arXiv subjects

Zhu Liu

Publications and source records attributed to Zhu Liu.

At least 55 records · Page 3Linked to original sources

arXiv2025

eRO-ExTra: eROSITA extragalactic non-AGN X-ray transients and variables in eRASS1 and eRASS2

(Abridged) While previous X-ray studies showed the dominance of regular active galactic nuclei (AGN) variability, a small fraction of sources arise from more exotic phenomena such as tidal disruption events (TDEs), quasi-periodic eruptions, or other short-lived events associated with supermassive black hole accretion. This paper describes the systematic selection of X-ray extragalactic transients found in the first two eROSITA all-sky surveys (eRASS) that are not associated with known AGN prior to eROSITA observations. We generated a variability sample from eRASS1 and eRASS2 (Dec. 2019-Dec. 2020), which includes sources with a variability significance and a fractional amplitude larger than four, located in the Legacy Survey DR10 (LS10) footprint. The properties of LS10 counterparts were used to exclude stars and known AGN. The sample was additionally cleaned using pre-eROSITA classifications, archival optical spectra, and archival X-ray data. The final catalog eRO-ExTra includes 304 extragalactic eROSITA transients and variables not associated with known AGN. More than 90% of sources have reliable LS10 optical counterparts. For each source, we provide archival X-ray data from Swift, ROSAT, and XMM-Newton; the eROSITA long-term light curve (2-2.5 years) with a light curve classification; as well as the best power law fit spectral results at the peak eROSITA epoch. Reliable spectroscopic and photometric redshifts are provided for more than 80% of the sample. Several sources in the catalog are known TDE candidates discovered by eROSITA. In addition, 31 sources are radio detected. The eRO-ExTra transients constitute a relatively clean parent sample of non-AGN variability phenomena associated with massive black holes. More than 95% of eRO-ExTra sources were discovered in X-rays with eROSITA for the first time, which makes it a valuable resource for studying unique nuclear transients.

astro-ph.HE↗

arXiv2024

JuniperLiu at CoMeDi Shared Task: Models as Annotators in Lexical Semantics Disagreements

We present the results of our system for the CoMeDi Shared Task, which predicts majority votes (Subtask 1) and annotator disagreements (Subtask 2). Our approach combines model ensemble strategies with MLP-based and threshold-based methods trained on pretrained language models. Treating individual models as virtual annotators, we simulate the annotation process by designing aggregation measures that incorporate continuous relatedness scores and discrete classification labels to capture both majority and disagreement. Additionally, we employ anisotropy removal techniques to enhance performance. Experimental results demonstrate the effectiveness of our methods, particularly for Subtask 2. Notably, we find that standard deviation on continuous relatedness scores among different model manipulations correlates with human disagreement annotations compared to metrics on aggregated discrete labels. The code will be published at https://github.com/RyanLiut/CoMeDi_Solution.

cs.CL↗

arXiv2024

Evaluating Distributed Representations for Multi-Level Lexical Semantics: A Research Proposal

Modern neural networks (NNs), trained on extensive raw sentence data, construct distributed representations by compressing individual words into dense, continuous, high-dimensional vectors. These representations are expected to capture multi-level lexical meaning. In this thesis, our objective is to examine the efficacy of distributed representations from NNs in encoding lexical meaning. Initially, we identify and formalize three levels of lexical semantics: \textit{local}, \textit{global}, and \textit{mixed} levels. Then, for each level, we evaluate language models by collecting or constructing multilingual datasets, leveraging various language models, and employing linguistic analysis theories. This thesis builds a bridge between computational models and lexical semantics, aiming to complement each other.

