Search

The process $e^+e^-\to K^0_S K^0_S \psi(3686)$ is studied by analyzing $e^+e^-$ collision data samples collected at eight center-of-mass energies ranging from 4.682 to 4.951 GeV with the BESIII detector operating at the BEPCII collider, corresponding to an integrated luminosity of $4.1~{\rm fb}^{-1}$. Observation of the $e^+e^-\to K^0_S K^0_S \psi(3686)$ process is found for the first time with a statistical significance of $6.3\sigma$, and the cross sections at each center-of-mass energy are measured. The ratio of cross sections of $e^+e^-\to K_S^0 K_S^0 \psi(3686)$ relative to $e^+e^-\to K^+ K^- \psi(3686)$ is determined to be $\frac{\sigma(e^+e^-\to K_S^0 K_S^0 \psi(3686))}{\sigma(e^+e^-\to K^+ K^- \psi(3686))}=0.45 \pm 0.25$, which is consistent with the prediction based on isospin symmetry. The uncertainty includes both statistical and systematic contributions. Additionally, the $K_S^0\psi(3686)$ invariant mass distribution is found to be consistent with three-body phase space. The significance of a contribution beyond three-body phase space is only $0.8\sigma$.

Using $(27.12\pm0.14) \times 10^{8}$ $\psi(2S)$ events collected by the BESIII detector operating at BEPCII, we search for the decay $\eta_c(2S)\to p\bar{p}$ via the process $\psi(2S)\to \gamma\eta_c(2S)$, and only find a signal with a significance of $1.7\,\sigma$. The upper limit of the product branching fraction at the 90% confidence level is determined to be $\mathcal{B}(\psi(2S)\to \gamma\eta_c(2S))\times \mathcal{B}(\eta_c(2S)\to p\bar{p})<2.4\times 10^{-7}$. The branching fractions of $\chi_{cJ}\to p\bar{p}~(J=0,1,2)$ are also measured to be $\mathcal{B}(\chi_{c0}\to p\bar{p})=(2.51\pm0.02\pm0.08)\times 10^{-4}$, $\mathcal{B}(\chi_{c1}\to p\bar{p})=(8.16\pm0.09\pm0.25)\times 10^{-4}$, and $\mathcal{B}(\chi_{c2}\to p\bar{p})=(8.33\pm0.09\pm0.22)\times 10^{-4}$, where the first uncertainty is statistical and the second systematic.

The rapid expansion of software systems and the growing number of reported vulnerabilities have emphasized the importance of accurately identifying vulnerable code segments. Traditional methods for vulnerability localization, such as manual code audits or rule-based tools, are often time-consuming and limited in scope, typically focusing on specific programming languages or types of vulnerabilities. In recent years, the introduction of large language models (LLMs) such as GPT and LLaMA has opened new possibilities for automating vulnerability detection. However, while LLMs show promise in this area, they face challenges, particularly in maintaining accuracy over longer code contexts. This paper introduces LOVA, a novel framework leveraging the self-attention mechanisms inherent in LLMs to enhance vulnerability localization. Our key insight is that self-attention mechanisms assign varying importance to different parts of the input, making it possible to track how much attention the model focuses on specific lines of code. In the context of vulnerability localization, the hypothesis is that vulnerable lines of code will naturally attract higher attention weights because they have a greater influence on the model's output. By systematically tracking changes in attention weights and focusing on specific lines of code, LOVA improves the precision of identifying vulnerable lines across various programming languages. Through rigorous experimentation and evaluation, we demonstrate that LOVA significantly outperforms existing LLM-based approaches, achieving up to a 5.3x improvement in F1-scores. LOVA also demonstrated strong scalability, with up to a 14.6x improvement in smart contract vulnerability localization across languages like C, Python, Java, and Solidity. Its robustness was proven through consistent performance across different LLM architectures.

Attention mechanisms, particularly channel attention, have become highly influential in numerous computer vision tasks. Despite their effectiveness, many existing methods primarily focus on optimizing performance through complex attention modules applied at individual convolutional layers, often overlooking the synergistic interactions that can occur across multiple layers. In response to this gap, we introduce bridge attention, a novel approach designed to facilitate more effective integration and information flow between different convolutional layers. Our work extends the original bridge attention model (BAv1) by introducing an adaptive selection operator, which reduces information redundancy and optimizes the overall information exchange. This enhancement results in the development of BAv2, which achieves substantial performance improvements in the ImageNet classification task, obtaining Top-1 accuracies of 80.49% and 81.75% when using ResNet50 and ResNet101 as backbone networks, respectively. These results surpass the retrained baselines by 1.61% and 0.77%, respectively. Furthermore, BAv2 outperforms other existing channel attention techniques, such as the classical SENet101, exceeding its retrained performance by 0.52% Additionally, integrating BAv2 into advanced convolutional networks and vision transformers has led to significant gains in performance across a wide range of computer vision tasks, underscoring its broad applicability.

