Search

Multimodal Fake News Detection has received increasing attention recently. Existing methods rely on independently encoded unimodal data and overlook the advantages of capturing intra-modality relationships and integrating inter-modal similarities using advanced techniques. To address these issues, Cross-Modal Tri-Transformer and Metric Learning for Multimodal Fake News Detection (CroMe) is proposed. CroMe utilizes Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models (BLIP2) as encoders to capture detailed text, image and combined image-text representations. The metric learning module employs a proxy anchor method to capture intra-modality relationships while the feature fusion module uses a Cross-Modal and Tri-Transformer for effective integration. The final fake news detector processes the fused features through a classifier to predict the authenticity of the content. Experiments on datasets show that CroMe excels in multimodal fake news detection.

We explore, through a combination of x-ray diffraction and elastoresistivity measurements, the effect of disorder on the strain-tuned charge density wave and associated multicriticality in Pd$_x$ErTe$_3$ (x = 0, 0.01, 0.02 and 0.026). We focus particularly on the behavior near the strain-tuned bicritical point that occurs in pristine ErTe$_3$ (x=0). Our study reveals that while Pd intercalation somewhat broadens the signatures of the CDW phase transitions, the line of first-order transitions at which the CDW reorients as a function of applied strain persists in the presence of disorder and still seemingly terminates at a critical point. The critical point occurs at a lower temperature and a lower strain compared to pristine ErTe$_3$. Similarly, the nematic elastoresistance of Pd$_x$ErTe$_3$, though suppressed in magnitude and broadened relative to that of ErTe$_3$, has a markedly more symmetric response around the critical point. These observations point to disorder driving a reduction in the system's electronic orthorhombicity even while the material remains irrevocably orthorhombic due to the presence of a glide plane in the crystal structure. Disorder, it would appear, reinforces the emergence of a "pseudo-tetragonal" electronic response in this fundamentally orthorhombic material.

Recently, generalizable feed-forward methods based on 3D Gaussian Splatting have gained significant attention for their potential to reconstruct 3D scenes using finite resources. These approaches create a 3D radiance field, parameterized by per-pixel 3D Gaussian primitives, from just a few images in a single forward pass. However, unlike multi-view methods that benefit from cross-view correspondences, 3D scene reconstruction with a single-view image remains an underexplored area. In this work, we introduce CATSplat, a novel generalizable transformer-based framework designed to break through the inherent constraints in monocular settings. First, we propose leveraging textual guidance from a visual-language model to complement insufficient information from a single image. By incorporating scene-specific contextual details from text embeddings through cross-attention, we pave the way for context-aware 3D scene reconstruction beyond relying solely on visual cues. Moreover, we advocate utilizing spatial guidance from 3D point features toward comprehensive geometric understanding under single-view settings. With 3D priors, image features can capture rich structural insights for predicting 3D Gaussians without multi-view techniques. Extensive experiments on large-scale datasets demonstrate the state-of-the-art performance of CATSplat in single-view 3D scene reconstruction with high-quality novel view synthesis.

GPT-4o is an autoregressive omni model that accepts as input any combination of text, audio, image, and video, and generates any combination of text, audio, and image outputs. It's trained end-to-end across text, vision, and audio, meaning all inputs and outputs are processed by the same neural network. GPT-4o can respond to audio inputs in as little as 232 milliseconds, with an average of 320 milliseconds, which is similar to human response time in conversation. It matches GPT-4 Turbo performance on text in English and code, with significant improvement on text in non-English languages, while also being much faster and 50\% cheaper in the API. GPT-4o is especially better at vision and audio understanding compared to existing models. In line with our commitment to building AI safely and consistent with our voluntary commitments to the White House, we are sharing the GPT-4o System Card, which includes our Preparedness Framework evaluations. In this System Card, we provide a detailed look at GPT-4o's capabilities, limitations, and safety evaluations across multiple categories, focusing on speech-to-speech while also evaluating text and image capabilities, and measures we've implemented to ensure the model is safe and aligned. We also include third-party assessments on dangerous capabilities, as well as discussion of potential societal impacts of GPT-4o's text and vision capabilities.

