Search

While Multi-Object Tracking (MOT) has made substantial advancements, it is limited by heavy reliance on prior knowledge and limited to predefined categories. In contrast, Generic Multiple Object Tracking (GMOT), tracking multiple objects with similar appearance, requires less prior information about the targets but faces challenges with variants like viewpoint, lighting, occlusion, and resolution. Our contributions commence with the introduction of the \textbf{\text{Refer-GMOT dataset}} a collection of videos, each accompanied by fine-grained textual descriptions of their attributes. Subsequently, we introduce a novel text prompt-based open-vocabulary GMOT framework, called \textbf{\text{TP-GMOT}}, which can track never-seen object categories with zero training examples. Within \text{TP-GMOT} framework, we introduce two novel components: (i) {\textbf{\text{TP-OD}}, an object detection by a textual prompt}, for accurately detecting unseen objects with specific characteristics. (ii) Motion-Appearance Cost SORT \textbf{\text{MAC-SORT}}, a novel object association approach that adeptly integrates motion and appearance-based matching strategies to tackle the complex task of tracking multiple generic objects with high similarity. Our contributions are benchmarked on the \text{Refer-GMOT} dataset for GMOT task. Additionally, to assess the generalizability of the proposed \text{TP-GMOT} framework and the effectiveness of \text{MAC-SORT} tracker, we conduct ablation studies on the DanceTrack and MOT20 datasets for the MOT task. Our dataset, code, and models will be publicly available at: https://fsoft-aic.github.io/TP-GMOT

(abridged) Together with gravity, turbulence, and stellar feedback, magnetic fields (B-fields) are thought to play a critical role in the evolution of molecular clouds and star formation processes. We aim to map the morphology and measure the strength of B-fields of the nearby molecular cloud, rho Ophiuchus-A ($\rho$ Oph-A), and then to understand the role of B-fields in regulating star formation and shaping the cloud. We have analyzed the far-infrared (FIR) polarization of thermal dust emission observed by SOFIA/HAWC$+$ at 89 and 154 $\mu$m toward the densest part of $\rho$ Oph-A, which is irradiated by the nearby B3/4 star, Oph-S1. The cloud exhibits well-ordered B-fields with magnetic orientations mainly perpendicular to the ridge of the cloud toward the densest region and B-field strengths are in the range of 0.2-2.5 mG, using the Davis-Chandrasekhar-Fermi method. The B-fields are strongest at the densest part of the cloud, which is associated with the starless core SM1, and decreases toward the outskirts of the cloud. By calculating the map of the mass-to-flux ratio, Alfv\'en Mach number, and plasma $\beta$ parameter in $\rho$ Oph-A, we find that the cloud is predominantly magnetically sub-critical, sub-Alfv\'enic, which implies that the cloud is supported by strong B-fields that dominate over gravity, turbulence, and thermal gas energy. Measured B-field strengths at two densest subregions using other methods that account for the compressible mode are relatively lower than that measured with the DCF method but do not significantly change our conclusions on the roles of B-fields relative to gravity and turbulence on star formation. A virial analysis suggests that the cloud is gravitationally unbound. We find that B-fields are sufficiently strong to support the cloud against radiative feedback and to regulate the shape of the cloud., Comment: Accepted to A&A

In this report, we introduce Vintern-1B, a reliable 1-billion-parameters multimodal large language model (MLLM) for Vietnamese language tasks. By integrating the Qwen2-0.5B-Instruct language model with the InternViT-300M-448px visual model, Vintern-1B is optimized for a range of applications, including optical character recognition (OCR), document extraction, and general question-answering in Vietnamese context. The model is fine-tuned on an extensive dataset of over 3 million image-question-answer pairs, achieving robust performance and reliable results across multiple Vietnamese language benchmarks like OpenViVQA and ViTextVQA. Vintern-1B is small enough to fit into various on-device applications easily. Additionally, we have open-sourced several Vietnamese vision question answering (VQA) datasets for text and diagrams, created with Gemini 1.5 Flash. Our models are available at: https://huggingface.co/5CD-AI/Vintern-1B-v2.

Creating soft-Coulomb-type (SC) molecular potential within single-active-electron approximation (SAE) is essential since it allows solving time-dependent Schr\"odinger equations with fewer computational resources compared to other multielectron methods. The current available SC potentials can accurately reproduce the energy of the highest occupied molecular orbital (HOMO), which is sufficient for analyzing nonlinear effects in laser-molecule interactions like high-order harmonic generation (HHG). However, recent discoveries of significant effects of deep-lying molecular orbitals call for more precise potentials to analyze them. In this study, we present a fast and accurate method based on machine learning to construct SC potentials that simultaneously reproduce various molecular features, including energies, symmetries, and dipole moments of HOMO, HOMO-1, and HOMO-2. We use this ML model to create SC SAE potentials of the HCN molecule and then comprehensively analyze the fingerprints of lower-lying orbitals in HHG spectra emitted during the H-CN stretching. Our findings reveal that HOMO-1 plays a role in forming the second HHG plateau. Additionally, as the H-C distance increases, the plateau structure and the smoothness of HHG spectra are altered due to the redistribution of orbital electron density. These results are in line with other experimental and theoretical studies. Lastly, the machine learning approach using deconvolution and convolution neural networks in the present study is so general that it can be applied to construct molecular potential for other molecules and molecular dynamic processes.