cs.CL↗

arXiv2024

Recurring tidal disruption events a decade apart in IRAS F01004-2237

We report the discovery of a second optical flare that occurred in September 2021 in IRAS F01004-2237, where the first flare occurred in 2010 has been reported, and present a detailed analysis of multi-band data. The position of the flare coincides with the galaxy centre with a precision of 650 pc. The flare peaks in $\sim50$ days with an absolute magnitude of $\sim-21$ and fades in two years roughly following $L\propto t^{-5/3}$. It maintains a nearly constant blackbody temperature of $\sim$22,000 K in the late time. Its optical and UV spectra show hydrogen and helium broad emission lines with full width at half maxima of 7,000--21,000 km s$^{-1}$ and He II/H$α$ ratio of 0.3--2.3. It shows weak X-ray emission relative to UV emission, with X-ray flares lasting for $<2-3$ weeks, during which the spectrum is soft with a power-law index $Γ=4.4^{+1.4}_{-1.3}$. These characters are consistent with a tidal disruption event (TDE), ruling out the possibilities of a supernova or an active galactic nuclei flare. With a TDE model, we infer a peak UV luminosity of $3.3\pm0.2\times10^{44}$ erg s$^{-1}$ and an energy budget of $4.5\pm0.2\times10^{51}$ erg. The two optical flares separated by $10.3\pm0.3$ years can be interpreted as repeating partial TDEs, double TDEs, or two independent TDEs. Although no definitive conclusion can be drawn, the partial TDEs interpretation predicts a third flare around 2033, and the independent TDEs interpretation predicts a high TDE rate of $\gtrsim10^{-2}$ yr$^{-1}$ in F01004-2237, both of which can be tested by future observations.

astro-ph.HE↗

arXiv2024

Einstein Probe discovery of EP240408a: a peculiar X-ray transient with an intermediate timescale

We report the discovery of a peculiar X-ray transient, EP240408a, by Einstein Probe (EP) and follow-up studies made with EP, Swift, NICER, GROND, ATCA and other ground-based multi-wavelength telescopes. The new transient was first detected with Wide-field X-ray Telescope (WXT) on board EP on April 8th, 2024, manifested in an intense yet brief X-ray flare lasting for 12 seconds. The flare reached a peak flux of 3.9x10^(-9) erg/cm2/s in 0.5-4 keV, about 300 times brighter than the underlying X-ray emission detected throughout the observation. Rapid and more precise follow-up observations by EP/FXT, Swift and NICER confirmed the finding of this new transient. Its X-ray spectrum is non-thermal in 0.5-10 keV, with a power-law photon index varying within 1.8-2.5. The X-ray light curve shows a plateau lasting for about 4 days, followed by a steep decay till becoming undetectable about 10 days after the initial detection. Based on its temporal property and constraints from previous EP observations, an unusual timescale in the range of 7-23 days is found for EP240408a, which is intermediate between the commonly found fast and long-term transients. No counterparts have been found in optical and near-infrared, with the earliest observation at 17 hours after the initial X-ray detection, suggestive of intrinsically weak emission in these bands. We demonstrate that the remarkable properties of EP240408a are inconsistent with any of the transient types known so far, by comparison with, in particular, jetted tidal disruption events, gamma-ray bursts, X-ray binaries and fast blue optical transients. The nature of EP240408a thus remains an enigma. We suggest that EP240408a may represent a new type of transients with intermediate timescales of the order of about 10 days. The detection and follow-ups of more of such objects are essential for revealing their origin.

astro-ph.HE↗

arXiv2024

The Scope 4 Emission: Neutralized Carbon Emissions

Assessing carbon negative and carbon neutrality is critical for mitigating and adapting global climate change. Here we proposed a new framework to account for carbon-negative and carbon-neutral actions by introducing the definition of Carbon Negative (C0),Carbon Neutrality Stock (C1), Carbon Supply (C2) and carbon-neutral emissions or Scope 4 emissions, which refers to the avoided emission due to use of non-fossil energy or C1 products. For the first time, we calculated the global neutralized carbon emissions or Scope 4 emission by renewable electricity generation, and the results indicating the significant contributions by China, with total neutralized carbon emissions (2.15 Mt C/day ) much higher than the U.S. (0.85 Mt C/day)and EU27 & UK (1.25 Mt C/day) together. We show that China contributed to more than 36% of global neutralized CO2 emissions, and such contributions are still increasing. This new framework reflects remarkable contributions for China to the global climate mitigation through the development of carbon neutrality energy system.