In recent years, the issue of radon emanation and diffusion has become a critical concern for rare decay experiments, such as JUNO and PandaX-4T. This paper introduces a detector design featuring a symmetric radon detector cavity for the quantitative assessment of membrane materials' radon blocking capabilities. The performance of this design is evaluated through the application of Fick's Law and the diffusion equation considering material solubility. Our detector has completed measurements of radon diffusion coefficients for four types of membrane materials currently used in experiments, which also confirms the rationality of this detector design. The findings are instrumental in guiding the selection and evaluation of optimal materials for radon shielding to reduce radon background, contributing to boost sensitivities of rare event research., Comment: 7 pages, 10 figures and 2 tables

There is a vast literature on representation learning based on principles such as coding efficiency, statistical independence, causality, controllability, or symmetry. In this paper we propose to learn representations from sequence data by factorizing the transformations of the latent variables into sparse components. Input data are first encoded as distributions of latent activations and subsequently transformed using a probability flow model, before being decoded to predict a future input state. The flow model is decomposed into a number of rotational (divergence-free) vector fields and a number of potential flow (curl-free) fields. Our sparsity prior encourages only a small number of these fields to be active at any instant and infers the speed with which the probability flows along these fields. Training this model is completely unsupervised using a standard variational objective and results in a new form of disentangled representations where the input is not only represented by a combination of independent factors, but also by a combination of independent transformation primitives given by the learned flow fields. When viewing the transformations as symmetries one may interpret this as learning approximately equivariant representations. Empirically we demonstrate that this model achieves state of the art in terms of both data likelihood and unsupervised approximate equivariance errors on datasets composed of sequence transformations., Comment: submitted to T-PAMI

The inclusive cross sections of prompt $J/\psi$ and $\psi(3686)$ production are measured at center-of-mass energies from 3.808 to 4.951 GeV. The dataset used is 22 fb$^{-1}$ of $e^{+}e^{-}$ annihilation data collected with the BESIII detector operating at the BEPCII storage ring. The results obtained are in agreement with the previous BESIII measurements of exclusive $J/\psi$ and $\psi(3686)$ production. The average values obtained for the cross sections measured in the center-of-mass energy ranges from 4.527 to 4.951 GeV for $J/\psi$ and from 4.843 to 4.951 GeV for $\psi(3686)$, where the impact of known resonances is negligible, are $14.0\pm1.7\pm3.1$ pb and $15.3\pm3.0$ pb, respectively. For $J/\psi$, the first and the second uncertainties are statistical and systematic, respectively. For $\psi(3686)$, the uncertainty is total. These values are useful for testing charmonium production models., Comment: 20 pages, 6 figures

Vision foundation models, particularly the ViT family, have revolutionized image understanding by providing rich semantic features. However, despite their success in 2D comprehension, their abilities on grasping 3D spatial relationships are still unclear. In this work, we evaluate and enhance the 3D awareness of ViT-based models. We begin by systematically assessing their ability to learn 3D equivariant features, specifically examining the consistency of semantic embeddings across different viewpoints. Our findings indicate that improved 3D equivariance leads to better performance on various downstream tasks, including pose estimation, tracking, and semantic transfer. Building on this insight, we propose a simple yet effective finetuning strategy based on 3D correspondences, which significantly enhances the 3D correspondence understanding of existing vision models. Remarkably, even finetuning on a single object for just one iteration results in substantial performance gains. All code and resources will be made publicly available to support further advancements in 3D-aware vision models. Our code is available at https://github.com/qq456cvb/3DCorrEnhance.

Over the last two decades, the competing orders in high-$T_{c}$ cuprates have been intensely studied, such as pseudogap phase, charge density waves (CDW), and pair density waves (PDW), which are thought to play a crucial role in high-temperature superconductivity. Using the $t$-$J$ model on a square lattice as the simplest model for high-$T_{c}$ cuprates, we employed the fermionic tensor product state (fTPS) method for numerical investigations. Our study revealed new types of PDW states alongside the well-known $d$-wave state and the recently discovered fluctuating PDW state within the low-energy subspace of the $t$-$J$ model. We believe that the competition among these states in the underdoped region suggests the potential existence of a fluctuating quantum liquid of PDW states, providing direct evidence for the pseudogap phase's "cheap vortex" scenario. Furthermore, we discuss the potential experimental implication of our discovery., Comment: 10 pages, 17 figures

Understanding the intricate magnetic structures of materials is crucial for the advancements in material science, spintronics, and geology. Recent developments of quantum-enabled magnetometers, such as nitrogen-vacancy (NV) centers in diamond, have enabled direct imaging of magnetic field distributions associated with a wide variety of magnetic profiles. However, reconstructing the magnetization of a sample from a measured magnetic field map poses a complex inverse problem, which can be further complicated by the presence of measurement noise, finite spatial resolution, and the sample-to-sensor distance. While magnetic field distributions are typically measured through various available imaging methods, accurately reconstructing the underlying structures from these maps remains a challenge. In this work, we introduce a novel and efficient GPU-based method for reconstructing magnetic source quantities (i.e. spatially varying magnetization density) from measured magnetic fields with minimum prior assumptions. We validate our method by simulating diverse magnetic structures under realistic experimental conditions, including multi-domain ferromagnetism and magnetic spin textures such as skyrmion, anti-skyrmion, and meron. Experimentally, we apply our technique to investigate the magnetic field maps from a lunar rock (Apollo lunar mare basalt sample 10003,184) obtained using a wide-field quantum diamond microscope. The reconstructed magnetic domains of the lunar rock are consistent with current paleomagnetic knowledge. Our approach provides a versatile and universal tool for investigating complex magnetization profiles, paving the way for future quantum sensing experiments., Comment: 8 pages, 4 figures