Mathematical models are established tools to assist in outbreak response. They help characterise complex patterns in disease spread, simulate control options to assist public health authorities in decision-making, and longer-term operational and financial planning. In the context of vaccine-preventable diseases (VPDs), vaccines are one of the most-cost effective outbreak response interventions, with the potential to avert significant morbidity and mortality through timely delivery. Models can contribute to the design of vaccine response by investigating the importance of timeliness, identifying high-risk areas, prioritising the use of limited vaccine supply, highlighting surveillance gaps and reporting, and determining the short- and long-term benefits. In this review, we examine how models have been used to inform vaccine response for 10 VPDs, and provide additional insights into the challenges of outbreak response modelling, such as data gaps, key vaccine-specific considerations, and communication between modellers and stakeholders. We illustrate that while models are key to policy-oriented outbreak vaccine response, they can only be as good as the surveillance data that inform them., Comment: 19 pages including references and abstract, 1 figure

Recent studies have addressed intricate phonological phenomena in French, relying on either extensive linguistic knowledge or a significant amount of sentence-level pronunciation data. However, creating such resources is expensive and non-trivial. To this end, we propose a novel two-step approach that encompasses two pronunciation tasks: grapheme-to-phoneme and post-lexical processing. We then investigate the efficacy of the proposed approach with a notably limited amount of sentence-level pronunciation data. Our findings demonstrate that the proposed two-step approach effectively mitigates the lack of extensive labeled data, and serves as a feasible solution for addressing French phonological phenomena even under resource-constrained environments., Comment: Accepted at EMNLP 2024 Main

The Boltzmann equation is a fundamental equation in kinetic theory that describes the motion of rarefied gases. In this study, we examine the Boltzmann equation within a $C^1$ bounded domain, subject to a large external potential $\Phi(x)$ and diffuse reflection boundary conditions. Initially, we prove the asymptotic stability of small perturbations near the local Maxwellian $\mu_E (x,v)$. Subsequently, we demonstrate the asymptotic stability of large amplitude solutions with initial data that is arbitrarily large in (weighted) $L^\infty$, but sufficiently small in the sense of relative entropy. Specifically, we extend the results for large amplitude solutions of the Boltzmann equation (with or without external potential) [10, 11, 12, 23] to scenarios involving significant external potentials [19, 28] under diffuse reflection boundary conditions., Comment: 99 pages

This report presents a solution for the swing-up and stabilisation tasks of the acrobot and the pendubot, developed for the AI Olympics competition at IROS 2024. Our approach employs the Average-Reward Entropy Advantage Policy Optimization (AR-EAPO), a model-free reinforcement learning (RL) algorithm that combines average-reward RL and maximum entropy RL. Results demonstrate that our controller achieves improved performance and robustness scores compared to established baseline methods in both the acrobot and pendubot scenarios, without the need for a heavily engineered reward function or system model. The current results are applicable exclusively to the simulation stage setup.

The galaxy M87 is one of the prime targets for high resolution radio imaging pursuing the ringlike shadow of its supermassive black hole, the innermost regions of accretion flow, and the formation of the relativistic jet. However, it remains challenging to observe both jointly. Only recently, global mm-VLBI array (GMVA)+ALMA observations at 86 GHz in 2018 were able to reconstruct the M87 black hole shadow and the extended jet emission simultaneously. In order to analyze the ring and jet of M87, conventional CLEAN algorithms were mainly employed alongside the RML method SMILI in the previous work. To test the robustness of the reconstructed structures of M87 GMVA+ALMA observations at 86GHz, we estimate the ring diameter, width, and the extended jet emission with the possible central spine by two different novel imaging algorithms: resolve and DoG-HiT. Overall reconstructions are consistent with the results reported in the previous paper. The ring structure of the M87 is resolved at higher resolution and the posterior distribution of M87 ring features is explored. The resolve images show that the ring diameter is 60.9 +- 2.2 muas and width is 16.0 +- 0.9 muas. The ring diameter is 61.0 muas and width is 20.6 muas by DoG-HiT. The ring diameter is therefore in agreement with the estimation (64+4-8 muas) by SMILI and the geometrical modeling. Two bright spots in the ring are reconstructed by four independent imaging methods, the substructure in the ring is therefore most likely originated from the data. A consistent limb-brightened jet structure is reconstructed by resolve and DoG-HiT, albeit with a less pronounced central spine. Modern data-driven imaging methods confirm the ring and jet structure in M87, complementing traditional VLBI methods with novel perspectives on the significance of recovered features. They confirm the result of the previous report., Comment: submitted to A&A