Bundle recommendation aims to enhance business profitability and user convenience by suggesting a set of interconnected items. In real-world scenarios, leveraging the impact of asymmetric item affiliations is crucial for effective bundle modeling and understanding user preferences. To address this, we present BunCa, a novel bundle recommendation approach employing item-level causation-enhanced multi-view learning. BunCa provides comprehensive representations of users and bundles through two views: the Coherent View, leveraging the Multi-Prospect Causation Network for causation-sensitive relations among items, and the Cohesive View, employing LightGCN for information propagation among users and bundles. Modeling user preferences and bundle construction combined from both views ensures rigorous cohesion in direct user-bundle interactions through the Cohesive View and captures explicit intents through the Coherent View. Simultaneously, the integration of concrete and discrete contrastive learning optimizes the consistency and self-discrimination of multi-view representations. Extensive experiments with BunCa on three benchmark datasets demonstrate the effectiveness of this novel research and validate our hypothesis.

We address the problem of offline learning a policy that avoids undesirable demonstrations. Unlike conventional offline imitation learning approaches that aim to imitate expert or near-optimal demonstrations, our setting involves avoiding undesirable behavior (specified using undesirable demonstrations). To tackle this problem, unlike standard imitation learning where the aim is to minimize the distance between learning policy and expert demonstrations, we formulate the learning task as maximizing a statistical distance, in the space of state-action stationary distributions, between the learning policy and the undesirable policy. This significantly different approach results in a novel training objective that necessitates a new algorithm to address it. Our algorithm, UNIQ, tackles these challenges by building on the inverse Q-learning framework, framing the learning problem as a cooperative (non-adversarial) task. We then demonstrate how to efficiently leverage unlabeled data for practical training. Our method is evaluated on standard benchmark environments, where it consistently outperforms state-of-the-art baselines. The code implementation can be accessed at: https://github.com/hmhuy0/UNIQ.

We present multi-epoch optical spectropolarimetric and imaging polarimetric observations of the nearby Type II supernova (SN) 2023ixf discovered in M101 at a distance of 6.85 Mpc. The first imaging polarimetric observations were taken +2.33 days (60085.08 MJD) after the explosion, while the last imaging polarimetric data points (+73.19 and +76.19 days) were acquired after the fall from the light curve plateau. At +2.33 days there is strong evidence of circumstellar material (CSM) interaction in the spectra and the light curve. A significant level of polarization $P_r = 0.88\pm 0.06 \% $ seen during this phase indicates that this CSM is aspherical. We find that the polarization evolves with time toward the interstellar polarization level ($0.35\%$) during the photospheric phase, which suggests that the recombination photosphere is spherically symmetric. There is a jump in polarization ($P_r =0.65 \pm 0.08 \% $) at +73.19 days when the light curve falls from the plateau. This is a phase where polarimetric data is sensitive to non-spherical inner ejecta or a decrease in optical depth into the single scattering regime. We also present spectropolarimetric data that reveal line (de)polarization during most of the observed epochs. In addition, at +14.50 days we see an "inverse P Cygn" profile in the H and He line polarization, which clearly indicates the presence of asymmetrically distributed material overlying the photosphere. The overall temporal evolution of polarization is typical for Type II SNe, but the high level of polarization during the rising phase has only been observed in SN 2023ixf., Comment: 14 pages, 7 figures, submitted to ApJL, comments welcome

We explore a robust version of the barycenter problem among $n$ centered Gaussian probability measures, termed Semi-Unbalanced Optimal Transport (SUOT)-based Barycenter, wherein the barycenter remains fixed while the others are relaxed using Kullback-Leibler divergence. We develop optimization algorithms on Bures-Wasserstein manifold, named the Exact Geodesic Gradient Descent and Hybrid Gradient Descent algorithms. While the Exact Geodesic Gradient Descent method is based on computing the exact closed form of the first-order derivative of the objective function of the barycenter along a geodesic on the Bures manifold, the Hybrid Gradient Descent method utilizes optimizer components when solving the SUOT problem to replace outlier measures before applying the Riemannian Gradient Descent. We establish the theoretical convergence guarantees for both methods and demonstrate that the Exact Geodesic Gradient Descent algorithm attains a dimension-free convergence rate. Finally, we conduct experiments to compare the normal Wasserstein Barycenter with ours and perform an ablation study., Comment: Ngoc-Hai Nguyen and Dung Le contributed equally to this work. 44 pages, 5 figures

We propose a quantitative direct method of proving the local stability for the trivial solution of a rough differential equation and of its regular discretization scheme. Using Doss-Sussmann technique and stopping time analysis, we prove that the trivial solution of the rough system is exponentially stable as long as the noise is small. The same conclusions hold for the regular discretization scheme with small noise and small step size. Our results are significantly stronger than \cite[Theorem 14]{garrido-atienzaetal} and \cite[Theorem 18]{GABSch18} and can be applied to non-flat bounded or linear noises.