Neutrino nucleus elastic scattering ({\nu}Ael) with reactor neutrinos is an interaction under full quantum-mechanical coherence. It has not yet been experimentally observed. We present new results on the studies of {\nu}Ael cross section with an electro-cooled p-type point-contact germanium detector at the Kuo-Sheng Reactor Neutrino laboratory. A total of (242)357 kg-days of Reactor ON(OFF) data at a detector threshold of 200 eVee in electron equivalent unit are analyzed. The Lindhard model parametrized by a single variable k which characterizes the quenching function was used. Limits at 90% confidence level are derived on the ratio {\rho} relative to standard model (SM) cross section of {\rho}<4.7 at the predicted value of k=0.162, while k<0.285 at the SM-value of {\rho}=1. Prospects on future positive measurements are discussed., Comment: 6 pages, 4 figures

Artificial intelligence (AI) has demonstrated significant success in automating the detection of glomeruli, the key functional units of the kidney, from whole slide images (WSIs) in kidney pathology. However, existing open-source tools are often distributed as source code or Docker containers, requiring advanced programming skills that hinder accessibility for non-programmers, such as clinicians. Additionally, current models are typically trained on a single dataset and lack flexibility in adjusting confidence levels for predictions. To overcome these challenges, we introduce GloFinder, a QuPath plugin designed for single-click automated glomeruli detection across entire WSIs with online editing through the graphical user interface (GUI). GloFinder employs CircleNet, an anchor-free detection framework utilizing circle representations for precise object localization, with models trained on approximately 160,000 manually annotated glomeruli. To further enhance accuracy, the plugin incorporates Weighted Circle Fusion (WCF), an ensemble method that combines confidence scores from multiple CircleNet models to produce refined predictions, achieving superior performance in glomerular detection. GloFinder enables direct visualization and editing of results in QuPath, facilitating seamless interaction for clinicians and providing a powerful tool for nephropathology research and clinical practice.

We present the polarization calibration of the 19-beam receiver at 1420 MHz within the full illumination of the Five-hundred-meter Aperture Spherical Telescope from October 2018 to March 2023. We perform spider observations to characterize the on-axis Mueller matrix of the central beam. The calibrated polarization percentage and polarization angle of a source with strong linear polarization emission are about 0.2\% and 0.5$^{\circ}$. Several parameters of the central-beam Mueller matrix show time variability from months to years, suggesting relatively frequent polarization calibrations are needed. We obtain the Mueller matrix parameters of the 18 off-center beams with the combination of on-the-fly observations and spider observations. The polarization calibration provides consistent fractional Stokes parameters of the 19 beams, although the Mueller matrix parameters of the off-center beams are not as accurate as those of the central beam. The Mueller matrix parameters of the central beam do not show a strong dependence on the reflector surface. However, we notice different off-center Mueller matrix parameters between the eastern and western sides of the reflector surface. We provide average parameters of the 19-beam Mueller matrices which should be applicable to observations from 2020 to 2022 with several caveats. After applying the average parameters, on-axis fractional linear polarization measurements $\gtrsim$ 10\% and on-axis fractional circular polarization measurements $\gtrsim$ 1.5\% can be considered high-confidence detections. For sources with weak polarization, timely polarization calibrations using spider observations are required., Comment: 16 pages, 13 figures, , Submitted to AJ

Despite their promise to perform complex reasoning, large language models (LLMs) have been shown to have limited effectiveness in end-to-end planning. This has inspired an intriguing question: if these models cannot plan well, can they still contribute to the planning framework as a helpful plan evaluator? In this work, we generalize this question to consider LLMs augmented with visual understanding, i.e., Vision-Language Models (VLMs). We introduce PathEval, a novel benchmark evaluating VLMs as plan evaluators in complex path-planning scenarios. Succeeding in the benchmark requires a VLM to be able to abstract traits of optimal paths from the scenario description, demonstrate precise low-level perception on each path, and integrate this information to decide the better path. Our analysis of state-of-the-art VLMs reveals that these models face significant challenges on the benchmark. We observe that the VLMs can precisely abstract given scenarios to identify the desired traits and exhibit mixed performance in integrating the provided information. Yet, their vision component presents a critical bottleneck, with models struggling to perceive low-level details about a path. Our experimental results show that this issue cannot be trivially addressed via end-to-end fine-tuning; rather, task-specific discriminative adaptation of these vision encoders is needed for these VLMs to become effective path evaluators.

Multimodal Large Language Models (MLLMs) have made significant strides in visual understanding and generation tasks. However, generating interleaved image-text content remains a challenge, which requires integrated multimodal understanding and generation abilities. While the progress in unified models offers new solutions, existing benchmarks are insufficient for evaluating these methods due to data size and diversity limitations. To bridge this gap, we introduce GATE OpenING (OpenING), a comprehensive benchmark comprising 5,400 high-quality human-annotated instances across 56 real-world tasks. OpenING covers diverse daily scenarios such as travel guide, design, and brainstorming, offering a robust platform for challenging interleaved generation methods. In addition, we present IntJudge, a judge model for evaluating open-ended multimodal generation methods. Trained with a novel data pipeline, our IntJudge achieves an agreement rate of 82. 42% with human judgments, outperforming GPT-based evaluators by 11.34%. Extensive experiments on OpenING reveal that current interleaved generation methods still have substantial room for improvement. Key findings on interleaved image-text generation are further presented to guide the development of next-generation models. The OpenING is open-sourced at https://opening.github.io., Comment: 53 pages, 19 figures

