February 2024 arXiv papers — page 16

Tao Peng, Ling Gui, Yi Sun

In recent years, the rapid development of deep learning technology has brought new prospects to the field of vulnerability detection. Many vulnerability detection methods involve converting source code into images for detection, yet they often overlook the quality of the generated images. Due to the fact that vulnerability images lack clear and continuous co

Nicola Vassena

We state two sufficient criteria for periodic oscillations in mass action systems. Neither criterion requires a computation of the Hurwitz determinants. Instead, both criteria exploit the linear algebra concepts of $D$-stability and $P$-matrices. The criteria are complementary: the first is based on a stable matrix that is not a $P^-$ matrix, while the secon

Tim Maurice Julitz, Antoine Tordeux, Nadine Schlüter, Manuel Löwer

Redundant architectures can improve the reliability of complex systems. However, component dependencies can affect the architecture and negate the benefit of redundancy. In this paper, we develop three component dependency models and analyze the reliability of different M-out-of-N configurations using Monte Carlo simulation. The first model assumes a linear

Toshiki Sakai, Jun Tsuchida, Hiroshi Yadohisa

A main purpose of spatial data analysis is to predict the objective variable for the unobserved locations. Although Geographically Weighted Regression (GWR) is often used for this purpose, estimation instability proves to be an issue. To address this issue, Bayesian Geographically Weighted Regression (BGWR) has been proposed. In BGWR, by setting the same pri

Takehiro Shoji, Jun Tsuchida, Hiroshi Yadohisa

When using the propensity score method to estimate the treatment effects, it is important to select the covariates to be included in the propensity score model. The inclusion of covariates unrelated to the outcome in the propensity score model led to bias and large variance in the estimator of treatment effects. Many data-driven covariate selection methods h

Hongfei Dai, Yufeng Chen, Wenlin Li, Fangmin Wang

Fiber optic networks are used worldwide and have been regarded as excellent media for transmitting time-frequency (TF) signals. In the past decades, fiber-based TF synchronization techniques have been extensively studied. Instruments based on these techniques have been successfully applied. With the increasing application of TF synchronization instruments, t

Zelin Ji, Zhijin Qin

The trend of massive connectivity pushes forward the explosive growth of end devices. The emergence of various applications has prompted a demand for pervasive connectivity and more efficient computing paradigms. On the other hand, the lack of computational capacity of the end devices restricts the implementation of the intelligent applications, and becomes

Martin Boosen, Michael Franke, Yves Vincent Grossmann, Sy Dat Ho

This paper analyses the practice of publishing research data within the Max Planck Society in the year 2020. The central finding of the study is that up to 40\% of the empirical text publications had research data available. The aggregation of the available data is predominantly analysed. There are differences between the sections of the Max Planck Society b

Zihua Liu, Yizhou Li, Masatoshi Okutomi

Stereo matching under foggy scenes remains a challenging task since the scattering effect degrades the visibility and results in less distinctive features for dense correspondence matching. While some previous learning-based methods integrated a physical scattering function for simultaneous stereo-matching and dehazing, simply removing fog might not aid dept

Qiuejie Xie, Qiming Feng, Tianqi Zhang, Qingqiu Li

Large language models (LLMs) are recognized as systems that closely mimic aspects of human intelligence. This capability has attracted attention from the social science community, who see the potential in leveraging LLMs to replace human participants in experiments, thereby reducing research costs and complexity. In this paper, we introduce a framework for l

Gregor Donabauer, Udo Kruschwitz

Pre-training of neural networks has recently revolutionized the field of Natural Language Processing (NLP) and has before demonstrated its effectiveness in computer vision. At the same time, advances around the detection of fake news were mainly driven by the context-based paradigm, where different types of signals (e.g. from social media) form graph-like st

Wenjiao Bian, Yusuke Monno, Masatoshi Okutomi

This paper addresses reflection removal, which is the task of separating reflection components from a captured image and deriving the image with only transmission components. Considering that the existence of the reflection changes the polarization state of a scene, some existing methods have exploited polarized images for reflection removal. While these met

Markus Kraft, Jonas Richter, Fengping Jin, Sourav Nandy

We investigate the Lindblad equation in the context of boundary-driven magnetization transport in spin-$1/2$ chains. Our central question is whether the nonequilibrium steady state of the open system, including its buildup in time, can be described on the basis of the dynamics in the closed system. To this end, we rely on a previous work [Phys. Rev. B 108, L