Recent advances in supercontinuum light generation have been remarkable, particularly in the context of highly nonlinear photonic integrated waveguides. In this study, we thoroughly investigate supercontinuum (SC) generation in high-index doped silica glass integrated waveguides, exploring various femtosecond pumping wavelengths and input polarization states. We demonstrate broadband SC generation spanning from 700 nm to 2400 nm when pumping within the anomalous dispersion regime at 1200 nm, 1300 nm, and 1550 nm. In contrast, pumping within the normal dispersion regime at 1000 nm results in narrower SC spectra, primarily due to coherent nonlinear effects such as self-phase modulation and optical wave breaking. Additionally, we examine the impact of TE/TM polarization modes on SC generation, shedding light on the polarization-dependent characteristics of the broadening process. Moreover, Raman scattering measurements reveal the emergence of two new peaks at 48.8 THz and 75.1 THz in the Raman gain curve. Our experimental results are supported by numerical simulations based on a generalized nonlinear Schrodinger equation that incorporates the new Raman gain contribution. Finally, relative intensity noise measurements conducted using the dispersive Fourier transform technique indicate excellent stability of the generated SC spectra., Comment: 21 pages, 13 figures

Grasping a variety of objects remains a key challenge in the development of versatile robotic systems. The human hand is remarkably dexterous, capable of grasping and manipulating objects with diverse shapes, mechanical properties, and textures. Inspired by how humans use two fingers to pick up thin and large objects such as fabric or sheets of paper, we aim to develop a gripper optimized for grasping such deformable objects. Observing how the soft and flexible fingertip joints of the hand approach and grasp thin materials, a hybrid gripper design that incorporates both soft and rigid components was proposed. The gripper utilizes a soft pneumatic ring wrapped around a rigid revolute joint to create a flexible two-fingered gripper. Experiments were conducted to characterize and evaluate the gripper performance in handling sheets of paper and other objects. Compared to rigid grippers, the proposed design improves grasping efficiency and reduces the gripping distance by up to eightfold.

Current evaluation practices in speech-driven gesture generation lack standardisation and focus on aspects that are easy to measure over aspects that actually matter. This leads to a situation where it is impossible to know what is the state of the art, or to know which method works better for which purpose when comparing two publications. In this position paper, we review and give details on issues with existing gesture-generation evaluation, and present a novel proposal for remedying them. Specifically, we announce an upcoming living leaderboard to benchmark progress in conversational motion synthesis. Unlike earlier gesture-generation challenges, the leaderboard will be updated with large-scale user studies of new gesture-generation systems multiple times per year, and systems on the leaderboard can be submitted to any publication venue that their authors prefer. By evolving the leaderboard evaluation data and tasks over time, the effort can keep driving progress towards the most important end goals identified by the community. We actively seek community involvement across the entire evaluation pipeline: from data and tasks for the evaluation, via tooling, to the systems evaluated. In other words, our proposal will not only make it easier for researchers to perform good evaluations, but their collective input and contributions will also help drive the future of gesture-generation research., Comment: 15 pages, 2 figures, project page: https://genea-workshop.github.io/leaderboard/

Designing neural network architectures that can handle data symmetry is crucial. This is especially important for geometric graphs whose properties are equivariance under Euclidean transformations. Current equivariant graph neural networks (EGNNs), particularly those using message passing, have a limitation in expressive power. Recent high-order graph neural networks can overcome this limitation, yet they lack equivariance properties, representing a notable drawback in certain applications in chemistry and physical sciences. In this paper, we introduce the Clifford Group Equivariant Graph Neural Networks (CG-EGNNs), a novel EGNN that enhances high-order message passing by integrating high-order local structures in the context of Clifford algebras. As a key benefit of using Clifford algebras, CG-EGNN can learn functions that capture equivariance from positional features. By adopting the high-order message passing mechanism, CG-EGNN gains richer information from neighbors, thus improving model performance. Furthermore, we establish the universality property of the $k$-hop message passing framework, showcasing greater expressive power of CG-EGNNs with additional $k$-hop message passing mechanism. We empirically validate that CG-EGNNs outperform previous methods on various benchmarks including n-body, CMU motion capture, and MD17, highlighting their effectiveness in geometric deep learning.

Neural Functional Networks (NFNs) have gained increasing interest due to their wide range of applications, including extracting information from implicit representations of data, editing network weights, and evaluating policies. A key design principle of NFNs is their adherence to the permutation and scaling symmetries inherent in the connectionist structure of the input neural networks. Recent NFNs have been proposed with permutation and scaling equivariance based on either graph-based message-passing mechanisms or parameter-sharing mechanisms. However, graph-based equivariant NFNs suffer from high memory consumption and long running times. On the other hand, parameter-sharing-based NFNs built upon equivariant linear layers exhibit lower memory consumption and faster running time, yet their expressivity is limited due to the large size of the symmetric group of the input neural networks. The challenge of designing a permutation and scaling equivariant NFN that maintains low memory consumption and running time while preserving expressivity remains unresolved. In this paper, we propose a novel solution with the development of MAGEP-NFN (Monomial mAtrix Group Equivariant Polynomial NFN). Our approach follows the parameter-sharing mechanism but differs from previous works by constructing a nonlinear equivariant layer represented as a polynomial in the input weights. This polynomial formulation enables us to incorporate additional relationships between weights from different input hidden layers, enhancing the model's expressivity while keeping memory consumption and running time low, thereby addressing the aforementioned challenge. We provide empirical evidence demonstrating that MAGEP-NFN achieves competitive performance and efficiency compared to existing baselines.

This paper systematically explores neural functional networks (NFN) for transformer architectures. NFN are specialized neural networks that treat the weights, gradients, or sparsity patterns of a deep neural network (DNN) as input data and have proven valuable for tasks such as learnable optimizers, implicit data representations, and weight editing. While NFN have been extensively developed for MLP and CNN, no prior work has addressed their design for transformers, despite the importance of transformers in modern deep learning. This paper aims to address this gap by providing a systematic study of NFN for transformers. We first determine the maximal symmetric group of the weights in a multi-head attention module as well as a necessary and sufficient condition under which two sets of hyperparameters of the multi-head attention module define the same function. We then define the weight space of transformer architectures and its associated group action, which leads to the design principles for NFN in transformers. Based on these, we introduce Transformer-NFN, an NFN that is equivariant under this group action. Additionally, we release a dataset of more than 125,000 Transformers model checkpoints trained on two datasets with two different tasks, providing a benchmark for evaluating Transformer-NFN and encouraging further research on transformer training and performance.