The recent breakthrough of large language models (LLMs) in natural language processing has sparked exploration in recommendation systems, however, their limited domain-specific knowledge remains a critical bottleneck. Specifically, LLMs lack key pieces of information crucial for sequential recommendations, such as user behavior patterns. To address this critical gap, we propose IDLE-Adapter, a novel framework that integrates pre-trained ID embeddings, rich in domain-specific knowledge, into LLMs to improve recommendation accuracy. IDLE-Adapter acts as a bridge, transforming sparse user-item interaction data into dense, LLM-compatible representations through a Pre-trained ID Sequential Model, Dimensionality Alignment, Layer-wise Embedding Refinement, and Layer-wise Distribution Alignment. Furthermore, IDLE-Adapter demonstrates remarkable flexibility by seamlessly integrating ID embeddings from diverse ID-based sequential models and LLM architectures. Extensive experiments across various datasets demonstrate the superiority of IDLE-Adapter, achieving over 10\% and 20\% improvements in HitRate@5 and NDCG@5 metrics, respectively, compared to state-of-the-art methods.

In 1965, Bollob\'as proved that for a Bollob\'as set-pair system $\{(A_i,B_i)\mid i\in[m]\}$, the maximum value of $\sum_{i=1}^m\binom{|A_i|+|B_i|}{A_i}^{-1}$ is $1$. In 2023, Heged\"{u}s and Frankl generalize the concept of Bollob\'as system to $d$-tuples, and made a conjecture: Suppose $\{(A_i^{(1)},\ldots,A_i^{(d)})\mid i\in[m]\}$ is a Bollob\'as system of $d$-tuples, the maximum value of $\sum_{i=1}^m\binom{|A_i^{(1)}|+\cdots+|A_i^{(d)}|}{|A_i^{(1)}|,\ldots,|A_i^{(d)}|}^{-1}$ is also $1$. In this paper, we show this conjecture is not correct, and we give an upper bound of it. In the case $d=3$, our upper bound is tight in the mean of asymptotic. We also improve an inequality for skew Bollob\'as systems of $d$-tuples of Heged\"{u}s and Frankl, and determine the maximum size or a uniform skew Bollob\'as system.

Many real-world user queries (e.g. "How do to make egg fried rice?") could benefit from systems capable of generating responses with both textual steps with accompanying images, similar to a cookbook. Models designed to generate interleaved text and images face challenges in ensuring consistency within and across these modalities. To address these challenges, we present ISG, a comprehensive evaluation framework for interleaved text-and-image generation. ISG leverages a scene graph structure to capture relationships between text and image blocks, evaluating responses on four levels of granularity: holistic, structural, block-level, and image-specific. This multi-tiered evaluation allows for a nuanced assessment of consistency, coherence, and accuracy, and provides interpretable question-answer feedback. In conjunction with ISG, we introduce a benchmark, ISG-Bench, encompassing 1,150 samples across 8 categories and 21 subcategories. This benchmark dataset includes complex language-vision dependencies and golden answers to evaluate models effectively on vision-centric tasks such as style transfer, a challenging area for current models. Using ISG-Bench, we demonstrate that recent unified vision-language models perform poorly on generating interleaved content. While compositional approaches that combine separate language and image models show a 111% improvement over unified models at the holistic level, their performance remains suboptimal at both block and image levels. To facilitate future work, we develop ISG-Agent, a baseline agent employing a "plan-execute-refine" pipeline to invoke tools, achieving a 122% performance improvement.

Few-shot image generation aims to generate diverse and high-quality images for an unseen class given only a few examples in that class. However, existing methods often suffer from a trade-off between image quality and diversity while offering limited control over the attributes of newly generated images. In this work, we propose Hyperbolic Diffusion Autoencoders (HypDAE), a novel approach that operates in hyperbolic space to capture hierarchical relationships among images and texts from seen categories. By leveraging pre-trained foundation models, HypDAE generates diverse new images for unseen categories with exceptional quality by varying semantic codes or guided by textual instructions. Most importantly, the hyperbolic representation introduces an additional degree of control over semantic diversity through the adjustment of radii within the hyperbolic disk. Extensive experiments and visualizations demonstrate that HypDAE significantly outperforms prior methods by achieving a superior balance between quality and diversity with limited data and offers a highly controllable and interpretable generation process.

In this work, we introduce a single parameter $\omega$, to effectively control granularity in diffusion-based synthesis. This parameter is incorporated during the denoising steps of the diffusion model's reverse process. Our approach does not require model retraining, architectural modifications, or additional computational overhead during inference, yet enables precise control over the level of details in the generated outputs. Moreover, spatial masks or denoising schedules with varying $\omega$ values can be applied to achieve region-specific or timestep-specific granularity control. Prior knowledge of image composition from control signals or reference images further facilitates the creation of precise $\omega$ masks for granularity control on specific objects. To highlight the parameter's role in controlling subtle detail variations, the technique is named Omegance, combining "omega" and "nuance". Our method demonstrates impressive performance across various image and video synthesis tasks and is adaptable to advanced diffusion models. The code is available at https://github.com/itsmag11/Omegance., Comment: Project page: https://itsmag11.github.io/Omegance/

