Search

The nascent topic of fake news requires automatic detection methods to quickly learn from limited annotated samples. Therefore, the capacity to rapidly acquire proficiency in a new task with limited guidance, also known as few-shot learning, is critical for detecting fake news in its early stages. Existing approaches either involve fine-tuning pre-trained language models which come with a large number of parameters, or training a complex neural network from scratch with large-scale annotated datasets. This paper presents a multimodal fake news detection model which augments multimodal features using unimodal features. For this purpose, we introduce Cross-Modal Augmentation (CMA), a simple approach for enhancing few-shot multimodal fake news detection by transforming n-shot classification into a more robust (n $\times$ z)-shot problem, where z represents the number of supplementary features. The proposed CMA achieves SOTA results over three benchmark datasets, utilizing a surprisingly simple linear probing method to classify multimodal fake news with only a few training samples. Furthermore, our method is significantly more lightweight than prior approaches, particularly in terms of the number of trainable parameters and epoch times. The code is available here: \url{https://github.com/zgjiangtoby/FND_fewshot}

Large visual-language models (LVLMs) exhibit exceptional performance in visual-language reasoning across diverse cross-modal benchmarks. Despite these advances, recent research indicates that Large Language Models (LLMs), like GPT-3.5-turbo, underachieve compared to well-trained smaller models, such as BERT, in Fake News Detection (FND), prompting inquiries into LVLMs' efficacy in FND tasks. Although performance could improve through fine-tuning LVLMs, the substantial parameters and requisite pre-trained weights render it a resource-heavy endeavor for FND applications. This paper initially assesses the FND capabilities of two notable LVLMs, CogVLM and GPT4V, in comparison to a smaller yet adeptly trained CLIP model in a zero-shot context. The findings demonstrate that LVLMs can attain performance competitive with that of the smaller model. Next, we integrate standard in-context learning (ICL) with LVLMs, noting improvements in FND performance, though limited in scope and consistency. To address this, we introduce the \textbf{I}n-context \textbf{M}ultimodal \textbf{F}ake \textbf{N}ews \textbf{D}etection (IMFND) framework, enriching in-context examples and test inputs with predictions and corresponding probabilities from a well-trained smaller model. This strategic integration directs the LVLMs' focus towards news segments associated with higher probabilities, thereby improving their analytical accuracy. The experimental results suggest that the IMFND framework significantly boosts the FND efficiency of LVLMs, achieving enhanced accuracy over the standard ICL approach across three publicly available FND datasets.

Coronal jets are one of the most common eruptive activities in the solar atmosphere. They are related to rich physics processes, including but not limited to magnetic reconnection, flaring, instabilities, and plasma heating. Automated identification of off-limb coronal jets has been difficult due to their abundant nature, complex appearance, and relatively small size compared to other features in the corona. In this paper, we present an automated coronal jet identification algorithm (AJIA) that utilizes true and fake jets previously detected by a laborious semi-automated jet detection algorithm (SAJIA, Liu et al. 2023) as the input of an image segmentation neural network U-NET. It is found that AJIA could achieve a much higher (0.81) detecting precision than SAJIA (0.34), meanwhile giving the possibility of whether each pixel in an input image belongs to a jet. We demonstrate that with the aid of artificial neural networks, AJIA could enable fast, accurate, and real-time coronal jet identification from SDO/AIA 304 \AA observations, which are essential in studying the collective and long-term behavior of coronal jets and their relation with the solar activity cycles., Comment: 13 pages, 7 figures

Accurate and robust localization remains a significant challenge for autonomous vehicles. The cost of sensors and limitations in local computational efficiency make it difficult to scale to large commercial applications. Traditional vision-based approaches focus on texture features that are susceptible to changes in lighting, season, perspective, and appearance. Additionally, the large storage size of maps with descriptors and complex optimization processes hinder system performance. To balance efficiency and accuracy, we propose a novel lightweight visual semantic localization algorithm that employs stable semantic features instead of low-level texture features. First, semantic maps are constructed offline by detecting semantic objects, such as ground markers, lane lines, and poles, using cameras or LiDAR sensors. Then, online visual localization is performed through data association of semantic features and map objects. We evaluated our proposed localization framework in the publicly available KAIST Urban dataset and in scenarios recorded by ourselves. The experimental results demonstrate that our method is a reliable and practical localization solution in various autonomous driving localization tasks.