Large language models (LLMs) have achieved remarkable success across various NLP tasks, yet their focus has predominantly been on English due to English-centric pre-training and limited multilingual data. While some multilingual LLMs claim to support for hundreds of languages, models often fail to provide high-quality response for mid- and low-resource languages, leading to imbalanced performance heavily skewed in favor of high-resource languages like English and Chinese. In this paper, we prioritize quality over scaling number of languages, with a focus on multilingual machine translation task, and introduce X-ALMA, a model designed with a commitment to ensuring top-tier performance across 50 diverse languages, regardless of their resource levels. X-ALMA surpasses state-of-the-art open-source multilingual LLMs, such as Aya-101 and Aya-23, in every single translation direction on the FLORES and WMT'23 test datasets according to COMET-22. This is achieved by plug-and-play language-specific module architecture to prevent language conflicts during training and a carefully designed training regimen with novel optimization methods to maximize the translation performance. At the final stage of training regimen, our proposed Adaptive Rejection Preference Optimization (ARPO) surpasses existing preference optimization methods in translation tasks.

Federated Learning (FL) is a method for training machine learning models using distributed data sources. It ensures privacy by allowing clients to collaboratively learn a shared global model while storing their data locally. However, a significant challenge arises when dealing with missing modalities in clients' datasets, where certain features or modalities are unavailable or incomplete, leading to heterogeneous data distribution. While previous studies have addressed the issue of complete-modality missing, they fail to tackle partial-modality missing on account of severe heterogeneity among clients at an instance level, where the pattern of missing data can vary significantly from one sample to another. To tackle this challenge, this study proposes a novel framework named FedMAC, designed to address multi-modality missing under conditions of partial-modality missing in FL. Additionally, to avoid trivial aggregation of multi-modal features, we introduce contrastive-based regularization to impose additional constraints on the latent representation space. The experimental results demonstrate the effectiveness of FedMAC across various client configurations with statistical heterogeneity, outperforming baseline methods by up to 26% in severe missing scenarios, highlighting its potential as a solution for the challenge of partially missing modalities in federated systems., Comment: The 22nd International Symposium on Network Computing and Applications (NCA 2024)

Federated Learning (FL) has emerged as a powerful paradigm for training machine learning models in a decentralized manner, preserving data privacy by keeping local data on clients. However, evaluating the robustness of these models against data perturbations on clients remains a significant challenge. Previous studies have assessed the effectiveness of models in centralized training based on certified accuracy, which guarantees that a certain percentage of the model's predictions will remain correct even if the input data is perturbed. However, the challenge of extending these evaluations to FL remains unresolved due to the unknown client's local data. To tackle this challenge, this study proposed a method named FedCert to take the first step toward evaluating the robustness of FL systems. The proposed method is designed to approximate the certified accuracy of a global model based on the certified accuracy and class distribution of each client. Additionally, considering the Non-Independent and Identically Distributed (Non-IID) nature of data in real-world scenarios, we introduce the client grouping algorithm to ensure reliable certified accuracy during the aggregation step of the approximation algorithm. Through theoretical analysis, we demonstrate the effectiveness of FedCert in assessing the robustness and reliability of FL systems. Moreover, experimental results on the CIFAR-10 and CIFAR-100 datasets under various scenarios show that FedCert consistently reduces the estimation error compared to baseline methods. This study offers a solution for evaluating the robustness of FL systems and lays the groundwork for future research to enhance the dependability of decentralized learning. The source code is available at https://github.com/thanhhff/FedCert/., Comment: The 22nd International Symposium on Network Computing and Applications (NCA 2024)

The main theme of this paper is to give sufficient conditions for the weighted boundedness of the bilinear fractional integral operator $\mathsf{BI}_\al$. The proposed condition involves the union of multilinear Muckenhoupt-type conditions. We have achieved new results in an unknown case and remarkably improved other known results by utilizing the hidden convolution nature inside the operator. We also study the effects of the general product commutators on the main operator and the weighted estimates for a related maximal operator that norm-wise dominates the main operator.

State-of-the-art medical multi-modal large language models (med-MLLM), like LLaVA-Med or BioMedGPT, leverage instruction-following data in pre-training. However, those models primarily focus on scaling the model size and data volume to boost performance while mainly relying on the autoregressive learning objectives. Surprisingly, we reveal that such learning schemes might result in a weak alignment between vision and language modalities, making these models highly reliant on extensive pre-training datasets - a significant challenge in medical domains due to the expensive and time-consuming nature of curating high-quality instruction-following instances. We address this with LoGra-Med, a new multi-graph alignment algorithm that enforces triplet correlations across image modalities, conversation-based descriptions, and extended captions. This helps the model capture contextual meaning, handle linguistic variability, and build cross-modal associations between visuals and text. To scale our approach, we designed an efficient end-to-end learning scheme using black-box gradient estimation, enabling faster LLaMa 7B training. Our results show LoGra-Med matches LLAVA-Med performance on 600K image-text pairs for Medical VQA and significantly outperforms it when trained on 10% of the data. For example, on VQA-RAD, we exceed LLAVA-Med by 20.13% and nearly match the 100% pre-training score (72.52% vs. 72.64%). We also surpass SOTA methods like BiomedGPT on visual chatbots and RadFM on zero-shot image classification with VQA, highlighting the effectiveness of multi-graph alignment., Comment: First version, fixed typo