No-Reference Image Quality Assessment for distorted images has always been a challenging problem due to image content variance and distortion diversity. Previous IQA models mostly encode explicit single-quality features of synthetic images to obtain quality-aware representations for quality score prediction. However, performance decreases when facing real-world distortion and restored images from restoration models. The reason is that they do not consider the degradation factors of the low-quality images adequately. To address this issue, we first introduce the DRI method to obtain degradation vectors and quality vectors of images, which separately model the degradation and quality information of low-quality images. After that, we add the restoration network to provide the MOS score predictor with degradation information. Then, we design the Representation-based Semantic Loss (RS Loss) to assist in enhancing effective interaction between representations. Extensive experimental results demonstrate that the proposed method performs favorably against existing state-of-the-art models on both synthetic and real-world datasets., Comment: 8 pages,6 figures, published to WACV

Medical image segmentation often faces the challenge of prohibitively expensive annotation costs. While few-shot learning offers a promising solution to alleviate this burden, conventional approaches still rely heavily on pre-training with large volumes of labeled data from known categories. To address this issue, we propose leveraging the Segment Anything Model (SAM), pre-trained on over 1 billion masks, thus circumventing the need for extensive domain-specific annotated data. In light of this, we developed SAM-MPA, an innovative SAM-based framework for few-shot medical image segmentation using Mask Propagation-based Auto-prompting. Initially, we employ k-centroid clustering to select the most representative examples for labelling to construct the support set. These annotated examples are registered to other images yielding deformation fields that facilitate the propagation of the mask knowledge to obtain coarse masks across the dataset. Subsequently, we automatically generate visual prompts based on the region and boundary expansion of the coarse mask, including points, box and a coarse mask. Finally, we can obtain the segmentation predictions by inputting these prompts into SAM and refine the results by post refinement module. We validate the performance of the proposed framework through extensive experiments conducted on two medical image datasets with different modalities. Our method achieves Dices of 74.53%, 94.36% on Breast US, Chest X-ray, respectively. Experimental results substantiate that SAM-MPA yields high-accuracy segmentations within 10 labeled examples, outperforming other state-of-the-art few-shot auto-segmentation methods. Our method enables the customization of SAM for any medical image dataset with a small number of labeled examples., Comment: Accepted as an oral presentation at NeurIPS 2024 AIM-FM Workshop

Segment Anything Model (SAM) has made great progress in anomaly segmentation tasks due to its impressive generalization ability. However, existing methods that directly apply SAM through prompting often overlook the domain shift issue, where SAM performs well on natural images but struggles in industrial scenarios. Parameter-Efficient Fine-Tuning (PEFT) offers a promising solution, but it may yield suboptimal performance by not adequately addressing the perception challenges during adaptation to anomaly images. In this paper, we propose a novel Self-Perceptinon Tuning (SPT) method, aiming to enhance SAM's perception capability for anomaly segmentation. The SPT method incorporates a self-drafting tuning strategy, which generates an initial coarse draft of the anomaly mask, followed by a refinement process. Additionally, a visual-relation-aware adapter is introduced to improve the perception of discriminative relational information for mask generation. Extensive experimental results on several benchmark datasets demonstrate that our SPT method can significantly outperform baseline methods, validating its effectiveness. Models and codes will be available online.

Pretrained models have revolutionized deep learning by enabling significant performance improvements across a wide range of tasks, leveraging large-scale, pre-learned knowledge representations. However, deploying these models in real-world multi-task learning (MTL) scenarios poses substantial challenges, primarily due to high computational costs and inefficiencies in inference. Traditional approaches such as pruning, quantization, and knowledge distillation have been explored to mitigate these issues, but they often fall short in fully addressing the complexities of multi-task environments. This paper introduces \textbf{\underline{S}}elective \textbf{\underline{T}}ask \textbf{\underline{A}}rithmetic \underline{\textbf{(STA)}}, a training-free framework designed to enhance multi-task performance through task-specific parameter fusion. STA addresses three key challenges: (i) \textbf{Parameter importance diversity: } Recognizing that different tasks relie on distinct parameters, STA employs a loss-sensitive parameter importance metric derived from a first-order Taylor expansion to accurately measure the importance of parameters for each task. (ii) \textbf{Over-reliance on hyperparameter tuning: }By enhancing the sparsity of task vectors through parameter importance metrics, STA reduces the need for extensive hyperparameter tuning, thereby improving the generalization and robustness of the model. (iii) \textbf{Neglect of other abilities in task arithmetic: } Previous works have largely overlooked the potential for more precise task forgetting. STA leverages its parameter importance metric to achieve more controlled and effective task forgetting, minimizing the impact of noisy elements that can degrade model performance. Experimental results demonstrate that STA achieves superior multi-task performance across benchmarks and excellent performance in task forgetting., Comment: Under Review

The stochastic nature of renewable energy and load demand requires efficient and accurate solutions for probabilistic optimal power flow (OPF). Quantum neural networks (QNNs), which combine quantum computing and machine learning, offer computational advantages in approximating OPF by effectively handling high-dimensional data. However, adversaries with access to non-private OPF solutions can potentially infer sensitive load demand patterns, raising significant privacy concerns. To address this issue, we propose a privacy-preserving QNN model for probabilistic OPF approximation. By incorporating Gaussian noise into the training process, the learning algorithm achieves ($\varepsilon, \delta$)-differential privacy with theoretical guarantees. Moreover, we develop a strongly entangled quantum state to enhance the nonlinearity expressiveness of the QNN. Experimental results demonstrate that the proposed method successfully prevents privacy leakage without compromising the statistical properties of probabilistic OPF. Moreover, compared to classical private neural networks, the QNN reduces the number of parameters by 90% while achieving significantly higher accuracy and greater stability., Comment: 7 pages, 4 figures