The application of machine learning to transcriptomics data has led to significant advances in cancer research. However, the high dimensionality and complexity of RNA sequencing (RNA-seq) data pose significant challenges in pan-cancer studies. This study hypothesizes that gene sets derived from single-cell RNA sequencing (scRNA-seq) data will outperform those selected using bulk RNA-seq in pan-cancer downstream tasks. We analyzed scRNA-seq data from 181 tumor biopsies across 13 cancer types. High-dimensional weighted gene co-expression network analysis (hdWGCNA) was performed to identify relevant gene sets, which were further refined using XGBoost for feature selection. These gene sets were applied to downstream tasks using TCGA pan-cancer RNA-seq data and compared to six reference gene sets and oncogenes from OncoKB evaluated with deep learning models, including multilayer perceptrons (MLPs) and graph neural networks (GNNs). The XGBoost-refined hdWGCNA gene set demonstrated higher performance in most tasks, including tumor mutation burden assessment, microsatellite instability classification, mutation prediction, cancer subtyping, and grading. In particular, genes such as DPM1, BAD, and FKBP4 emerged as important pan-cancer biomarkers, with DPM1 consistently significant across tasks. This study presents a robust approach for feature selection in cancer genomics by integrating scRNA-seq data and advanced analysis techniques, offering a promising avenue for improving predictive accuracy in cancer research., Comment: 16 pages, 3 figures, 1 tables, and 6 supplementary Table

Entropy Regularisation is a widely adopted technique that enhances policy optimisation performance and stability. A notable form of entropy regularisation is augmenting the objective with an entropy term, thereby simultaneously optimising the expected return and the entropy. This framework, known as maximum entropy reinforcement learning (MaxEnt RL), has shown theoretical and empirical successes. However, its practical application in straightforward on-policy actor-critic settings remains surprisingly underexplored. We hypothesise that this is due to the difficulty of managing the entropy reward in practice. This paper proposes a simple method of separating the entropy objective from the MaxEnt RL objective, which facilitates the implementation of MaxEnt RL in on-policy settings. Our empirical evaluations demonstrate that extending Proximal Policy Optimisation (PPO) and Trust Region Policy Optimisation (TRPO) within the MaxEnt framework improves policy optimisation performance in both MuJoCo and Procgen tasks. Additionally, our results highlight MaxEnt RL's capacity to enhance generalisation.

Competing interactions in frustrated magnets can give rise to highly degenerate ground states from which correlated liquid-like states of matter often emerge. The scaling of this degeneracy influences the ultimate ground state, with extensive degeneracies potentially yielding quantum spin liquids, while sub-extensive or smaller degeneracies yield static orders. A longstanding problem is to understand how ordered states precipitate from this degenerate manifold and what echoes of the degeneracy survive ordering. Here, we use neutron scattering to experimentally demonstrate a new "nodal line" spin liquid, where spins collectively fluctuate within a sub-extensive manifold spanning one-dimensional lines in reciprocal space. Realized in the spin-orbit coupled, face-centered cubic iridate K$_2$IrCl$_6$, we show that the sub-extensive degeneracy is robust, but remains susceptible to fluctuations or longer range interactions which cooperate to select a magnetic order at low temperatures. Proximity to the nodal line spin liquid influences the ordered state, enhancing the effects of quantum fluctuations and stabilizing it through the opening of a large spin-wave gap. Our results demonstrate quantum fluctuations can act counter-intuitively in frustrated materials: instead of destabilizing ordering, at the brink of the nodal spin liquid they can act to stabilize it and dictate its low-energy physics., Comment: Main article: 9 pages, 3 figures. Supplemental material: 22 pages, 15 figures

