Search

Secure multiparty computation enables collaborative computations across multiple users while preserving individual privacy, which has a wide range of applications in finance, machine learning and healthcare. Secure multiparty computation can be realized using oblivious transfer as a primitive function. In this paper, we present an experimental implementation of a quantum-secure quantum oblivious transfer (QOT) protocol using an adapted quantum key distribution system combined with a bit commitment scheme, surpassing previous approaches only secure in the noisy storage model. We demonstrate the first practical application of the QOT protocol by solving the private set intersection, a prime example of secure multiparty computation, where two parties aim to find common elements in their datasets without revealing any other information. In our experiments, two banks can identify common suspicious accounts without disclosing any other data. This not only proves the experimental functionality of QOT, but also showcases its real-world commercial applications.

We present a study of the multiwavelength (MW) variability of the blazar AO 0235+164 based on the radio-to-$\gamma$-ray data covering a long time period from 1997 to 2023. The radio data are represented by the 1-22 GHz measurements from the RATAN-600 radio telescope, the 5 and 8 GHz data from the RT-32 telescopes, and the 37 GHz data from the RT-22 telescope. The optical measurements in the $R$-band were collected with the 1-m Zeiss-1000 and 0.5-m AS-500/2 telescopes. Additionally we used the archive data at 230~GHz from the SMA and the $\gamma$-ray data in the 0.1-100 GeV band from the Fermi-LAT point source 4FGL-DR2 catalogue. The variability properties during four epochs containing major flares and one epoch of relatively low activity were analysed. A significant correlation ($\geq\!2\sigma$) between the radio, optical, and $\gamma$-ray bands is found for all these periods with time delays from 0 to 1.7 yrs. The relation between time delay and frequency is described by a linear law with a negative slope of -10 day/GHz. The discovered properties of MW variability for the low activity period and for flaring states suggest that the mechanisms dominating the radio-$\gamma$-ray variations are not substantially different. The detected quasi-periodic oscillations of about 6 and 2 years are tentative, as the time span of the observations includes fewer than 4 full cycles for the radio and optical data and only about 3 cycles for the Fermi-LAT data. The physical parameters of the radio jet were obtained using the Hedgehog model applied to the average radio spectrum of AO 0235+164 in the range 0.1-300 GHz. The effectiveness of replacing electrons with protons in the synchrotron radio emission of relativistic jets is shown for describing the nature of blazars and the generation of high energy neutrinos., Comment: Accepted 2024 October 30 for publication in MNRAS

Large Language Models (LLMs) have recently demonstrated remarkable coding capabilities. However, assessing code generation based on well-formed properties and aligning it with developer preferences remains challenging. In this paper, we explore two key questions under the new challenge of code preference learning: (i) How do we train models to predict meaningful preferences for code? and (ii) How do human and LLM preferences align with verifiable code properties and developer code tastes? To this end, we propose CodeFavor, a framework for training pairwise code preference models from synthetic evolution data, including code commits and code critiques. To evaluate code preferences, we introduce CodePrefBench, a benchmark comprising 1364 rigorously curated code preference tasks to cover three verifiable properties-correctness, efficiency, and security-along with human preference. Our evaluation shows that CodeFavor holistically improves the accuracy of model-based code preferences by up to 28.8%. Meanwhile, CodeFavor models can match the performance of models with 6-9x more parameters while being 34x more cost-effective. We also rigorously validate the design choices in CodeFavor via a comprehensive set of controlled experiments. Furthermore, we discover the prohibitive costs and limitations of human-based code preference: despite spending 23.4 person-minutes on each task, 15.1-40.3% of tasks remain unsolved. Compared to model-based preference, human preference tends to be more accurate under the objective of code correctness, while being sub-optimal for non-functional objectives.

Based on new obtained analytical results, the main properties of photon echo quantum memory protocols are analysed and discussed together with recently achieved experimental results. The main attention is paid to studying the influence of spectral dispersion and nonlinear interaction of light pulses with resonant atoms. The distinctive features of the effect of spectral dispersion on the quantum storage of broadband signal pulses in the studied echo protocols are identified and discussed. Using photon echo area theorem, closed analytical solutions for echo protocols of quantum memory are obtained, describing the storage of weak and intense signal pulses, allowing us to find the conditions for the implementation of high efficiency in the echo protocols under strong nonlinear interaction of signal and control pulses with atoms. The key existing practical problems and the ways to solve them in realistic experimental conditions are outlined. We also briefly discuss the potential of using the considered photon echo quantum memory protocols in a quantum repeater.