Optimization in the Bures-Wasserstein space has been gaining popularity in the machine learning community since it draws connections between variational inference and Wasserstein gradient flows. The variational inference objective function of Kullback-Leibler divergence can be written as the sum of the negative entropy and the potential energy, making forward-backward Euler the method of choice. Notably, the backward step admits a closed-form solution in this case, facilitating the practicality of the scheme. However, the forward step is no longer exact since the Bures-Wasserstein gradient of the potential energy involves "intractable" expectations. Recent approaches propose using the Monte Carlo method -- in practice a single-sample estimator -- to approximate these terms, resulting in high variance and poor performance. We propose a novel variance-reduced estimator based on the principle of control variates. We theoretically show that this estimator has a smaller variance than the Monte-Carlo estimator in scenarios of interest. We also prove that variance reduction helps improve the optimization bounds of the current analysis. We demonstrate that the proposed estimator gains order-of-magnitude improvements over the previous Bures-Wasserstein methods.

Low-energy spin-polarized electrons (SPEs) are thought to cause symmetry breaking and could explain the origin of homochirality of prebiotic molecules such as amino acids and sugars. Here we study the effect of cosmic rays (CRs) on the emission of SPEs from aligned grains in dense protostellar environments and explore the SPE effects on chiral asymmetry of prebiotic molecules. We first show that icy grains in protostellar environments can align with magnetic fields due to magnetically enhanced radiative torque mechanism. We then study the production of thermal electrons by CR ionization of the H$_2$ gas and the CR-induced UV radiation using the attenuated CR spectra in dense cores obtained from a continous slowing down model. Next, we show that thermal electrons with initial random spins captured by aligned grains will quickly become spin-polarized due to the Barnett effect, converting unpolarized incident electrons into SPEs. We calculate the rate of photoemission of such SPEs by CRs-induced UV radiation and secondary electron emission from aligned grains and find that the photoemission by CRs-induced UV radiation is dominant. Finally, we calculate the total production rate of SPEs inside aligned dust grains by CRs. Low-energy secondary SPEs from aligned grains induced by CRs would cause the chiral asymmetry of chiral prebiotic molecules formed in the ice mantle of aligned grains, in analogous to UV circularly polarized light. We propose that amino acids and sugars of chiral assymmetry detected in meteorite/asteroids/comets might be formed in the ice mantle of grains under the irradiation of SPEs released from aligned grains by CRs in protostellar environments., Comment: 22 pages, 8 figures. To be submitted, comments welcome

Nonlinear parabolic equations are central to numerous applications in science and engineering, posing significant challenges for analytical solutions and necessitating efficient numerical methods. Exponential integrators have recently gained attention for handling stiff differential equations. This paper explores exponential Runge--Kutta methods for solving such equations, focusing on the simplified form $u^{\prime}(t)+A u(t)=B u(t)$, where $A$ generates an analytic semigroup and $B$ is relatively bounded with respect to $A$. By treating $A$ exactly and $B$ explicitly, we derive error bounds for exponential Runge--Kutta methods up to third order. Our analysis shows that these methods maintain their order under mild regularity conditions on the initial data $u_0$, while also addressing the phenomenon of order reduction in higher-order methods. Through a careful convergence analysis and numerical investigations, this study provides a comprehensive understanding of the applicability and limitations of exponential Runge--Kutta methods in solving linear parabolic equations involving two unbounded and non-commuting operators., Comment: 24 pages, 4 figures

Automatic polyp segmentation is crucial for effective diagnosis and treatment in colonoscopy images. Traditional methods encounter significant challenges in accurately delineating polyps due to limitations in feature representation and the handling of variability in polyp appearance. Deep learning techniques, including CNN and Transformer-based methods, have been explored to improve polyp segmentation accuracy. However, existing approaches often neglect additional semantics, restricting their ability to acquire adequate contexts of polyps in colonoscopy images. In this paper, we propose an innovative method named ``Automatic Polyp Segmentation with Self-Enriched Semantic Model'' to address these limitations. First, we extract a sequence of features from an input image and decode high-level features to generate an initial segmentation mask. Using the proposed self-enriched semantic module, we query potential semantics and augment deep features with additional semantics, thereby aiding the model in understanding context more effectively. Extensive experiments show superior segmentation performance of the proposed method against state-of-the-art polyp segmentation baselines across five polyp benchmarks in both superior learning and generalization capabilities., Comment: Asian Conference on Computer Vision 2024

Few-shot Continual Relations Extraction (FCRE) is an emerging and dynamic area of study where models can sequentially integrate knowledge from new relations with limited labeled data while circumventing catastrophic forgetting and preserving prior knowledge from pre-trained backbones. In this work, we introduce a novel method that leverages often-discarded language model heads. By employing these components via a mutual information maximization strategy, our approach helps maintain prior knowledge from the pre-trained backbone and strategically aligns the primary classification head, thereby enhancing model performance. Furthermore, we explore the potential of Large Language Models (LLMs), renowned for their wealth of knowledge, in addressing FCRE challenges. Our comprehensive experimental results underscore the efficacy of the proposed method and offer valuable insights for future work., Comment: Accepted to EMNLP 2024

This study introduces an innovative automatic labeling framework to address the challenges of lexical normalization in social media texts for low-resource languages like Vietnamese. Social media data is rich and diverse, but the evolving and varied language used in these contexts makes manual labeling labor-intensive and expensive. To tackle these issues, we propose a framework that integrates semi-supervised learning with weak supervision techniques. This approach enhances the quality of training dataset and expands its size while minimizing manual labeling efforts. Our framework automatically labels raw data, converting non-standard vocabulary into standardized forms, thereby improving the accuracy and consistency of the training data. Experimental results demonstrate the effectiveness of our weak supervision framework in normalizing Vietnamese text, especially when utilizing Pre-trained Language Models. The proposed framework achieves an impressive F1-score of 82.72% and maintains vocabulary integrity with an accuracy of up to 99.22%. Additionally, it effectively handles undiacritized text under various conditions. This framework significantly enhances natural language normalization quality and improves the accuracy of various NLP tasks, leading to an average accuracy increase of 1-3%.