Shin-ichi Kimura, Muhammad Frassetia Lubis, Hiroshi Watanabe, Yasuyuki Shimura

At the quantum critical point of correlated materials, a non-Fermi liquid state appears where electron correlations continuously develop to very low temperatures. The relaxation time of the interacted electrons, namely quasiparticles, is scaled with the Planckian time, $\hbar/k_{\rm B}T$. However, there is a debate over whether heavy-fermion systems can obey

Zhuofeng Wu, Yusuke Monno, Masatoshi Okutomi

In this paper, we address the task of aberration-aware depth-from-defocus (DfD), which takes account of spatially variant point spread functions (PSFs) of a real camera. To effectively obtain the spatially variant PSFs of a real camera without requiring any ground-truth PSFs, we propose a novel self-supervised learning method that leverages the pair of real

Koen de Vos, Gijs van den Brandt, Jordy Senden, Pieter Pauwels

With the increase in the availability of Building Information Models (BIM) and (semi-) automatic tools to generate BIM from point clouds, we propose a world model architecture and algorithms to allow the use of the semantic and geometric knowledge encoded within these models to generate maps for robot localization and navigation. When heterogeneous robots ar

Pankaj Bhardwaj, Jarnail Singh, Vikram Verma, Ravi Kumar

Over the last two decades, the new branch of spintronics, i.e., semiconductor spintronics, has gained more attention because it integrates the characteristics of conventional semiconductors, such as optical bandgap and charge carriers, helpful for processing and computing pieces of information combined with magnets for data storage applications in a single d

Cidan Shi, Lihuang Fang, Han Wu, Xiaoyu Xian

In real-world environments, outdoor imaging systems are often affected by disturbances such as rain degradation. Especially, in nighttime driving scenes, insufficient and uneven lighting shrouds the scenes in darkness, resulting degradation of both the image quality and visibility. Particularly, in the field of autonomous driving, the visual perception abili

Zihua Liu, Songyan Zhang, Zhicheng Wang, Masatoshi Okutomi

Despite the remarkable progress facilitated by learning-based stereo-matching algorithms, disparity estimation in low-texture, occluded, and bordered regions still remains a bottleneck that limits the performance. To tackle these challenges, geometric guidance like plane information is necessary as it provides intuitive guidance about disparity consistency a

Samuel Mimram

A series of works has established rewriting as an essential tool in order to prove coherence properties of algebraic structures, such as MacLane's coherence theorem for monoidal categories, based on the observation that, under reasonable assumptions, confluence diagrams for critical pairs provide the required coherence axioms. We are interested here in exten

Feihong Lu, Weiqi Wang, Yangyifei Luo, Ziqin Zhu

Social media has become a ubiquitous tool for connecting with others, staying updated with news, expressing opinions, and finding entertainment. However, understanding the intention behind social media posts remains challenging due to the implicitness of intentions in social media posts, the need for cross-modality understanding of both text and images, and

Urtzi Buijs, José Carrasquel, Lucile Vandembroucq

We give an explicit minimal Quillen model for the Cartesian product $X\times Y$ of rational $2$-cones in terms of derivations and a binary operation $\star \colon \mathbb{M}(V)\otimes \mathbb{L}(W)\to \mathbb{L}(V\oplus W\oplus s(V\otimes W))$, where $(\mathbb{L}(V), \partial)$ and $(\mathbb{L}(W), \partial)$ are Quillen minimal models for $X$ and $Y$ respec

Qiyuan Zhu, A. K. Qin, Prabath Abeysekara, Hussein Dia

Traffic incident detection plays a key role in intelligent transportation systems, which has gained great attention in transport engineering. In the past, traditional machine learning (ML) based detection methods achieved good performance under a centralised computing paradigm, where all data are transmitted to a central server for building ML models therein

Lanling Xu, Zhen Tian, Bingqian Li, Junjie Zhang

With the rapid development of recommender systems, there is increasing side information that can be employed to improve the recommendation performance. Specially, we focus on the utilization of the associated \emph{textual data} of items (eg product title) and study how text features can be effectively fused with ID features in sequential recommendation. How

Michael Lorke, Igor Khanonkin, Stephan Michael, Johann Peter Reithmaier

In quantum-dot tunnel-injection lasers, the excited charge carriers are efficiently captured from the bulk states via an injector quantum well and then transferred into the quantum dots via a tunnel barrier. The alignment of the electronic levels is crucial for the high efficiency of these processes and especially for the fast modulation dynamics of these la