We present a refined speckle-interferometric orbit of a binary system $\mu$ Cet, with the main component studied based on the analysis of photometric and spectroscopic data, obtained at the SAO RAS 6-m telescope. The object was initially classified as a giant with chemical composition anomalies. As a result of our analysis, we conclude that the star belongs to the Main Sequence, to the class of non-peculiar stars. Analysis of photometric data from the TESS mission indicates that the main component of the system belongs to the $\gamma$ Dor pulsators., Comment: Accepted for publication in Astrophysical Bulletin

Commentary provides readers with a deep understanding of events by presenting diverse arguments and evidence. However, creating commentary is a time-consuming task, even for skilled commentators. Large language models (LLMs) have simplified the process of natural language generation, but their direct application in commentary creation still faces challenges due to unique task requirements. These requirements can be categorized into two levels: 1) fundamental requirements, which include creating well-structured and logically consistent narratives, and 2) advanced requirements, which involve generating quality arguments and providing convincing evidence. In this paper, we introduce Xinyu, an efficient LLM-based system designed to assist commentators in generating Chinese commentaries. To meet the fundamental requirements, we deconstruct the generation process into sequential steps, proposing targeted strategies and supervised fine-tuning (SFT) for each step. To address the advanced requirements, we present an argument ranking model for arguments and establish a comprehensive evidence database that includes up-to-date events and classic books, thereby strengthening the substantiation of the evidence with retrieval augmented generation (RAG) technology. To evaluate the generated commentaries more fairly, corresponding to the two-level requirements, we introduce a comprehensive evaluation metric that considers five distinct perspectives in commentary generation. Our experiments confirm the effectiveness of our proposed system. We also observe a significant increase in the efficiency of commentators in real-world scenarios, with the average time spent on creating a commentary dropping from 4 hours to 20 minutes. Importantly, such an increase in efficiency does not compromise the quality of the commentaries.

Pictor A is a $\gamma$-ray emitting radio galaxy and has a bright hotspot called WHS, located $\sim$4 arcmin away from the nucleus. In this letter, we present an analysis of its 16-year Fermi-LAT data and report the first Imaging X-ray Polarimetry Explorer (IXPE) observation for this source. Our analysis of the Fermi-LAT observations reveals evidence of two components in the average $\gamma$-ray spectrum of Pictor A, exhibiting a statistically significant hardening from $\Gamma^1_{\gamma}=3.25\pm0.15$ to $\Gamma^2_{\gamma}=1.81\pm0.07$ at a break energy of $2.46\pm0.09$ GeV. The evident variability of $\gamma$-rays is observed in Pictor A. Interestingly, the variability is dominated by the component below the break energy, and the component above the break energy shows no variability. Furthermore, we find that a power-law function can adequately fit the spectrum during high-flux states, whereas a broken power-law is still required to explain the spectrum during low-flux state. We suggest that the low-energy component originates from the nucleus, while the high-energy component primarily stems from WHS. The broadband spectral energy distributions of both nucleus and WHS can be well represented by a simple leptonic model, with both $\gamma$-ray components attributed to the synchrotron-self-Compton (SSC) process. The analysis of IXPE data on the nucleus yields an upper limit to the polarization degree $\Pi_{\rm X}<$8.9\% in the 2--8 keV band, agreeing with its X-ray emission originating from SSC. However, $\Pi_{\rm X}=23.5\%\pm5.6\%$ is observed at a confidence level of $>99\%$ in the 5--7 keV band, and the possible physical origin of this narrow-energy-band polarization signal is discussed., Comment: 14 Pages, 4 Figures, 3 Tables, submitted, comments are welcome