The 21-cm forest, composed of spectral absorption features from high-redshift background radio sources, provides a unique probe for studying small-scale structures during the epoch of reionization. It is particularly sensitive to detecting small-scale structures and early heating processes. Despite the rich information contained in the 21-cm forest signal, the complexity of directly modeling the signal has led to a lack of effective analytical models. However, the one-dimensional (1D) power spectrum of the 21-cm forest contains valuable information about the matter power spectrum, making analytical modeling feasible. This work employs an analytical modeling approach based on the halo model, which links the distribution of matter to dark matter halos, allowing for effective predictions of cosmic structure formation and its impact on the 21-cm signal. By considering various parameter scenarios within the halo model framework, particularly different dark matter particle masses and varying levels of cosmic heating, we can capture the complexities of small-scale structures and make the 1D power spectrum modeling applicable across a wide range of parameters. This method not only enhances our understanding of the 21-cm forest signal but also provides theoretical support for future observational data. Observing the 21-cm forest with large radio telescopes, such as the Square Kilometre Array, is anticipated to enable simultaneous exploration of dark matter properties and the heating history of the early universe., Comment: 10 pages, 7 figures

Electrical contact is fundamental to almost every aspect of modern industry, including the fast-growing electric vehicle industry. In metallic contacts in atmospheric conditions, most of the electrical current passes via the micro-junctions formed between two electrodes. The classic electrical contact theory predicts an infinite current density at the circular contact periphery. In the present work, we explore the influence of the dielectric breakdown of air outside the contact area on the electrical contact interface. Incorporating the discharging boundary condition governed by the modified Paschen law, we develop the numerical model as well as two sets of closed-form solutions for low applied voltage cases where two electrodes are in solid-solid contact and complete separation, respectively. For Hertzian contact, the present work theoretically proves that the ignorance of discharge can lead to a singular current density at the contact periphery and an overestimation of the electrical contact resistance. The current density monotonically increases along the radial direction to a finite value at the contact area periphery, followed by a monotonic drop within the discharge zone. The present study serves as a foundation for the modeling of discharging rough surface electrical contact and sheds light on the machine element surface damages caused by the electrical discharge machining.

Recent advancements in diffusion models have made generative image editing more accessible, enabling creative edits but raising ethical concerns, particularly regarding malicious edits to human portraits that threaten privacy and identity security. Existing protection methods primarily rely on adversarial perturbations to nullify edits but often fail against diverse editing requests. We propose FaceLock, a novel approach to portrait protection that optimizes adversarial perturbations to destroy or significantly alter biometric information, rendering edited outputs biometrically unrecognizable. FaceLock integrates facial recognition and visual perception into perturbation optimization to provide robust protection against various editing attempts. We also highlight flaws in commonly used evaluation metrics and reveal how they can be manipulated, emphasizing the need for reliable assessments of protection. Experiments show FaceLock outperforms baselines in defending against malicious edits and is robust against purification techniques. Ablation studies confirm its stability and broad applicability across diffusion-based editing algorithms. Our work advances biometric defense and sets the foundation for privacy-preserving practices in image editing. The code is available at: https://github.com/taco-group/FaceLock., Comment: GitHub: https://github.com/taco-group/FaceLock

In the domain of large language models, considerable advancements have been attained in multimodal large language models and explainability research, propelled by the continuous technological progress and innovation. Nonetheless, security and privacy concerns continue to pose as prominent challenges in this field. The emergence of blockchain technology, marked by its decentralized nature, tamper-proof attributes, distributed storage functionality, and traceability, has provided novel approaches for resolving these issues. Both of these technologies independently hold vast potential for development; yet, their combination uncovers substantial cross-disciplinary opportunities and growth prospects. The current research tendencies are increasingly concentrating on the integration of blockchain with large language models, with the aim of compensating for their respective limitations through this fusion and promoting further technological evolution. In this study, we evaluate the advantages and developmental constraints of the two technologies, and explore the possibility and development potential of their combination. This paper primarily investigates the technical convergence in two directions: Firstly, the application of large language models to blockchain, where we identify six major development directions and explore solutions to the shortcomings of blockchain technology and their application scenarios; Secondly, the application of blockchain technology to large language models, leveraging the characteristics of blockchain to remedy the deficiencies of large language models and exploring its application potential in multiple fields.