Jan Henrik Bertrand, David B. Hoffmann, Jacopo Pio Gargano, Laurent Mombaerts

Recent advances in representation learning have successfully leveraged the underlying domain-specific structure of data across various fields. However, representing diverse and complex entities stored in tabular format within a latent space remains challenging. In this paper, we introduce DEEPCAE, a novel method for calculating the regularization term for mu

William Gazali, Jocelyn Michelle Kho, Joshua Santoso, Williem

In recent years, model quantization for face recognition has gained prominence. Traditionally, compressing models involved vast datasets like the 5.8 million-image MS1M dataset as well as extensive training times, raising the question of whether such data enormity is essential. This paper addresses this by introducing an efficiency-driven approach, fine-tuni

Weilin Wan, Weizhong Zhang, Quan Zhou, Fan Yi

Out-of-distribution detection (OOD) is a crucial technique for deploying machine learning models in the real world to handle the unseen scenarios. In this paper, we first propose a simple yet effective Neural Activation Prior (NAP) for OOD detection. Our neural activation prior is based on a key observation that, for a channel before the global pooling layer

Yuanyuan Lian

We investigate the interior pointwise $C^{\alpha}$ regularity for weak solutions of elliptic and parabolic equations with divergence-free drifts. For such equations, the integrability condition on the drift can be relaxed and the interior $C^{\alpha}$ regularity for some $0<\alpha<1$ has been obtained previously with the aid of Harnack inequality. In this pa

Huihuang Zhou

In this paper, we genelize the Heintze-Karcher type inequalities for fractional Q-curvature $Q_{2\gamma}$ on conformally compact Einstein manifolds. Such inequality holds for all $\gamma\in (0,1]$. In particular, for $\gamma=\frac{1}{2}$ and $\gamma=1$, we obtain some rigidity theorems by characterising the equalities.

Yu Chen, Xiangcheng Zhang, Siwei Wang, Longbo Huang

In the realm of reinforcement learning (RL), accounting for risk is crucial for making decisions under uncertainty, particularly in applications where safety and reliability are paramount. In this paper, we introduce a general framework on Risk-Sensitive Distributional Reinforcement Learning (RS-DisRL), with static Lipschitz Risk Measures (LRM) and general f

Shiyao Li, Xuefei Ning, Luning Wang, Tengxuan Liu

Post-training quantization (PTQ) has emerged as a promising technique to reduce the cost of large language models (LLMs). Specifically, PTQ can effectively mitigate memory consumption and reduce computational overhead in LLMs. To meet the requirements of both high efficiency and performance across diverse scenarios, a comprehensive evaluation of quantized LL

Yulong Liu, Yunlong Yuan, Chunwei Wang, Jianhua Han

The distinction between humans and animals lies in the unique ability of humans to use and create tools. Tools empower humans to overcome physiological limitations, fostering the creation of magnificent civilizations. Similarly, enabling foundational models like Large Language Models (LLMs) with the capacity to learn external tool usage may serve as a pivota

Benjamin Capdeville

In [The Space of Spaces: Curvature Bounds and Gradient Flows on the Space of Metric Measure Spaces. Memoirs of the American Mathematical Society. American Mathematical Society, 2023], Sturm studied the space of all metric measure spaces up to isomorphism which he called The space of spaces. He also introduced for a natural number n the space of all n-points

Ellen Meyberg, Julius Degünther, Udo Seifert

For a Markovian dynamics on discrete states, the logarithmic ratio of waiting-time distributions between two successive, instantaneous transitions in forward and backward direction is a measure of time-irreversibility. It thus serves as an entropy estimator, which is exact in the case of a uni-cyclic network. We adopt this framework to overdamped Langevin dy

Zhuoran Jin, Pengfei Cao, Hongbang Yuan, Yubo Chen

Recently, retrieval augmentation and tool augmentation have demonstrated a remarkable capability to expand the internal memory boundaries of language models (LMs) by providing external context. However, internal memory and external context inevitably clash, leading to knowledge conflicts within LMs. In this paper, we aim to interpret the mechanism of knowled

Bedionita Soro, Bruno Andreis, Hayeon Lee, Wonyong Jeong

Transfer learning has gained significant attention in recent deep learning research due to its ability to accelerate convergence and enhance performance on new tasks. However, its success is often contingent on the similarity between source and target data, and training on numerous datasets can be costly, leading to blind selection of pretrained models with

Xinjie Zhang, Ren Yang, Dailan He, Xingtong Ge

Implicit neural representations (INRs) have emerged as a promising approach for video storage and processing, showing remarkable versatility across various video tasks. However, existing methods often fail to fully leverage their representation capabilities, primarily due to inadequate alignment of intermediate features during target frame decoding. This pap