Two-dimensional (2D) semiconductors are promising for low-power complementary metal oxide semiconductor (CMOS) electronics, which require ultrathin n- and p-type transistor channels. Among 2D semiconductors, WS2 is expected to have good conduction for both electrons and holes, but p-type WS2 transistors have been difficult to realize due to the relatively deep valence band and the presence of mid-gap states with conventional metal contacts. Here, we report topological semimetal NbP as p-type electrical contacts to bilayer WS2 with up to 5.8 microamperes per micron hole current at room temperature; this is the highest to date for sub 2 nm thin WS2 and more than 50 times larger than with metals like Ni or Pd. The p-type conduction is enabled by the simultaneously high work function and low density of states of the NbP, which reduce Fermi level pinning. These contacts are sputter-deposited at room temperature, an approach compatible with CMOS fabrication, a step towards enabling ultrathin WS2 semiconductors in future nanoelectronics.

URIEL is a knowledge base offering geographical, phylogenetic, and typological vector representations for 7970 languages. It includes distance measures between these vectors for 4005 languages, which are accessible via the lang2vec tool. Despite being frequently cited, URIEL is limited in terms of linguistic inclusion and overall usability. To tackle these challenges, we introduce URIEL+, an enhanced version of URIEL and lang2vec addressing these limitations. In addition to expanding typological feature coverage for 2898 languages, URIEL+ improves user experience with robust, customizable distance calculations to better suit the needs of the users. These upgrades also offer competitive performance on downstream tasks and provide distances that better align with linguistic distance studies.

Centralized social networks have experienced a transformative impact on our digital era communication, connection, and information-sharing information. However, it has also raised significant concerns regarding users' privacy and individual rights. In response to these concerns, this paper proposes a novel Decentralized Social Network employing Blockchain technology and Decentralized Storage Networks completed by Access Control Smart Contracts. The initial phase comprises a comprehensive literature review, delving into decentralized social networks, explaining the review methodology, and presenting the resulting findings. Building upon these findings and an analysis of previous research gaps, we propose a novel architecture for decentralized social networks. In conclusion, the principal results highlight the benefit of our decentralized social network to protect user privacy. Moreover, the users have all rights to their posted information following the General Data Protection Regulation (GDPR).

We completely determine the depth and regularity of symbolic powers of the fiber product of two homogeneous ideals in disjoint sets of variables, given knowledge of the symbolic powers of each factor. Generalizing previous joint work with Vu, we provide exact, characteristic-independent formulas for the depth and regularity of ordinary powers of such fiber products.

This paper advances the understanding of how the size of a machine learning model affects its vulnerability to poisoning, despite state-of-the-art defenses. Given isotropic random honest feature vectors and the geometric median (or clipped mean) as the robust gradient aggregator rule, we essentially prove that, perhaps surprisingly, linear and logistic regressions with $D \geq 169 H^2/P^2$ parameters are subject to arbitrary model manipulation by poisoners, where $H$ and $P$ are the numbers of honestly labeled and poisoned data points used for training. Our experiments go on exposing a fundamental tradeoff between augmenting model expressivity and increasing the poisoners' attack surface, on both synthetic data, and on MNIST & FashionMNIST data for linear classifiers with random features. We also discuss potential implications for source-based learning and neural nets., Comment: 29 pages, 3 figures

Ego-velocity estimation from point cloud measurements of a millimeter-wave frequency-modulated continuous wave (mmWave FMCW) radar has become a crucial component of radar-inertial odometry (RIO) systems. Conventional approaches often perform poorly when the number of point cloud outliers exceeds that of inliers. In this paper, we propose CREVE, an acceleration-based inequality constraints filter that leverages additional measurements from an inertial measurement unit (IMU) to achieve robust ego-velocity estimations. To further enhance accuracy and robustness against sensor errors, we introduce a practical accelerometer bias estimation method and a parameter adaptation rule. The effectiveness of the proposed method is evaluated using five open-source drone datasets. Experimental results demonstrate that our algorithm significantly outperforms three existing state-of-the-art methods, achieving reductions in absolute trajectory error of approximately 53%, 84%, and 35% compared to them., Comment: 7 pages, conference

In this work, we present a numerical method that provides accurate real-time detection for the widths of the fractures in a fractured porous medium based on observational data on porous medium fluid mass and velocity. To achieve this task, an inverse problem is formulated by first constructing a forward formulation based on the reduced fracture model of the diffusion equation. A parameter estimation problem is then performed online by utilizing a direct filter method. Numerical experiments are carried out to demonstrate the accuracy of our method in approximating the target parameters.