Reward modeling is crucial for aligning large language models (LLMs) with human preferences, especially in reinforcement learning from human feedback (RLHF). However, current reward models mainly produce scalar scores and struggle to incorporate critiques in a natural language format. We hypothesize that predicting both critiques and the scalar reward would improve reward modeling ability. Motivated by this, we propose Critic-RM, a framework that improves reward models using self-generated critiques without extra supervision. Critic-RM employs a two-stage process: generating and filtering high-quality critiques, followed by joint fine-tuning on reward prediction and critique generation. Experiments across benchmarks show that Critic-RM improves reward modeling accuracy by 3.7%-7.3% compared to standard reward models and LLM judges, demonstrating strong performance and data efficiency. Additional studies further validate the effectiveness of generated critiques in rectifying flawed reasoning steps with 2.5%-3.2% gains in improving reasoning accuracy., Comment: 20 pages

The increasing complexity of AI models, especially in deep learning, has raised concerns about transparency and accountability, particularly in high-stakes applications like medical diagnostics, where opaque models can undermine trust. Explainable Artificial Intelligence (XAI) aims to address these issues by providing clear, interpretable models. Among XAI techniques, Concept Bottleneck Models (CBMs) enhance transparency by using high-level semantic concepts. However, CBMs are vulnerable to concept-level backdoor attacks, which inject hidden triggers into these concepts, leading to undetectable anomalous behavior. To address this critical security gap, we introduce ConceptGuard, a novel defense framework specifically designed to protect CBMs from concept-level backdoor attacks. ConceptGuard employs a multi-stage approach, including concept clustering based on text distance measurements and a voting mechanism among classifiers trained on different concept subgroups, to isolate and mitigate potential triggers. Our contributions are threefold: (i) we present ConceptGuard as the first defense mechanism tailored for concept-level backdoor attacks in CBMs; (ii) we provide theoretical guarantees that ConceptGuard can effectively defend against such attacks within a certain trigger size threshold, ensuring robustness; and (iii) we demonstrate that ConceptGuard maintains the high performance and interpretability of CBMs, crucial for trustworthiness. Through comprehensive experiments and theoretical proofs, we show that ConceptGuard significantly enhances the security and trustworthiness of CBMs, paving the way for their secure deployment in critical applications., Comment: 17pages, 4 figures

Concept Bottleneck Models (CBMs) enhance model interpretability by introducing human-understandable concepts within the architecture. However, existing CBMs assume static datasets, limiting their ability to adapt to real-world, continuously evolving data streams. To address this, we define a novel concept-incremental and class-incremental continual learning task for CBMs, enabling models to accumulate new concepts and classes over time while retaining previously learned knowledge. To achieve this, we propose CONceptual Continual Incremental Learning (CONCIL), a framework that prevents catastrophic forgetting by reformulating concept and decision layer updates as linear regression problems, thus eliminating the need for gradient-based updates. CONCIL requires only recursive matrix operations, making it computationally efficient and suitable for real-time and large-scale data applications. Experimental results demonstrate that CONCIL achieves "absolute knowledge memory" and outperforms traditional CBM methods in concept- and class-incremental settings, establishing a new benchmark for continual learning in CBMs.

The Zero-Shot Object Navigation (ZSON) task requires embodied agents to find a previously unseen object by navigating in unfamiliar environments. Such a goal-oriented exploration heavily relies on the ability to perceive, understand, and reason based on the spatial information of the environment. However, current LLM-based approaches convert visual observations to language descriptions and reason in the linguistic space, leading to the loss of spatial information. In this paper, we introduce TopV-Nav, a MLLM-based method that directly reasons on the top-view map with complete spatial information. To fully unlock the MLLM's spatial reasoning potential in top-view perspective, we propose the Adaptive Visual Prompt Generation (AVPG) method to adaptively construct semantically-rich top-view map. It enables the agent to directly utilize spatial information contained in the top-view map to conduct thorough reasoning. Besides, we design a Dynamic Map Scaling (DMS) mechanism to dynamically zoom top-view map at preferred scales, enhancing local fine-grained reasoning. Additionally, we devise a Target-Guided Navigation (TGN) mechanism to predict and to utilize target locations, facilitating global and human-like exploration. Experiments on MP3D and HM3D benchmarks demonstrate the superiority of our TopV-Nav, e.g., $+3.9\%$ SR and $+2.0\%$ SPL absolute improvements on HM3D., Comment: 10 pages

We hypothesize that a user's visual history with images reflecting their daily life, offers valuable insights into their interests and preferences, and can be leveraged for personalization. Among the many challenges to achieve this goal, the foremost is the diversity and noises in the visual history, containing images not necessarily related to a recommendation task, not necessarily reflecting the user's interest, or even not necessarily preference-relevant. Existing recommendation systems either rely on task-specific user interaction logs, such as online shopping history for shopping recommendations, or focus on text signals. We propose a novel approach, VisualLens, that extracts, filters, and refines image representations, and leverages these signals for personalization. We created two new benchmarks with task-agnostic visual histories, and show that our method improves over state-of-the-art recommendations by 5-10% on Hit@3, and improves over GPT-4o by 2-5%. Our approach paves the way for personalized recommendations in scenarios where traditional methods fail.

Effective extraction of the world knowledge in LLMs for complex decision-making tasks remains a challenge. We propose a framework PIANIST for decomposing the world model into seven intuitive components conducive to zero-shot LLM generation. Given only the natural language description of the game and how input observations are formatted, our method can generate a working world model for fast and efficient MCTS simulation. We show that our method works well on two different games that challenge the planning and decision making skills of the agent for both language and non-language based action taking, without any training on domain-specific training data or explicitly defined world model., Comment: Published at Language Gamification Workshop 2024 @ NeurIPS

In a multi-tenant large language model (LLM) serving platform hosting diverse applications, some users may submit an excessive number of requests, causing the service to become unavailable to other users and creating unfairness. Existing fairness approaches do not account for variations in token lengths across applications and multiple LLM calls, making them unsuitable for such platforms. To address the fairness challenge, this paper analyzes millions of requests from thousands of users on MS CoPilot, a real-world multi-tenant LLM platform hosted by Microsoft. Our analysis confirms the inadequacy of existing methods and guides the development of FairServe, a system that ensures fair LLM access across diverse applications. FairServe proposes application-characteristic aware request throttling coupled with a weighted service counter based scheduling technique to curb abusive behavior and ensure fairness. Our experimental results on real-world traces demonstrate FairServe's superior performance compared to the state-of-the-art method in ensuring fairness. We are actively working on deploying our system in production, expecting to benefit millions of customers world-wide.