Ozge Keskin, Ersin Gogus, Yuki Kaneko, Mustafa Demirer

SGR J1935+2154 has truly been the most prolific magnetar over the last decade: It has been entering into burst active episodes once every 1-2 years since its discovery in 2014, it emitted the first Galactic fast radio burst associated with an X-ray burst in 2020, and has emitted hundreds of energetic short bursts. Here, we present the time-resolved spectral

Abdul Basit, Khizar Hussain, Muhammad Abdullah Hanif, Muhammad Shafique

Large language models (LLMs) are revolutionizing various domains with their remarkable natural language processing (NLP) abilities. However, deploying LLMs in resource-constrained edge computing and embedded systems presents significant challenges. Another challenge lies in delivering medical assistance in remote areas with limited healthcare facilities and

Yanjie Li, Jingyi Liu, Weijun Li, Lina Yu

Mathematical formulas are the crystallization of human wisdom in exploring the laws of nature for thousands of years. Describing the complex laws of nature with a concise mathematical formula is a constant pursuit of scientists and a great challenge for artificial intelligence. This field is called symbolic regression (SR). Symbolic regression was originally

Shicheng Xu, Liang Pang, Mo Yu, Fandong Meng

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating additional information from retrieval. However, studies have shown that LLMs still face challenges in effectively using the retrieved information, even ignoring it or being misled by it. The key reason is that the training of LLMs does not clearly make LLMs learn how

Tonghe Zhang, Yu Chen, Longbo Huang

This work pioneers regret analysis of risk-sensitive reinforcement learning in partially observable environments with hindsight observation, addressing a gap in theoretical exploration. We introduce a novel formulation that integrates hindsight observations into a Partially Observable Markov Decision Process (POMDP) framework, where the goal is to optimize a

Clément Berger, David Coulette, Paul Vigneaux

With the growing demand of mineral consumption, the management of the mining waste is crucial. Cemented paste backfill (CPB) is one of the techniques developed by the mining industry to fill the voids generated by the excavation of underground spaces. The CPB process is the subject of various studies aimed at optimizing its implementation in the field. In th

Shyang-En Weng, Shaou-Gang Miaou, Ricky Christanto

Human vision relies heavily on available ambient light to perceive objects. Low-light scenes pose two distinct challenges: information loss due to insufficient illumination and undesirable brightness shifts. Low-light image enhancement (LLIE) refers to image enhancement technology tailored to handle this scenario. We introduce CPGA-Net, an innovative LLIE ne

Chaokang Jiang, Guangming Wang, Jiuming Liu, Hesheng Wang

Learning 3D scene flow from LiDAR point clouds presents significant difficulties, including poor generalization from synthetic datasets to real scenes, scarcity of real-world 3D labels, and poor performance on real sparse LiDAR point clouds. We present a novel approach from the perspective of auto-labelling, aiming to generate a large number of 3D scene flow

Zhenxiao Cheng, Jie Zhou, Wen Wu, Qin Chen

Gradient-based explanation methods are increasingly used to interpret neural models in natural language processing (NLP) due to their high fidelity. Such methods determine word-level importance using dimension-level gradient values through a norm function, often presuming equal significance for all gradient dimensions. However, in the context of Aspect-based

Seungjong Sun, Eungu Lee, Dongyan Nan, Xiangying Zhao

Large language models exhibit societal biases associated with demographic information, including race, gender, and others. Endowing such language models with personalities based on demographic data can enable generating opinions that align with those of humans. Building on this idea, we propose "random silicon sampling," a method to emulate the opinions of t

Rami Atar, Gershon Wolansky

We consider a load balancing model where a Poisson stream of jobs arrive at a system of many servers whose service time distribution possesses a finite second moment. A small fraction of arrivals pass through the so called power-of-choice algorithm, which assigns a job to the shortest among $\ell$, $\ell\ge 2$, randomly chosen queues, and the remaining jobs

K. J. Arnold, N. Jayjong, M. L. D. Kang, Qin Qichen

We investigate sideband spectroscopy of a trapped ion using a probe laser phase modulated at the trap drive frequency. The enhanced sensitivity of our technique over traditional sideband spectroscopy allows us to detect stray fields of $0.01\,\mathrm{V/m}$ on a timescale of a few minutes and detect differential phases of $5\,\mu\mathrm{rad}$ between applied

