban designers and planners, even those without expertise in acoustics, to easily anticipate changes in acoustics impacts caused by design in the early design stages., Comment: Accepted by Applied Acoustics

Both horizontal and vertical coherent beam-beam instability are important issues at CEPC. The horizontal instability (X-Z instability) could be induced by beam-beam itself. In this paper we try to study the effect of chromaticity and resistive feedback by analysis and simulation. The vertical instability may be induced due to the combined effect of beam-beam interaction and vacuum impedance. Finite chromaticity and asymmetrical tunes have been proposed to suppress the vertical instability. Due to the further increase of impedance budget, we need to find more measures to mitigate the instability. The effect of resistive feedback and hourglass effect are evaluated by simulation., Comment: 4 pages, 5 figures, IPAC24 WECD2

Learning-based techniques have become popular in both model predictive control (MPC) and reinforcement learning (RL). Probabilistic ensemble (PE) models offer a promising approach for modelling system dynamics, showcasing the ability to capture uncertainty and scalability in high-dimensional control scenarios. However, PE models are susceptible to mode collapse, resulting in non-robust control when faced with environments slightly different from the training set. In this paper, we introduce the $\textbf{u}$ncertainty-$\textbf{d}$riven rob$\textbf{u}$st $\textbf{c}$ontrol (UDUC) loss as an alternative objective for training PE models, drawing inspiration from contrastive learning. We analyze the robustness of UDUC loss through the lens of robust optimization and evaluate its performance on the challenging Real-world Reinforcement Learning (RWRL) benchmark, which involves significant environmental mismatches between the training and testing environments.

In the Massive Open Online Courses (MOOC) learning scenario, the semantic information of instructional videos has a crucial impact on learners' emotional state. Learners mainly acquire knowledge by watching instructional videos, and the semantic information in the videos directly affects learners' emotional states. However, few studies have paid attention to the potential influence of the semantic information of instructional videos on learners' emotional states. To deeply explore the impact of video semantic information on learners' emotions, this paper innovatively proposes a multimodal emotion recognition method by fusing video semantic information and physiological signals. We generate video descriptions through a pre-trained large language model (LLM) to obtain high-level semantic information about instructional videos. Using the cross-attention mechanism for modal interaction, the semantic information is fused with the eye movement and PhotoPlethysmoGraphy (PPG) signals to obtain the features containing the critical information of the three modes. The accurate recognition of learners' emotional states is realized through the emotion classifier. The experimental results show that our method has significantly improved emotion recognition performance, providing a new perspective and efficient method for emotion recognition research in MOOC learning scenarios. The method proposed in this paper not only contributes to a deeper understanding of the impact of instructional videos on learners' emotional states but also provides a beneficial reference for future research on emotion recognition in MOOC learning scenarios.

The purpose of this paper is to study the unique continuation property for a Schr\"odinger-type equation $ \bar\partial u = Vu$ on a domain in $\mathbb C^n$, where the solution $u$ may be a scalar function, or a vector-valued function. While simple examples show that the unique continuation property fails in general if the potential $V\in L^{p}, p<2n$, we first prove that, in the case when $u $ is a scalar function, the unique continuation property holds when $V\in L_{loc}^{2n}$ and is $\bar\partial$-closed. For vector-valued smooth solutions, we establish the unique continuation property either when $V\in L_{loc}^p $, $ p>2n$ for $n\ge 3$, or when $V\in L_{loc}^{2n}$ for $n = 2$. Finally, we discuss the unique continuation property for some special cases where $V\notin L_{loc}^{2n}$, for instance, $V $ is a constant multiple of $ \frac{1}{|z|}$., Comment: 27 pages