Reinforcement Learning (RL) has been shown to be effective and convenient for a number of tasks in robotics. However, it requires the exploration of a sufficiently large number of state-action pairs, many of which may be unsafe or unimportant. For instance, online model-free learning can be hazardous and inefficient in the absence of guarantees that a certain set of desired states will be reached during an episode. An increasingly common approach to address safety involves the addition of a shielding system that constrains the RL actions to a safe set of actions. In turn, a difficulty for such frameworks is how to effectively couple RL with the shielding system to make sure the exploration is not excessively restricted. This work presents a novel safe model-free RL agent called Critic As Lyapunov Function (CALF) and showcases how CALF can be used to improve upon control baselines in robotics in an efficient and convenient fashion while ensuring guarantees of stable goal reaching. The latter is a crucial part of safety, as seen generally. With CALF all state-action pairs remain explorable and yet reaching of desired goal states is formally guaranteed. Formal analysis is provided that shows the goal stabilization-ensuring properties of CALF and a set of real-world and numerical experiments with a non-holonomic wheeled mobile robot (WMR) TurtleBot3 Burger confirmed the superiority of CALF over such a well-established RL agent as proximal policy optimization (PPO), and a modified version of SARSA in a few-episode setting in terms of attained total cost.

Grasp detection is a fundamental robotic task critical to the success of many industrial applications. However, current language-driven models for this task often struggle with cluttered images, lengthy textual descriptions, or slow inference speed. We introduce GraspMamba, a new language-driven grasp detection method that employs hierarchical feature fusion with Mamba vision to tackle these challenges. By leveraging rich visual features of the Mamba-based backbone alongside textual information, our approach effectively enhances the fusion of multimodal features. GraspMamba represents the first Mamba-based grasp detection model to extract vision and language features at multiple scales, delivering robust performance and rapid inference time. Intensive experiments show that GraspMamba outperforms recent methods by a clear margin. We validate our approach through real-world robotic experiments, highlighting its fast inference speed., Comment: 8 pages. Project page: https://airvlab.github.io/grasp-anything/

Let $G$ be $Sp_{2n}$, $SO_{2n}$ or $SO_{2n+1}$ and let $G^\vee$ be its Langlands dual group. Barbash and Vogan based on earlier work of Lusztig and Spaltenstein, define a duality map $D$ that sends nilpotent orbits $\mathbb{O}_{e^\vee} \subset \mathfrak{g}^\vee$ to special nilpotent orbits $\mathbb{O}_e\subset \mathfrak{g}$. In a work by Losev, Mason-Brown and Matvieievskyi, an upgraded version $\tilde{D}$ of this duality is considered, called the refined BVLS duality. $\tilde{D}(\mathbb{O}_{e^\vee})$ is a $G$-equivariant cover $\tilde{\mathbb{O}}_e$ of $\mathbb{O}_e$. Let $S_{{e^\vee}}$ be the nilpotent Slodowy slice of the orbit $\mathbb{O}_{e^\vee}$. The two varieties $X^\vee= S_{e^\vee}$ and $X=$ Spec$(\mathbb{C}[\tilde{\mathbb{O}}_e])$ are expected to be symplectic dual to each other. In this context, a version of the Hikita conjecture predicts an isomorphism between the cohomology ring of the Springer fiber $\mathcal{B}_{e^\vee}$ and the ring of regular functions on the scheme-theoretic fixed point $X^T$ for some torus $T$. This paper verifies the isomorphism for certain pairs $e$ and $e^\vee$. These cases are expected to cover almost all instances in which the Hikita conjecture holds when $e^\vee$ regular in a Levi $\mathfrak{l}^\vee\subset \mathfrak{g}^\vee$. Our results in these cases follow from the relations of three different types of objects: generalized coinvariant algebras, equivariant cohomology rings, and functions on scheme-theoretic intersections. We also give evidence for the Hikita conjecture when $e^\vee$ is distinguished.

This paper proposes a model predictive controller for discrete-time linear systems with additive, possibly unbounded, stochastic disturbances and subject to chance constraints. By computing a polytopic probabilistic positively invariant set for constraint tightening with the help of the computation of the minimal robust positively invariant set, the chance constraints are guaranteed, assuming only the mean and covariance of the disturbance distribution are given. The resulting online optimization problem is a standard strictly quadratic programming, just like in conventional model predictive control with recursive feasibility and stability guarantees and is simple to implement. A numerical example is provided to illustrate the proposed method., Comment: This paper was accepted for publication in CDC 2024

The differences in H2O2 production between conventional (CONV) and ultra-high dose rate (UHDR) irradiations in water radiolysis are still not fully understood. The lower levels of this radiolytic species, as a critical end product of water radiolysis, are particularly relevant for investigating the connection between the high-density energy deposition during short-duration physical events (ionizations or excitations) and biological responses of the FLASH effect. In this study, we developed a new Geant4-DNA chemistry model to simulate radiolysis considering the time structure of the irradiation pulse at different absorbed doses to liquid water of 0.01, 0.1, 1, and 2 Gy under 1 MeV electron irradiation. The model allows the description of the beam's temporal structure, including the pulse duration, the pulse repetition frequency, and the pulse amplitude for the different beam irradiation conditions through a wide dose rate range, from 0.01 Gy/s up to about 105 Gy/s, at various oxygen concentrations. The preliminary results indicate a correlation between the temporal structure of the pulses and a significant reduction in the production of reactive oxygen species (ROS) at different dose rates., Comment: 27 pages, 14 figures including 3 figures in appendix