Junyu Ma

It was proved by Gromov-Lawson\cite{gl83} that complete three manifold with positive scalar curvature bounded below has finite Urysohn 1-width only depends on the uniform positive scalar curvature bounds. It is natural to ask the same question for the four manifolds. In this paper, we can show that closed four and five manifolds with positive biRicci curvatu

Jian Liu, Sipeng Zhang, Chuixin Kong, Wenyuan Zhang

This technical report presents our solution, "occTransformer" for the 3D occupancy prediction track in the autonomous driving challenge at CVPR 2023. Our method builds upon the strong baseline BEVFormer and improves its performance through several simple yet effective techniques. Firstly, we employed data augmentation to increase the diversity of the trainin

Swagata Ashwani, Kshiteesh Hegde, Nishith Reddy Mannuru, Mayank Jindal

With the rise of Large Language Models(LLMs), it has become crucial to understand their capabilities and limitations in deciphering and explaining the complex web of causal relationships that language entails. Current methods use either explicit or implicit causal reasoning, yet there is a strong need for a unified approach combining both to tackle a wide ar

Ágnes Nagyné Szokol, Judit Kámán, Roman Holomb, Márk Aladi

Plasmonic nanoparticles embedded into a solid matrix could play crucial role in laser-matter interactions. In this study, excess energy creation was observed during the single-shot irradiation of a polymer matrix containing plasmonic gold nanorods, resonant to the laser wavelength, with a high intensity femtosecond laser pulse. This effect was manifested in

Jianxiong Li, Jinliang Zheng, Yinan Zheng, Liyuan Mao

Multimodal pretraining is an effective strategy for the trinity of goals of representation learning in autonomous robots: 1) extracting both local and global task progressions; 2) enforcing temporal consistency of visual representation; 3) capturing trajectory-level language grounding. Most existing methods approach these via separate objectives, which often

Michele Girfoglio, Annalisa Quaini, Gianluigi Rozza

We consider three conservative forms of the mildly compressible Euler equations, called CE1, CE2 and CE3, with the goal of understanding which leads to the most accurate and robust pressure-based solver in a finite volume environment. Forms CE1 and CE2 are both written in density, momentum, and specific enthalpy, but employ two different treatments of the bu

Rachid Achbah

This study aims to empirically investigate the impact of managers' characteristics on their choice between in-court and out-of-court restructuring. Based on the theory of upper echelons, we tested the preferences of 342 managers of financially distressed French firms regarding restructuring decisions. The overall findings of this study provide empirical supp

Chu Zhou, Minggui Teng, Xinyu Zhou, Chao Xu

A polarization camera can capture four linear polarized images with different polarizer angles in a single shot, which is useful in polarization-based vision applications since the degree of linear polarization (DoLP) and the angle of linear polarization (AoLP) can be directly computed from the captured polarized images. However, since the on-chip micro-pola

Shanu Vashishtha, Abhinav Prakash, Lalitesh Morishetti, Kaushiki Nag

Text-to-image models such as stable diffusion have opened a plethora of opportunities for generating art. Recent literature has surveyed the use of text-to-image models for enhancing the work of many creative artists. Many e-commerce platforms employ a manual process to generate the banners, which is time-consuming and has limitations of scalability. In this

Jiequan Cui, Beier Zhu, Xin Wen, Xiaojuan Qi

In this paper, we present an empirical study on image recognition fairness, i.e., extreme class accuracy disparity on balanced data like ImageNet. We experimentally demonstrate that classes are not equal and the fairness issue is prevalent for image classification models across various datasets, network architectures, and model capacities. Moreover, several

Lei Lyu, Chen Pang, Jihua Wang

Deep neural networks have demonstrated superior performance in artificial intelligence applications, but the opaqueness of their inner working mechanism is one major drawback in their application. The prevailing unit-based interpretation is a statistical observation of stimulus-response data, which fails to show a detailed internal process of inherent mechan

Shu Wang, Jong-Hak Woo, Elena Gallo, Hengxiao Guo

Changing-look (CL) Active Galactic Nuclei (AGNs), characterized by appearance/disappearance of broad emission lines in the span of a few years, present a challenge for the AGN unified model, whereby the Type 1 vs. Type 2 dichotomy results from orientation effects alone. We present a systematic study of a large sample of spectroscopically classified AGNs, usi

Yajun Liu, Beth Andrews

Sequential change-point detection for time series enables us to sequentially check the hypothesis that the model still holds as more and more data are observed. It is widely used in data monitoring in practice. In this work, we consider sequential change-point detection for compositional time series, time series in which the observations are proportions. For