The training and inference of large language models (LLMs) are together a costly process that transports knowledge from raw data to meaningful computation. Inspired by the memory hierarchy of the human brain, we reduce this cost by equipping LLMs with explicit memory, a memory format cheaper than model parameters and text retrieval-augmented generation (RAG). Conceptually, with most of its knowledge externalized to explicit memories, the LLM can enjoy a smaller parameter size, training cost, and inference cost, all proportional to the amount of remaining "abstract knowledge". As a preliminary proof of concept, we train from scratch a 2.4B LLM, which achieves better performance than much larger LLMs as well as RAG models, and maintains higher decoding speed than RAG. The model is named $\text{Memory}^3$, since explicit memory is the third form of memory in LLMs after implicit memory (model parameters) and working memory (context key-values). We introduce a memory circuitry theory to support the externalization of knowledge, and present novel techniques including a memory sparsification mechanism that makes storage tractable and a two-stage pretraining scheme that facilitates memory formation.

We introduce ReXTime, a benchmark designed to rigorously test AI models' ability to perform temporal reasoning within video events. Specifically, ReXTime focuses on reasoning across time, i.e. human-like understanding when the question and its corresponding answer occur in different video segments. This form of reasoning, requiring advanced understanding of cause-and-effect relationships across video segments, poses significant challenges to even the frontier multimodal large language models. To facilitate this evaluation, we develop an automated pipeline for generating temporal reasoning question-answer pairs, significantly reducing the need for labor-intensive manual annotations. Our benchmark includes 921 carefully vetted validation samples and 2,143 test samples, each manually curated for accuracy and relevance. Evaluation results show that while frontier large language models outperform academic models, they still lag behind human performance by a significant 14.3% accuracy gap. Additionally, our pipeline creates a training dataset of 9,695 machine generated samples without manual effort, which empirical studies suggest can enhance the across-time reasoning via fine-tuning., Comment: Project page: https://rextime.github.io/

Large language models (LLMs) excel in generating coherent text, but they often struggle with context awareness, leading to inaccuracies in tasks requiring faithful adherence to provided information. We introduce FastMem, a novel method designed to enhance instruction fine-tuned LLMs' context awareness through fast memorization of the prompt. FastMem maximizes the likelihood of the prompt before inference by updating only the last Feed-Forward Network (FFN) module. This targeted approach ensures efficient optimization without overfitting, significantly improving the model's ability to comprehend and accurately follow the context. Our experiments demonstrate substantial gains in reading comprehension, text summarization and adherence to output structures. For instance, FastMem improves the accuracy of Llama 3-8B-Inst on the NQ-SWAP dataset from 59.1% to 71.6%, and reduces the output structure failure rate of Qwen 1.5-4B-Chat from 34.9% to 25.5%. Extensive experimental results highlight FastMem's potential to offer a robust solution to enhance the reliability and accuracy of LLMs in various applications. Our code is available at: https://github.com/IAAR-Shanghai/FastMem

The accurate determination of the true redshift distributions in tomographic bins is critical for cosmological constraints from photometric surveys. The proposed redshift self-calibration method, which utilizes the photometric galaxy clustering alone, is highly convenient and avoids the challenges from incomplete or unrepresentative spectroscopic samples in external calibration. However, the imperfection of the theoretical approximation on broad bins as well as the flaw of the algorithm in previous work risk the accuracy and application of the method. In this paper, we propose the improved self-calibration algorithm that incorporates novel update rules, which effectively accounts for heteroskedastic weights and noisy data with negative values. The improved algorithm greatly expands the application range of self-calibration method and accurately reconstructs the redshift distributions for various mock data. Using the luminous red galaxy (LRG) sample of the Dark Energy Spectroscopic Instrument (DESI) survey, we find that the reconstructed results are comparable to the state-of-the-art external calibration. This suggests the exciting prospect of using photometric galaxy clustering to reconstruct redshift distributions in the cosmological analysis of survey data., Comment: 25 pages, 10 figures, accepted for publication in JCAP