Adapting machine learning models to new domains without labeled data, especially when source data is inaccessible, is a critical challenge in applications like medical imaging, autonomous driving, and remote sensing. This task, known as Source-Free Unsupervised Domain Adaptation (SFUDA), involves adapting a pre-trained model to a target domain using only unlabeled target data, which can lead to issues such as overfitting, underfitting, and poor generalization due to domain discrepancies and noise. Existing SFUDA methods often rely on single-model architectures, struggling with uncertainty and variability in the target domain. To address these challenges, we propose DRIVE (Dual-Robustness through Information Variability and Entropy), a novel SFUDA framework leveraging a dual-model architecture. The two models, initialized with identical weights, work in parallel to capture diverse target domain characteristics. One model is exposed to perturbations via projection gradient descent (PGD) guided by mutual information, focusing on high-uncertainty regions. We also introduce an entropy-aware pseudo-labeling strategy that adjusts label weights based on prediction uncertainty, ensuring the model focuses on reliable data while avoiding noisy regions. The adaptation process has two stages: the first aligns the models on stable features using a mutual information consistency loss, and the second dynamically adjusts the perturbation level based on the loss from the first stage, encouraging the model to explore a broader range of the target domain while preserving existing performance. This enhances generalization capabilities and robustness against interference. Evaluations on standard SFUDA benchmarks show that DRIVE consistently outperforms previous methods, delivering improved adaptation accuracy and stability across complex target domains.

Chronic rhinosinusitis (CRS) is characterized by persistent inflammation in the paranasal sinuses, leading to typical symptoms of nasal congestion, facial pressure, olfactory dysfunction, and discolored nasal drainage, which can significantly impact quality-of-life. Eosinophils (Eos), a crucial component in the mucosal immune response, have been linked to disease severity in CRS. The diagnosis of eosinophilic CRS typically uses a threshold of 10-20 eos per high-power field (HPF). However, manually counting Eos in histological samples is laborious and time-intensive, making the use of AI-driven methods for automated evaluations highly desirable. Interestingly, eosinophils are predominantly located in the gastrointestinal (GI) tract, which has prompted the release of numerous deep learning models trained on GI data. This study leverages a CircleSnake model initially trained on upper-GI data to segment Eos cells in whole slide images (WSIs) of nasal tissues. It aims to determine the extent to which Eos segmentation models developed for the GI tract can be adapted to nasal applications without retraining. The experimental results show promising accuracy in some WSIs, although, unsurprisingly, the performance varies across cases. This paper details these performance outcomes, delves into the reasons for such variations, and aims to provide insights that could guide future development of deep learning models for eosinophilic CRS., Comment: 8 pages, 5 figures. Accepted by SPIE Medical Imaging 2025 on October 28, 2024

Instruction-based image editing aims to modify specific image elements with natural language instructions. However, current models in this domain often struggle to accurately execute complex user instructions, as they are trained on low-quality data with limited editing types. We present AnyEdit, a comprehensive multi-modal instruction editing dataset, comprising 2.5 million high-quality editing pairs spanning over 20 editing types and five domains. We ensure the diversity and quality of the AnyEdit collection through three aspects: initial data diversity, adaptive editing process, and automated selection of editing results. Using the dataset, we further train a novel AnyEdit Stable Diffusion with task-aware routing and learnable task embedding for unified image editing. Comprehensive experiments on three benchmark datasets show that AnyEdit consistently boosts the performance of diffusion-based editing models. This presents prospects for developing instruction-driven image editing models that support human creativity., Comment: 41 pages, 24 figures

We investigate nonradial $f$-mode oscillations of hybrid neutron stars in full general relativity, employing hybrid equations of state describing a nuclear outer core and a pasta-phase transition to a quark-matter core. The validity of various universal relations is confirmed for those stars. Prospects of observations are also discussed., Comment: 13 pages, 10 figures

Recent advancements in Large Language Models (LLMs) have opened new avenues for accelerating drug discovery processes. Despite their potential, several critical challenges remain unsolved, particularly in translating theoretical ideas into practical applications within the highly specialized field of pharmaceutical research, limiting practitioners from leveraging the latest AI development in drug discovery. To this end, we introduce DrugAgent, a multi-agent framework aimed at automating machine learning (ML) programming in drug discovery. DrugAgent incorporates domain expertise by identifying specific requirements and building domain-specific tools, while systematically exploring different ideas to find effective solutions. A preliminary case study demonstrates DrugAgent's potential to overcome key limitations LLMs face in drug discovery, moving toward AI-driven innovation. For example, DrugAgent is able to complete the ML programming pipeline end-to-end, from data acquisition to performance evaluation for the ADMET prediction task, and finally select the best model, where the random forest model achieves an F1 score of 0.92 when predicting absorption using the PAMPA dataset.