Haoyu Lei, Amin Gohari, Farzan Farnia

Fair supervised learning algorithms assigning labels with little dependence on a sensitive attribute have attracted great attention in the machine learning community. While the demographic parity (DP) notion has been frequently used to measure a model's fairness in training fair classifiers, several studies in the literature suggest potential impacts of enfo

Han Guo, Ramtin Hosseini, Ruiyi Zhang, Sai Ashish Somayajula

Masked Autoencoder (MAE) is a notable method for self-supervised pretraining in visual representation learning. It operates by randomly masking image patches and reconstructing these masked patches using the unmasked ones. A key limitation of MAE lies in its disregard for the varying informativeness of different patches, as it uniformly selects patches to ma

Mengying Jiang, Guizhong Liu, Yuanchao Su, Weiqiang Jin

Most existing methods for predicting drug-drug interactions (DDI) predominantly concentrate on capturing the explicit relationships among drugs, overlooking the valuable implicit correlations present between drug pairs (DPs), which leads to weak predictions. To address this issue, this paper introduces a hierarchical multi-relational graph representation lea

Carlos A. Argüelles, Kareem Farrag, Teppei Katori

The ultra-light dark matter is a new class of dark matter candidates. Unlike traditional dark matter particle candidates, the ultra-light dark matter behaves like a classical field, which saturates the entire Milky Way galaxy with a coherent oscillation. If such dark matter exists and couples with neutrinos, properties of astrophysical neutrinos propagating

Takayuki Goto, Masayoshi Fujihala, Setsuo Mitsuda

NMR study has been performed on an S = 1/2 antiferromagnet KCu6AlBiO4(SO4)5Cl on the square-Kagome lattice, which has three slightly inequivalent nearest-neighbor interactions. Because of the geometrical frustration inherited from triangles within the square kagome lattice and of the low dimensionality, a long range magnetic order is strongly suppressed; its

Ayan Mitra, Isidro Gómez-Vargas, Vasilios Zarikas

In this paper, we present an analysis of Supernova Ia (SNIa) distance moduli $\mu(z)$ and dark energy using an Artificial Neural Network (ANN) reconstruction based on LSST simulated three-year SNIa data. The ANNs employed in this study utilize genetic algorithms for hyperparameter tuning and Monte Carlo Dropout for predictions. Our ANN reconstruction archite

Rasmus Laurvig Haugaard, Yitaek Kim, Thorbjørn Mosekjær Iversen

Calibration of fixtures in robotic work cells is essential but also time consuming and error-prone, and poor calibration can easily lead to wasted debugging time in downstream tasks. Contact-based calibration methods let the user measure points on the fixture's surface with a tool tip attached to the robot's end effector. Most such methods require the user t

Juan Zhang, Jiahao Chen, Cheng Wang, Zhiwang Yu

Despite numerous completed studies, achieving high fidelity talking face generation with highly synchronized lip movements corresponding to arbitrary audio remains a significant challenge in the field. The shortcomings of published studies continue to confuse many researchers. This paper introduces G4G, a generic framework for high fidelity talking face gene

Shaoyang Xu, Weilong Dong, Zishan Guo, Xinwei Wu

Prior research has revealed that certain abstract concepts are linearly represented as directions in the representation space of LLMs, predominantly centered around English. In this paper, we extend this investigation to a multilingual context, with a specific focus on human values-related concepts (i.e., value concepts) due to their significance for AI safe

Zhenbang Feng, Hardhik Mohanty, Bhaskar Krishnamachari

In decentralized finance (DeFi), stablecoins like DAI are designed to offer a stable value amidst the fluctuating nature of cryptocurrencies. We examine the class of crypto-backed stable derivatives, with a focus on mechanisms for price stabilization, which is exemplified by the well-known stablecoin DAI from MakerDAO. For simplicity, we focus on a single-co

Urtzi Buijs, José Carrasquel

In this note we give a characterization of the sectional category of a map between rational spaces in terms of its Koszul-Quillen model.