This paper presents the participation of team QUST in Task 8 SemEval 2024. We first performed data augmentation and cleaning on the dataset to enhance model training efficiency and accuracy. In the monolingual task, we evaluated traditional deep-learning methods, multiscale positive-unlabeled framework (MPU), fine-tuning, adapters and ensemble methods. Then, we selected the top-performing models based on their accuracy from the monolingual models and evaluated them in subtasks A and B. The final model construction employed a stacking ensemble that combined fine-tuning with MPU. Our system achieved 8th (scored 8th in terms of accuracy, officially ranked 13th) place in the official test set in multilingual settings of subtask A. We release our system code at:https://github.com/warmth27/SemEval2024_QUST

In the ultra-thin regime, Bi2Te3 films feature two surfaces (with each surface being a two-dimensional Dirac-fermion system) with complicated spin textures and a tunneling term between them. We find in this regime that the quasiparticle scattering is completely different compared with the thick-film case and even behaves differently at each thickness. The thickness-dependent warping effect and tunneling term are found to be the two main factors that govern the scattering behaviors. The inter-band back-scattering that signals the existence of a tunneling term is found to disappear at 4 quintuple layers by the step-edge reflection approach. A four-band model is presented that captures the main features of the thickness-dependent scattering behaviors. Our work clarifies that the prohibition of back-scattering guaranteed by symmetry in topological insulators breaks down in the ultra-thin regime., Comment: 31 pages, 13 figures including the supplementary materials

The astrophysical origin of binary black hole (BBH) mergers remains uncertain though many events have been observed by the LIGO-Virgo-KAGRA network. Such mergers are predicted to originate in the vicinity of massive black holes (MBHs). Especially, GW190814, due to its secondary mass and mass ratio being beyond the expectations of isolated stellar evolution theories, is a promising event that has happened in an active galactic nucleus(AGN) disk. In this model, a compact object resides in the vicinity of a merging BBH. Here we report multiple pieces of evidence pointing to the fact that GW190814 is a BBH merging near a compact object. The orbital motion of BBHs around the third body produces a line-of-sight acceleration (LSA) and induces a varying Doppler shift. Using a waveform template that considers LSA, we perform Bayesian inference on a few BBH events with a high signal-to-noise ratio in the gravitational-wave transient catalog (GWTC). Compared to the model for isolated BBH mergers, we obtain significantly higher network signal-to-noise ratios for GW190814 by that with the LSA and constrain the LSA to $a = 0.0014^{+0.0014}_{-0.0022} ~c~\mathrm{s}^{-1}$. In addition, the logarithmic Bayes factor for the LSA case over the isolated case is $16.6$, which means the LSA model is significantly preferred by the GW data. We conclude that this is the first indication showing merging BBHs are located near a compact object., Comment: 19 pages, 4 figures

Detecting the environment around the supermassive black holes and tests of general relativity are important applications of extreme-mass-ratio inspirals (EMRIs). There is still a challenge to efficiently describe various "dirty" impacts on the inspirals like dark matter, gas, dipole radiation, electromagnetic interaction, and so on. In this Letter, we find the inherent linearity of the asymptotic solution of the inhomogeneous Teukolsky equation. Based on this property, we completely decouple the factors of the perturber and the background spacetime in the energy fluxes and waveforms. With the new decoupling form, the waveforms of EMRIs with non-geodesic motion in Kerr spacetime can be calculated conveniently. This will help to resolve the environment (including gas, field, dark matter, electromagnetic interaction, etc.) around the supermassive black holes and test general relativity., Comment: 6 pages + supplementary materials, 4 figures

Binary neutron star mergers are unique sources of gravitational waves in multi-messenger astronomy. The inspiral phase of binary neutron stars can emit gravitational waves as chirp signals. The present waveform models of gravitational wave only considered the gravitational interaction. In this paper, we derive the waveform of the gravitational wave signal taking into account the presence of magnetic fields. We found that the electromagnetic interaction and radiation can introduce different frequency-dependent power laws for both amplitude and frequency of the gravitational wave. We show from the results of Fisher information matrix that the third-generation observation may detect magnetic dipole moments if the magnetic field is around 10^17 G.

The COVID-19 pandemic led to an infodemic where an overwhelming amount of COVID-19 related content was being disseminated at high velocity through social media. This made it challenging for citizens to differentiate between accurate and inaccurate information about COVID-19. This motivated us to carry out a comparative study of the characteristics of COVID-19 misinformation versus those of accurate COVID-19 information through a large-scale computational analysis of over 242 million tweets. The study makes comparisons alongside four key aspects: 1) the distribution of topics, 2) the live status of tweets, 3) language analysis and 4) the spreading power over time. An added contribution of this study is the creation of a COVID-19 misinformation classification dataset. Finally, we demonstrate that this new dataset helps improve misinformation classification by more than 9\% based on average F1 measure., Comment: ICWSM TrueHealth 2023

This paper describes the participation of team QUST in the SemEval2023 task 3. The monolingual models are first evaluated with the under-sampling of the majority classes in the early stage of the task. Then, the pre-trained multilingual model is fine-tuned with a combination of the class weights and the sample weights. Two different fine-tuning strategies, the task-agnostic and the task-dependent, are further investigated. All experiments are conducted under the 10-fold cross-validation, the multilingual approaches are superior to the monolingual ones. The submitted system achieves the second best in Italian and Spanish (zero-shot) in subtask-1.