The superradiant phase transition (SRPT) is forbidden in the standard isotropic Dicke model due to the so-called no-go theorem induced by A-square term. In the framework of the Dicke model, we demonstrate that SRPTs can occur at both zero and finite temperatures if we intrinsically tune the rotating wave and count-rotating atom-cavity coupling independently, and/or introduce the nonlinear Stark coupling terms, thus overcoming the no-go theorem. The phase transitions in this so-called anisotropic Dicke-Stark model share the same universality class with the original Dicke model. The critical coupling strength of this model decreases with the isotropic constant gradually, but can be driven to zero quickly with the strong nonlinear Stark coupling. We believe that we have proposed a feasible scheme to observe the SRPT in the future solid-state experiments., Comment: 6 pages, 6 figures

Recent years have witnessed the prosperity of knowledge graph based recommendation system (KGRS), which enriches the representation of users, items, and entities by structural knowledge with striking improvement. Nevertheless, its unaffordable computational cost still limits researchers from exploring more sophisticated models. We observe that the bottleneck for training efficiency arises from the knowledge graph, which is plagued by the well-known issue of knowledge explosion. Recently, some works have attempted to slim the inflated KG via summarization techniques. However, these summarized nodes may ignore the collaborative signals and deviate from the facts that nodes in knowledge graph represent symbolic abstractions of entities from the real-world. To this end, in this paper, we propose a novel approach called KGTrimmer for knowledge graph pruning tailored for recommendation, to remove the unessential nodes while minimizing performance degradation. Specifically, we design an importance evaluator from a dual-view perspective. For the collective view, we embrace the idea of collective intelligence by extracting community consensus based on abundant collaborative signals, i.e. nodes are considered important if they attract attention of numerous users. For the holistic view, we learn a global mask to identify the valueless nodes from their inherent properties or overall popularity. Next, we build an end-to-end importance-aware graph neural network, which injects filtered knowledge to enhance the distillation of valuable user-item collaborative signals. Ultimately, we generate a pruned knowledge graph with lightweight, stable, and robust properties to facilitate the following-up recommendation task. Extensive experiments are conducted on three publicly available datasets to prove the effectiveness and generalization ability of KGTrimmer.

The density fields constructed by traditional mass assignment methods are susceptible to irritating discreteness, which hinders morphological measurements of cosmic large-scale structure (LSS) through Minkowski functionals (MFs). For alleviating this issue, fixed-kernel smoothing methods are commonly used in literatures, at the expense of losing substantial structural information. In this work, we propose to measure MFs with Delaunay tessellation field estimation (DTFE) technique, with the goal to maximize extractions of morphological information from sparse tracers. We perform our analyses starting from matter fields and progressively extending to halo fields. At matter field level, we elucidate how discreteness affects the morphological measurements of LSS. Then, by comparing with traditional Gaussian smoothing scheme, we preliminarily showcase the advantages of DTFE for enhancing measurements of MFs from sparse tracers. At halo field level, we first numerically investigate various systematic effects on MFs of DTFE fields, which are induced by finite voxel sizes, halo number densities, halo weightings, and redshift space distortions (RSDs), respectively. Then, we explore the statistical power of MFs measured with DTFE for extracting cosmological information encoded in RSDs. We find that MFs measured with DTFE exhibit improvements by $\sim$ $2$ orders of magnitude in discriminative power for RSD effects and by a factor of $\sim$ $3$-$5$ in constraining power on structure growth rate over the MFs measured with Gaussian smoothing. These findings demonstrate the remarkable enhancements in statistical power of MFs achieved by DTFE, showing enormous application potentials of our method in extracting various key cosmological information from galaxy surveys., Comment: 19 pages, 15 figures, and 1 table; accepted for publication in ApJS