Haoyu Xie, Changqi Wang, Jian Zhao, Yang Liu

Tremendous breakthroughs have been developed in Semi-Supervised Semantic Segmentation (S4) through contrastive learning. However, due to limited annotations, the guidance on unlabeled images is generated by the model itself, which inevitably exists noise and disturbs the unsupervised training process. To address this issue, we propose a robust contrastive-ba

Vishnu Sarukkai, Lu Yuan, Mia Tang, Maneesh Agrawala

We introduce a novel sketch-to-image tool that aligns with the iterative refinement process of artists. Our tool lets users sketch blocking strokes to coarsely represent the placement and form of objects and detail strokes to refine their shape and silhouettes. We develop a two-pass algorithm for generating high-fidelity images from such sketches at any poin

Yan Zhang, Ming Jia, Meng Li, Jianyu Wang

Operators' cognitive functions are impaired significantly under extreme heat stress, potentially resulting in more severe secondary disasters. This research investigated the impact of elevated temperature and humidity (25 60%RH, 30 70%RH, 35 80%RH, 40 90%RH) on the cognitive functions and performance of operators. Meanwhile, we explored the psychological-phy

Minghan Li, Shuai Li, Xindong Zhang, Lei Zhang

Despite the recent advances in unified image segmentation (IS), developing a unified video segmentation (VS) model remains a challenge. This is mainly because generic category-specified VS tasks need to detect all objects and track them across consecutive frames, while prompt-guided VS tasks require re-identifying the target with visual/text prompts througho

Wanqian Li, Xiaotian Sun, Xinyu Wang, Lei Wang

Processing-in-memory architectures have been regarded as a promising solution for CNN acceleration. Existing PIM accelerator designs rely heavily on the experience of experts and require significant manual design overhead. Manual design cannot effectively optimize and explore architecture implementations. In this work, we develop an automatic framework PIMSY

Sahithya Ravi, Patrick Huber, Akshat Shrivastava, Aditya Sagar

The emergence of Large Language Models (LLMs) has brought to light promising language generation capabilities, particularly in performing tasks like complex reasoning and creative writing. Consequently, distillation through imitation of teacher responses has emerged as a popular technique to transfer knowledge from LLMs to more accessible, Small Language Mod

Zhihao Cao

Functional near-infrared spectroscopy (fNIRS) is a non-invasive technique for monitoring brain activity. To better understand the brain, researchers often use deep learning to address the classification challenges of fNIRS data. Our study shows that while current networks in fNIRS are highly accurate for predictions within their training distribution, they f

Kyudong Choi, In-Jee Jeong, Deokwoo Lim

In this paper, we consider incompressible Euler flows in $ \mathbb{R}^{4} $ under bi-rotational symmetry, namely solutions that are invariant under rotations in $\mathbb{R}^{4}$ fixing either the first two or last two axes. With the additional swirl-free assumption, our first main result gives local wellposedness of Yudovich-type solutions, extending the wor

Koji Nakano

The roulette wheel selection is a critical process in heuristic algorithms, enabling the probabilistic choice of items based on assigned fitness values. It selects an item with a probability proportional to its fitness value. This technique is commonly employed in ant-colony algorithms to randomly determine the next city to visit when solving the traveling s

Qinglin Liu, Xiaoqian Lv, Wei Yu, Changyong Guo

Natural image matting aims to estimate the alpha matte of the foreground from a given image. Various approaches have been explored to address this problem, such as interactive matting methods that use guidance such as click or trimap, and automatic matting methods tailored to specific objects. However, existing matting methods are designed for specific objec

Wei Hong, Wei Liu, Luhan Yang

This paper is devoted to proving the small noise asymptotic behaviour, particularly large deviation principle, for multi-scale stochastic dynamical systems with fully local monotone coefficients driven by multiplicative noise. The main techniques are based on a combination of the weak convergence approach, the time discretization technique and the theory of

HongLin Gong, Mengzhao Jia, Liqiang Jing

In line with the latest research, the task of identifying helpful reviews from a vast pool of user-generated textual and visual data has become a prominent area of study. Effective modal representations are expected to possess two key attributes: consistency and differentiation. Current methods designed for Multimodal Review Helpfulness Prediction (MRHP) fac

Catharine W. K. Lo, José Francisco Rodrigues

We show that the solutions to the nonlocal obstacle problems for the nonlocal $-\Delta_p^s$ operator, when the fractional parameter $s\to\sigma$ for $0<\sigma\leq1$, converge to the solution of the corresponding obstacle problem for $-\Delta_p^\sigma$, being $\sigma=1$ the classical obstacle problem for the local $p$-Laplacian. We discuss the weak stability

Saparya Suresh, Sudheesh K. Kattumannil

The categorical Gini covariance is a dependence measure between a numerical variable and a categorical variable. The Gini covariance measures dependence by quantifying the difference between the conditional and unconditional distributional functions. The categorical Gini covariance equals zero if and only if the numerical variable and the categorical variabl