The standard paradigm for fake news detection mainly utilizes text information to model the truthfulness of news. However, the discourse of online fake news is typically subtle and it requires expert knowledge to use textual information to debunk fake news. Recently, studies focusing on multimodal fake news detection have outperformed text-only methods. Recent approaches utilizing the pre-trained model to extract unimodal features, or fine-tuning the pre-trained model directly, have become a new paradigm for detecting fake news. Again, this paradigm either requires a large number of training instances, or updates the entire set of pre-trained model parameters, making real-world fake news detection impractical. Furthermore, traditional multimodal methods fuse the cross-modal features directly without considering that the uncorrelated semantic representation might inject noise into the multimodal features. This paper proposes a Similarity-Aware Multimodal Prompt Learning (SAMPLE) framework. First, we incorporate prompt learning into multimodal fake news detection. Prompt learning, which only tunes prompts with a frozen language model, can reduce memory usage significantly and achieve comparable performances, compared with fine-tuning. We analyse three prompt templates with a soft verbalizer to detect fake news. In addition, we introduce the similarity-aware fusing method to adaptively fuse the intensity of multimodal representation and mitigate the noise injection via uncorrelated cross-modal features. For evaluation, SAMPLE surpasses the F1 and the accuracies of previous works on two benchmark multimodal datasets, demonstrating the effectiveness of the proposed method in detecting fake news. In addition, SAMPLE also is superior to other approaches regardless of few-shot and data-rich settings.

The popular waveform templates of extreme-mass-ratio inspirals usually omit the mass-ratio corrections in the conservative dynamics, and employ adiabatic approximation to include the radiation reaction. With the help of effective-one-body dynamics, we investigate the influence of mass-ratio corrections in the conservative part on the gravitational waves. We find that for the extra-relativistic orbits, the mass-ratio corrections can produce obvious orbital dephasing even for very small mass-ratio and then affect the waveforms. More importantly, it is noted that omitting the mass-ratio corrections in waveform templates may induce a fake signal of deviation from general relativity.

We analyze and observe the Fock-Darwin (FD) states in a circular n-p junction (CNPJ) of topological surface states. Theoretically, in the CNPJ induced by the sub-surface point charge, the FD states of Dirac fermions are found to have a unique core-shell structure of trapped electrons and holes. The interplay between them is highly tunable by the magnetic field, which has no analog in their conventional counterparts and even in FD states of Dirac fermions confined by the most-studied parabolic-like potentials. A modified Einstein-Brillouin-Keller method is introduced to derive the electron-core states semiclassically. Experimentally, we obtain the clearly resolved FD states of topological surface states up to 14 Tesla which are very different from those of conventional electrons. Our data also visualizes directly directly the field-dependent potential landscape that may be modified by the electron-electron interactions in a CNPJ at the surface of a three-dimensional topological insulator thin film. Our findings signal the high tunability of the FD states of topological surface states in CNPJs that can be obtained by molecular beam epitaxy., Comment: 21 pages, 6 figures

The nature of black holes is one of most exciting issues in gravitational physics. If there is an exotic compact object as the compact as a black hole but without a horizon, gravitational wave echoes may be produced after the merger. In this work, we show that for extreme-mass-ratio binaries, even during the inspiraling phase of compact binary coalescence, the exists of hard surface of the exotic compact object will produce detectable signals on the gravitational waves. We predict that once the LIGO-Virgo-KAGRA, Einstein Telescope or Cosmic Explorer detect such kind of sources, our model shows that one can constrain the properties of surfaces of the compact objects in inspiraling stage better than the current level.

Here we visualize the trapping of topological surface states in the circular n-p junctions on the top surface of the 7-quintuple-layer three dimensional (3D) topological insulator (TI) Sb2Te3 epitaxial films. As shown by spatially- and field-dependent tunneling spectra, these trapped resonances show field-induced splittings between the degenerate time-reversal-symmetric states at zero magnetic field. These behaviors are attributed unambiguously to Berry-phase switch by comparing the experimental data with both numerical and semi-classical simulations. The successful electrostatic trapping of topological surface states in epitaxial films and the observation of Berry-phase switch provide a rich platform of exploiting new ideas for TI-based quantum devices., Comment: 24pages,including the supplementary materials

The spreading COVID-19 misinformation over social media already draws the attention of many researchers. According to Google Scholar, about 26000 COVID-19 related misinformation studies have been published to date. Most of these studies focusing on 1) detect and/or 2) analysing the characteristics of COVID-19 related misinformation. However, the study of the social behaviours related to misinformation is often neglected. In this paper, we introduce a fine-grained annotated misinformation tweets dataset including social behaviours annotation (e.g. comment or question to the misinformation). The dataset not only allows social behaviours analysis but also suitable for both evidence-based or non-evidence-based misinformation classification task. In addition, we introduce leave claim out validation in our experiments and demonstrate the misinformation classification performance could be significantly different when applying to real-world unseen misinformation.