The radio galaxy PKS 1007+142 is classified as a compact steep-spectrum source (CSS) and belongs to the class of young Active Galactic Nuclei (AGNs). In this paper, we investigate the $\gamma$-ray emission from this CSS by conducting a comprehensive analysis of the 15 yr Fermi Large Area Telescope (Fermi-LAT) observation data. The Fermi-LAT latest Source Catalog, 4FGL-DR4, includes an unassociated $\gamma$-ray source, 4FGL J1010.0+1416, located at 0.24{\deg} away from the radio position of PKS 1007+142. Using the 15 yr Fermi-LAT observation data, we re-estimate the best-fit position of the $\gamma$-ray source and find that PKS 1007+142 is in close proximity to the $\gamma$-ray source and falls within its 68% error circle. Therefore, we conclude that PKS 1007+142 is the most plausible counterpart to the unassociated LAT source with a detection test statistics (TS) $\sim$43.4 ($\sim 6.6\sigma$). PKS 1007+142 exhibits a steep power-law spectrum in the 0.1--300 GeV band, with a photon spectral index ($\Gamma_{\gamma}$) of $2.86\pm0.17$. The average flux in the considered time interval is $\rm (2.14\pm0.34)\times10^{-12}\ erg\ cm^{-2}\ s^{-1}$. Comparing PKS 1007+142 with other $\gamma$-ray emitting AGNs in both the $L_{\gamma}-\Gamma_{\gamma}$ and $L_\gamma-L_{\rm 1.4GHz}$ planes, it shows a softer $\gamma$-ray spectrum and lower luminosity compared to other $\gamma$-ray emitting CSSs. Furthermore, the possible origins of $\gamma$-ray in PKS 1007+142 are also discussed., Comment: 11 pages, 5 figures, 2 tables, accepted for publication in ApJ

Printing custom DNA sequences is essential to scientific and biomedical research, but the technology can be used to manufacture plagues as well as cures. Just as ink printers recognize and reject attempts to counterfeit money, DNA synthesizers and assemblers should deny unauthorized requests to make viral DNA that could be used to ignite a pandemic. There are three complications. First, we don't need to quickly update printers to deal with newly discovered currencies, whereas we regularly learn of new viruses and other biological threats. Second, anti-counterfeiting specifications on a local printer can't be extracted and misused by malicious actors, unlike information on biological threats. Finally, any screening must keep the inspected DNA sequences private, as they may constitute valuable trade secrets. Here we describe SecureDNA, a free, privacy-preserving, and fully automated system capable of verifiably screening all DNA synthesis orders of 30+ base pairs against an up-to-date database of hazards, and its operational performance and specificity when applied to 67 million base pairs of DNA synthesized by providers in the United States, Europe, and China., Comment: Main text 10 pages, 4 figures. 5 supplementary figures. Total 21 pages. Direct correspondence to: Ivan B. Damgard (ivan@cs.au.dk), Andrew C. Yao (andrewcyao@mail.tsinghua.edu.cn), Kevin M. Esvelt (esvelt@mit.edu)

The power spectrum, as a statistic in Fourier space, is commonly numerically calculated using the fast Fourier transform method to efficiently reduce the computational costs. To alleviate the systematic bias known as aliasing due to the insufficient sampling, the interlacing technique was proposed. We derive the analytical form of the shot noise under the interlacing technique, which enables the exact separation of the Poisson shot noise from the signal in this case. Thanks to the accurate shot noise subtraction, we demonstrate an enhancement in the accuracy of power spectrum estimation, and compare with the other widely used estimators in community. The good performance of our estimation allows an abatement in the computational cost by using low resolution and low order mass assignment scheme in the analysis for huge surveys and mocks., Comment: 25 pages, 11 figures

Large-scale vision-language models (VLMs) have shown a strong zero-shot generalization capability on unseen-domain data. However, adapting pre-trained VLMs to a sequence of downstream tasks often leads to the forgetting of previously learned knowledge and a reduction in zero-shot classification performance. To tackle this problem, we propose a unique Selective Dual-Teacher Knowledge Transfer framework that leverages the most recent fine-tuned and the original pre-trained VLMs as dual teachers to preserve the previously learned knowledge and zero-shot capabilities, respectively. With only access to an unlabeled reference dataset, our proposed framework performs a selective knowledge distillation mechanism by measuring the feature discrepancy from the dual-teacher VLMs. Consequently, our selective dual-teacher knowledge distillation mitigates catastrophic forgetting of previously learned knowledge while preserving the zero-shot capabilities of pre-trained VLMs. Extensive experiments on benchmark datasets demonstrate that our framework is favorable against state-of-the-art continual learning approaches for preventing catastrophic forgetting and zero-shot degradation. Project page: https://chuyu.org/research/snd, Comment: Accepted to ECCV 2024. Project page: https://chuyu.org/research/snd