Neural functional networks (NFNs) have recently gained significant attention due to their diverse applications, ranging from predicting network generalization and network editing to classifying implicit neural representation. Previous NFN designs often depend on permutation symmetries in neural networks' weights, which traditionally arise from the unordered arrangement of neurons in hidden layers. However, these designs do not take into account the weight scaling symmetries of $\operatorname{ReLU}$ networks, and the weight sign flipping symmetries of $\operatorname{sin}$ or $\operatorname{tanh}$ networks. In this paper, we extend the study of the group action on the network weights from the group of permutation matrices to the group of monomial matrices by incorporating scaling/sign-flipping symmetries. Particularly, we encode these scaling/sign-flipping symmetries by designing our corresponding equivariant and invariant layers. We name our new family of NFNs the Monomial Matrix Group Equivariant Neural Functional Networks (Monomial-NFN). Because of the expansion of the symmetries, Monomial-NFN has much fewer independent trainable parameters compared to the baseline NFNs in the literature, thus enhancing the model's efficiency. Moreover, for fully connected and convolutional neural networks, we theoretically prove that all groups that leave these networks invariant while acting on their weight spaces are some subgroups of the monomial matrix group. We provide empirical evidences to demonstrate the advantages of our model over existing baselines, achieving competitive performance and efficiency.

We completely determine the asymptotic depth, equivalently, the asymptotic projective dimension of a chain of edge ideals that is invariant under the action of the monoid Inc of increasing functions on the positive integers. Our results and their proofs also reveal surprising combinatorial and topological properties of corresponding graphs and their independence complexes. In particular, we are able to determine the asymptotic behavior of all reduced homology groups of these independence complexes., Comment: 33 pages

Existing work on improving language model reasoning typically explores a single solution path, which can be prone to errors. Inspired by perspective-taking in social studies, this paper introduces DiPT, a novel approach that complements current reasoning methods by explicitly incorporating diversified viewpoints. This approach allows the model to gain a deeper understanding of the problem's context and identify the most effective solution path during the inference stage. Additionally, it provides a general data-centric AI recipe for augmenting existing data to improve their quality for fine-tuning. Our empirical results demonstrate that DiPT can be flexibly integrated into existing methods that focus on a single reasoning approach, enhancing their reasoning performance and stability when presented with paraphrased problems. Furthermore, we illustrate improved context understanding by maintaining the model's safe outputs against "jailbreaking" prompts intentionally designed to bypass safeguards built into deployed models. Lastly, we show that fine-tuning with data enriched with diverse perspectives can boost the reasoning capabilities of the model compared to fine-tuning with raw data alone., Comment: LLM Reasoning with Perspectives, Preprint

Negation is a fundamental linguistic concept used by humans to convey information that they do not desire. Despite this, there has been minimal research specifically focused on negation within vision-language tasks. This lack of research means that vision-language models (VLMs) may struggle to understand negation, implying that they struggle to provide accurate results. One barrier to achieving human-level intelligence is the lack of a standard collection by which research into negation can be evaluated. This paper presents the first large-scale dataset, Negative Instruction (NeIn), for studying negation within the vision-language domain. Our dataset comprises 530,694 quadruples, i.e., source image, original caption, negative sentence, and target image in total, including 495,694 queries for training and 35,000 queries for benchmarking across multiple vision-language tasks. Specifically, we automatically generate NeIn based on a large, existing vision-language dataset, MS-COCO, via two steps: generation and filtering. During the generation phase, we leverage two VLMs, BLIP and MagicBrush, to generate the target image and a negative clause that expresses the content of the source image. In the subsequent filtering phase, we apply BLIP to remove erroneous samples. Additionally, we introduce an evaluation protocol for negation understanding of image editing models. Extensive experiments using our dataset across multiple VLMs for instruction-based image editing tasks demonstrate that even recent state-of-the-art VLMs struggle to understand negative queries. The project page is: https://tanbuinhat.github.io/NeIn/

Audio-driven talking face generation is a widely researched topic due to its high applicability. Reconstructing a talking face using audio significantly contributes to fields such as education, healthcare, online conversations, virtual assistants, and virtual reality. Early studies often focused solely on changing the mouth movements, which resulted in outcomes with limited practical applications. Recently, researchers have proposed a new approach of constructing the entire face, including face pose, neck, and shoulders. To achieve this, they need to generate through landmarks. However, creating stable landmarks that align well with the audio is a challenge. In this paper, we propose the KFusion of Dual-Domain model, a robust model that generates landmarks from audio. We separate the audio into two distinct domains to learn emotional information and facial context, then use a fusion mechanism based on the KAN model. Our model demonstrates high efficiency compared to recent models. This will lay the groundwork for the development of the audio-driven talking face generation problem in the future.

In response to the ongoing pandemic and health emergency of COVID-19, several models have been used to understand the dynamics of virus spread. Some employ mathematical models like the compartmental SEIHRD approach and others rely on agent-based modeling (ABM). In this paper, a new city-based agent-based modeling approach called COVID19-CBABM is introduced. It considers not only the transmission mechanism simulated by the SEHIRD compartments but also models people movements and their interactions with their surroundings, particularly their interactions at different types of Points of Interest (POI), such as supermarkets. Through the development of knowledge extraction procedures for Safegraph data, our approach simulates realistic conditions based on spatial patterns and infection conditions considering locations where people spend their time in a given city. Our model was implemented in Python using the Mesa-Geo framework. COVID19-CBABM is portable and can be easily extended by adding more complicated scenarios. Therefore, it is a useful tool to assist the government and health authorities in evaluating strategic decisions and actions efficiently against this epidemic, using the unique mobility patterns of each city.