Search

Compositional Zero-Shot Learning (CZSL) aims to learn semantic primitives (attributes and objects) from seen compositions and recognize unseen attribute-object compositions. Existing CZSL datasets focus on single attributes, neglecting the fact that objects naturally exhibit multiple interrelated attributes. Real-world objects often possess multiple interrelated attributes, and current datasets' narrow attribute scope and single attribute labeling introduce annotation biases, undermining model performance and evaluation. To address these limitations, we introduce the Multi-Attribute Composition (MAC) dataset, encompassing 18,217 images and 11,067 compositions with comprehensive, representative, and diverse attribute annotations. MAC includes an average of 30.2 attributes per object and 65.4 objects per attribute, facilitating better multi-attribute composition predictions. Our dataset supports deeper semantic understanding and higher-order attribute associations, providing a more realistic and challenging benchmark for the CZSL task. We also develop solutions for multi-attribute compositional learning and propose the MM-encoder to disentangling the attributes and objects., Comment: 13pages,5figures

Few-mode multi-core fiber (FM-MCF) based Space-Division Multiplexing (SDM) systems possess the potential to maximize the number of multiplexed spatial channels per fiber by harnessing both the space (fiber cores) and mode (optical mode per core) dimensions. However, to date, no SDM transmissions over field-deployed FM-MCFs in realistic outdoor settings have been reported, which contrasts with SDM schemes demonstrated using single-mode multi-core fibers (SM-MCFs) installed in practical fiber cable ducts. In this paper, we present the successful demonstration of bidirectional SDM transmission over a 5-km field-deployed seven ring-core fiber (7-RCF) with a cladding diameter of 178 ${\mu}$m, achieving a Spectral Efficiency (SE) of 2$\times$201.6 bit/s/Hz. This work establishes a new record for the highest SE attained in SDM demonstrations utilizing field-deployed fiber cables, achieving an approximate 10x increase compared to the SE of reported field-deployed optical fiber cable transmission systems. Notably, these results are realized through the utilization of small-scale modular 4$\times$4 multiple-input multiple-output (MIMO) processing with a time-domain equalization (TDE) tap number not exceeding 15, maintaining a complexity per unit capacity comparable to that of MIMO equalization in SDM demonstrations employing weakly coupled SM-MCF cables. These results underscore the significant potential for achieving heightened SE and expanding capacity per individual fiber using SDM techniques in practical applications., Comment: 17 pages, 8 figures

Fairness-awareness has emerged as an essential building block for the responsible use of artificial intelligence in real applications. In many cases, inequity in performance is due to the change in distribution over different regions. While techniques have been developed to improve the transferability of fairness, a solution to the problem is not always feasible with no samples from the new regions, which is a bottleneck for pure data-driven attempts. Fortunately, physics-based mechanistic models have been studied for many problems with major social impacts. We propose SimFair, a physics-guided fairness-aware learning framework, which bridges the data limitation by integrating physical-rule-based simulation and inverse modeling into the training design. Using temperature prediction as an example, we demonstrate the effectiveness of the proposed SimFair in fairness preservation., Comment: Accepted to AAAI 2024 (preprint)

Although sparse-view computed tomography (CT) has significantly reduced radiation dose, it also introduces severe artifacts which degrade the image quality. In recent years, deep learning-based methods for inverse problems have made remarkable progress and have become increasingly popular in CT reconstruction. However, most of these methods suffer several limitations: dependence on high-quality training data, weak interpretability, etc. In this study, we propose a fully unsupervised framework called Deep Radon Prior (DRP), inspired by Deep Image Prior (DIP), to address the aforementioned limitations. DRP introduces a neural network as an implicit prior into the iterative method, thereby realizing cross-domain gradient feedback. During the reconstruction process, the neural network is progressively optimized in multiple stages to narrow the solution space in radon domain for the under-constrained imaging protocol, and the convergence of the proposed method has been discussed in this work. Compared with the popular pre-trained method, the proposed framework requires no dataset and exhibits superior interpretability and generalization ability. The experimental results demonstrate that the proposed method can generate detailed images while effectively suppressing image artifacts.Meanwhile, DRP achieves comparable or better performance than the supervised methods., Comment: 11 pages, 12 figures, Journal paper

As Archimedes famously said, ``Give me a lever long enough and a fulcrum on which to place it, and I shall move the world'', in this study, we propose to use a tiny Language Model (LM), \eg, a Transformer with 67M parameters, to lever much larger Vision-Language Models (LVLMs) with 9B parameters. Specifically, we use this tiny \textbf{Lever-LM} to configure effective in-context demonstration (ICD) sequences to improve the In-Context Learinng (ICL) performance of LVLMs. Previous studies show that diverse ICD configurations like the selection and ordering of the demonstrations heavily affect the ICL performance, highlighting the significance of configuring effective ICD sequences. Motivated by this and by re-considering the the process of configuring ICD sequence, we find this is a mirror process of human sentence composition and further assume that effective ICD configurations may contain internal statistical patterns that can be captured by Lever-LM. Then a dataset with effective ICD sequences is constructed to train Lever-LM. After training, given novel queries, new ICD sequences are configured by the trained Lever-LM to solve vision-language tasks through ICL. Experiments show that these ICD sequences can improve the ICL performance of two LVLMs compared with some strong baselines in Visual Question Answering and Image Captioning, validating that Lever-LM can really capture the statistical patterns for levering LVLMs., Comment: 17 pages, 6 figures