Tong Liu, Yingjie Zhang, Zhe Zhao, Yinpeng Dong

In recent years, large language models (LLMs) have demonstrated notable success across various tasks, but the trustworthiness of LLMs is still an open problem. One specific threat is the potential to generate toxic or harmful responses. Attackers can craft adversarial prompts that induce harmful responses from LLMs. In this work, we pioneer a theoretical fou

Yichao Wu, Yafei Xiang, Shuning Huo, Yulu Gong

In addressing the computational and memory demands of fine-tuning Large Language Models(LLMs), we propose LoRA-SP(Streamlined Partial Parameter Adaptation), a novel approach utilizing randomized half-selective parameter freezing within the Low-Rank Adaptation(LoRA)framework. This method efficiently balances pre-trained knowledge retention and adaptability fo

Guy Elisha, Sourav Halder, Xinyi Liu, Dustin A. Carlson

An understanding how neurological disorders lead to mechanical dysfunction of the esophagus requires knowledge of the neural circuit of the enteric nervous system. Historically, this has been elusive. Here, we present an empirically guided neural circuit for the esophagus. It has a chain of unidirectionally coupled relaxation oscillators, receiving excitator

Bhargav Ghanekar, Salman Siddique Khan, Pranav Sharma, Shreyas Singh

Passive, compact, single-shot 3D sensing is useful in many application areas such as microscopy, medical imaging, surgical navigation, and autonomous driving where form factor, time, and power constraints can exist. Obtaining RGB-D scene information over a short imaging distance, in an ultra-compact form factor, and in a passive, snapshot manner is challengi

Qiao Wang, Zheng Yuan

In this study, we evaluated the performance of the state-of-the-art sequence tagging grammar error detection and correction model (SeqTagger) using Japanese university students' writing samples. With an automatic annotation toolkit, ERRANT, we first evaluated SeqTagger's performance on error correction with human expert correction as the benchmark. Then a hu

Guy Elisha, Richard Gast, Sourav Halder, Sara A. Solla

Certain biological systems exhibit both direct and retrograde propagating wave signals, despite unidirectional neural coupling. However, there is no model to explain this. Therefore, the underlying physics of reversing the signal's direction for one-way coupling remains unclear. Here, we resolve this issue using a Wilson-Cowan oscillators network. By analyzi

Derong Xu, Ziheng Zhang, Zhihong Zhu, Zhenxi Lin

Model editing aims to precisely alter the behaviors of large language models (LLMs) in relation to specific knowledge, while leaving unrelated knowledge intact. This approach has proven effective in addressing issues of hallucination and outdated information in LLMs. However, the potential of using model editing to modify knowledge in the medical field remai

Song Yang

For each $0<\alpha<\frac{1}{2}$, there exists a Bayer--Lahoz--Macr{\`{\i}}--Stellari inducing Bridgeland stability condition $\sigma(\alpha)$ on a Kuznetsov component $\mathrm{Ku}(Q)$ of the smooth quadric threefold $Q$. We obtain the non-emptiness of the moduli space $M_{\sigma(\alpha)}([\mathcal{P}_{x}])$ of $\sigma(\alpha)$-semistable objects in $\mathrm{

Wen-Xiang Chen

This article investigates the phenomenon of mass inflation and its consequential impact on the stability of Cauchy horizons within the framework of general relativity. Mass inflation, defined by an exponential surge in energy, is pivotal in preserving causality across solutions like the Kerr black hole, ensuring the singular nature of causality-violating reg

June Yong Yang, Byeongwook Kim, Jeongin Bae, Beomseok Kwon

Key-Value (KV) Caching has become an essential technique for accelerating the inference speed and throughput of generative Large Language Models~(LLMs). However, the memory footprint of the KV cache poses a critical bottleneck in LLM deployment as the cache size grows with batch size and sequence length, often surpassing even the size of the model itself. Al

Markus Lohmayer, Giuseppe Capobianco, Sigrid Leyendecker

Multibody dynamics simulation plays an important role in various fields, including mechanical engineering, robotics, and biomechanics. Setting up computational models however becomes increasingly challenging as systems grow in size and complexity. Especially the consistent combination of models across different physical domains usually demands a lot of atten

Chengpin Luo, Brian M. Kurkoski

A coding lattice $\Lambda_c$ and a shaping lattice $\Lambda_s$ forms a nested lattice code $\mathcal{C}$ if $\Lambda_s \subseteq \Lambda_c$. Under some conditions, $\mathcal{C}$ is a finite cyclic group formed by rectangular encoding. This paper presents the conditions for the existence of such $\mathcal{C}$ and provides some designs. These designs correspon