Self-calibration methods with the CLEAN algorithm have been widely employed in Very Long Baseline Interferometry (VLBI) data processing in order to correct antenna-based amplitude and phase corruptions present in the data. However, human interaction during the conventional CLEAN self-calibration process can impose a strong effective prior, which in turn may produce artifacts within the final image and hinder the reproducibility of final results. In this work, we aim to demonstrate a combined self-calibration and imaging method for VLBI data in a Bayesian inference framework. The method corrects for amplitude and phase gains for each antenna and polarization mode by inferring the temporal correlation of the gain solutions. We use Stokes I data of M87 taken with the Very Long Baseline Array (VLBA) at 43GHz, pre-calibrated using the rPICARD CASA-based pipeline. For antenna-based gain calibration and imaging, we use the Bayesian imaging software resolve. To estimate gain and image uncertainties, we use a Variational Inference method. We obtain a high-resolution M87 Stokes I image at 43GHz in conjunction with antenna-based gain solutions using our Bayesian self-calibration and imaging method. The core with counter-jet structure is better resolved, and extended jet emission is better described compared to the CLEAN reconstruction. Furthermore, uncertainty estimation of the image and antenna-based gains allows us to quantify the reliability of the result. Our Bayesian self-calibration and imaging method is able to reconstruct robust and reproducible Stokes I images and gain solutions with uncertainty estimation by taking into account the uncertainty information in the data., Comment: accepted for publication in A&A

Syntactic elements, such as word order and case markers, are fundamental in natural language processing. Recent studies show that syntactic information boosts language model performance and offers clues for people to understand their learning mechanisms. Unlike languages with a fixed word order such as English, Korean allows for varied word sequences, despite its canonical structure, due to case markers that indicate the functions of sentence components. This study explores whether Korean language models can accurately capture this flexibility. We note that incomplete word orders and omitted case markers frequently appear in ordinary Korean communication. To investigate this further, we introduce the Syntactically Incomplete Korean (SIKO) dataset. Through SIKO, we assessed Korean language models' flexibility with incomplete syntax and confirmed the dataset's training value. Results indicate these models reflect Korean's inherent flexibility, accurately handling incomplete inputs. Moreover, fine-tuning with SIKO enhances the ability to handle common incomplete Korean syntactic forms. The dataset's simple construction process, coupled with significant performance enhancements, solidifies its standing as an effective data augmentation technique., Comment: COLM 2024; Code and dataset is available in https://github.com/grayapple-git/SIKO

Non-convex functional constrained optimization problems have gained substantial attention in machine learning and signal processing. This paper develops a new primal-dual algorithm for solving this class of problems. The algorithm is based on a novel form of the Lagrangian function, termed {\em Proximal-Perturbed Augmented Lagrangian}, which enables us to develop an efficient and simple first-order algorithm that converges to a stationary solution under mild conditions. Our method has several key features of differentiation over existing augmented Lagrangian-based methods: (i) it is a single-loop algorithm that does not require the continuous adjustment of the penalty parameter to infinity; (ii) it can achieves an improved iteration complexity of $\widetilde{\mathcal{O}}(1/\epsilon^2)$ or at least ${\mathcal{O}}(1/\epsilon^{2/q})$ with $q \in (2/3,1)$ for computing an $\epsilon$-approximate stationary solution, compared to the best-known complexity of $\mathcal{O}(1/\epsilon^3)$; and (iii) it effectively handles functional constraints for feasibility guarantees with fixed parameters, without imposing boundedness assumptions on the dual iterates and the penalty parameters. We validate the effectiveness of our method through numerical experiments on popular non-convex problems.

The advances in the Neural Radiance Fields (NeRF) research offer extensive applications in diverse domains, but protecting their copyrights has not yet been researched in depth. Recently, NeRF watermarking has been considered one of the pivotal solutions for safely deploying NeRF-based 3D representations. However, existing methods are designed to apply only to implicit or explicit NeRF representations. In this work, we introduce an innovative watermarking method that can be employed in both representations of NeRF. This is achieved by fine-tuning NeRF to embed binary messages in the rendering process. In detail, we propose utilizing the discrete wavelet transform in the NeRF space for watermarking. Furthermore, we adopt a deferred back-propagation technique and introduce a combination with the patch-wise loss to improve rendering quality and bit accuracy with minimum trade-offs. We evaluate our method in three different aspects: capacity, invisibility, and robustness of the embedded watermarks in the 2D-rendered images. Our method achieves state-of-the-art performance with faster training speed over the compared state-of-the-art methods.

In this paper, we present a new heuristic derivation of the gravitational deflection of light around the Sun at the undergraduate level. Instead of solving the geodesic equation directly, we compute the correct deflection angle by focusing on the acceleration term of null geodesics. Using this heuristic deviation, we expect that undergraduate students who have not learned general relativity will be able to experience this computation, which is one of the most remarkable evidences of general relativity., Comment: 8 pages, 2 figures