In this paper, we present the design and implementation of a two-element interferometer working in the millimeter wave band (39.5 GHz - 40 GHz) for observing solar radio emissions through nulling interference. The system is composed of two 50 cm aperture Cassegrain antennas mounted on a common equatorial mount, with a separation of 230 wavelengths. The cross-correlation of the received signals effectively cancels the quiet solar component of the large flux density (~3000 sfu) that reduces the detection limit due to atmospheric fluctuations. The system performance is obtained as follows: the noise factor of the AFE in the observation band is less than 2.1 dB, system sensitivity is approximately 12.4 K (~34 sfu) with an integration time constant of 0.1 ms (default), the frequency resolution is 153 kHz, and the dynamic range is larger than 30 dB. Through actual testing, the nulling interferometer observes a quiet sun with a low level of output fluctuations (of up to 50 sfu) and has a significantly lower radiation flux variability (of up to 190 sfu) than an equivalent single-antenna system, even under thick cloud cover. As a result, this new design can effectively improve observation sensitivity by reducing the impact of atmospheric and system fluctuations during observation.

We study the direct radiation excited by oscillating axion (or axion-like particle) dark matter in a homogenous magnetic field and its detection scheme. We concretely derive the analytical expression of the axion-induced radiated power for a cylindrical uniform magnetic field. In the long wave limit, the radiation power is proportional to the square of the B-field volume and the axion mass $m_a$, whereas it oscillate as approaching the short wave limit and the peak powers are proportional to the side area of the cylindrical magnetic field and $m_a^{-2}$. The maximum power locates at mass $m_a\sim\frac{3\pi}{4R}$ for fixed radius $R$. Based on this characteristic of the power, we discuss a scheme to detect the axions in the mass range $1-10^4$\,neV, where four detectors of different bandwidths surround the B-field. The expected sensitivity for $m_a\lesssim1\,\mu$eV under typical-parameter values can far exceed the existing constraints., Comment: 10 pages, 9 figures, comments welcome!

The COVID-19 pandemic has been severely impacting global society since December 2019. Massive research has been undertaken to understand the characteristics of the virus and design vaccines and drugs. The related findings have been reported in biomedical literature at a rate of about 10,000 articles on COVID-19 per month. Such rapid growth significantly challenges manual curation and interpretation. For instance, LitCovid is a literature database of COVID-19-related articles in PubMed, which has accumulated more than 200,000 articles with millions of accesses each month by users worldwide. One primary curation task is to assign up to eight topics (e.g., Diagnosis and Treatment) to the articles in LitCovid. Despite the continuing advances in biomedical text mining methods, few have been dedicated to topic annotations in COVID-19 literature. To close the gap, we organized the BioCreative LitCovid track to call for a community effort to tackle automated topic annotation for COVID-19 literature. The BioCreative LitCovid dataset, consisting of over 30,000 articles with manually reviewed topics, was created for training and testing. It is one of the largest multilabel classification datasets in biomedical scientific literature. 19 teams worldwide participated and made 80 submissions in total. Most teams used hybrid systems based on transformers. The highest performing submissions achieved 0.8875, 0.9181, and 0.9394 for macro F1-score, micro F1-score, and instance-based F1-score, respectively. The level of participation and results demonstrate a successful track and help close the gap between dataset curation and method development. The dataset is publicly available via https://ftp.ncbi.nlm.nih.gov/pub/lu/LitCovid/biocreative/ for benchmarking and further development.

Axion-like particles (ALPs) are predicted in some well-motivated theories beyond the Standard Model. The TeV gamma-rays from active galactic nuclei (AGN) suffer attenuation by the pair production interactions with the cosmic background light (EBL/CMB) during its travel to the earth. The attenuation can be circumvented through photon-ALP conversions in the AGN and Galaxy magnetic-field, and a flux enhancement is expected to arise in the observed spectrum. In this work, we study the potential of the AGN gamma-ray spectrum for energy up to above 100\,TeV to probe ALP-parameter space at around $\mu$eV, where the coupling $g_{a\gamma}$ is so far relatively weakly constrained. We find the nearby and bright sources, Mrk\,501, IC\,310 and M\,87, are suitable for our objective. Assuming an intrinsic spectrum exponential cutoff energy, we extrapolate the observed spectra of these sources up to above 100\,TeV by the models with/without ALPs. For $g_{a\gamma}\gtrsim 2\times$$10^{-11} \rm GeV^{-1}$ with $m_{a}\lesssim0.5\,\mu$eV, the flux at around 100\,TeV predicted by the ALP model can be enhanced more than an order of magnitude than that from the standard absorption, and could be detected by LHAASO. Our result is subject to the uncertainty from the intrinsic cutoff energy and the AGN lobe (or plume) magnetic-field. For an optimistic estimation, the constraint can be improved to $g_{a\gamma}\gtrsim 2\times$$10^{-11} \rm GeV^{-1}$ with $m_{a}\lesssim1\,\mu$eV. This require further observations on these sources by the forthcoming CTA, LHAASO, SWGO and so on., Comment: 14 pages, 7 figures, accepted for publication in Physical Review D