physics.soc-ph↗

arXiv2024

Searching a Compact Architecture for Robust Multi-Exposure Image Fusion

In recent years, learning-based methods have achieved significant advancements in multi-exposure image fusion. However, two major stumbling blocks hinder the development, including pixel misalignment and inefficient inference. Reliance on aligned image pairs in existing methods causes susceptibility to artifacts due to device motion. Additionally, existing techniques often rely on handcrafted architectures with huge network engineering, resulting in redundant parameters, adversely impacting inference efficiency and flexibility. To mitigate these limitations, this study introduces an architecture search-based paradigm incorporating self-alignment and detail repletion modules for robust multi-exposure image fusion. Specifically, targeting the extreme discrepancy of exposure, we propose the self-alignment module, leveraging scene relighting to constrain the illumination degree for following alignment and feature extraction. Detail repletion is proposed to enhance the texture details of scenes. Additionally, incorporating a hardware-sensitive constraint, we present the fusion-oriented architecture search to explore compact and efficient networks for fusion. The proposed method outperforms various competitive schemes, achieving a noteworthy 3.19\% improvement in PSNR for general scenarios and an impressive 23.5\% enhancement in misaligned scenarios. Moreover, it significantly reduces inference time by 69.1\%. The code will be available at https://github.com/LiuZhu-CV/CRMEF.

cs.CV↗

arXiv2024

Reconstructing Global Daily CO2 Emissions via Machine Learning

High temporal resolution CO2 emission data are crucial for understanding the drivers of emission changes, however, current emission dataset is only available on a yearly basis. Here, we extended a global daily CO2 emissions dataset backwards in time to 1970 using machine learning algorithm, which was trained to predict historical daily emissions on national scales based on relationships between daily emission variations and predictors established for the period since 2019. Variation in daily CO2 emissions far exceeded the smoothed seasonal variations. For example, the range of daily CO2 emissions equivalent to 31% of the year average daily emissions in China and 46% of that in India in 2022, respectively. We identified the critical emission-climate temperature (Tc) is 16.5 degree celsius for global average (18.7 degree celsius for China, 14.9 degree celsius for U.S., and 18.4 degree celsius for Japan), in which negative correlation observed between daily CO2 emission and ambient temperature below Tc and a positive correlation above it, demonstrating increased emissions associated with higher ambient temperature. The long-term time series spanning over fifty years of global daily CO2 emissions reveals an increasing trend in emissions due to extreme temperature events, driven by the rising frequency of these occurrences. This work suggests that, due to climate change, greater efforts may be needed to reduce CO2 emissions.

physics.ao-ph↗

arXiv2024

Low latency carbon budget analysis reveals a large decline of the land carbon sink in 2023

In 2023, the CO2 growth rate was 3.37 +/- 0.11 ppm at Mauna Loa, 86% above the previous year, and hitting a record high since observations began in 1958, while global fossil fuel CO2 emissions only increased by 0.6 +/- 0.5%. This implies an unprecedented weakening of land and ocean sinks, and raises the question of where and why this reduction happened. Here we show a global net land CO2 sink of 0.44 +/- 0.21 GtC yr-1, the weakest since 2003. We used dynamic global vegetation models, satellites fire emissions, an atmospheric inversion based on OCO-2 measurements, and emulators of ocean biogeochemical and data driven models to deliver a fast-track carbon budget in 2023. Those models ensured consistency with previous carbon budgets. Regional flux anomalies from 2015-2022 are consistent between top-down and bottom-up approaches, with the largest abnormal carbon loss in the Amazon during the drought in the second half of 2023 (0.31 +/- 0.19 GtC yr-1), extreme fire emissions of 0.58 +/- 0.10 GtC yr-1 in Canada and a loss in South-East Asia (0.13 +/- 0.12 GtC yr-1). Since 2015, land CO2 uptake north of 20 degree N declined by half to 1.13 +/- 0.24 GtC yr-1 in 2023. Meanwhile, the tropics recovered from the 2015-16 El Nino carbon loss, gained carbon during the La Nina years (2020-2023), then switched to a carbon loss during the 2023 El Nino (0.56 +/- 0.23 GtC yr-1). The ocean sink was stronger than normal in the equatorial eastern Pacific due to reduced upwelling from La Nina's retreat in early 2023 and the development of El Nino later. Land regions exposed to extreme heat in 2023 contributed a gross carbon loss of 1.73 GtC yr-1, indicating that record warming in 2023 had a strong negative impact on the capacity of terrestrial ecosystems to mitigate climate change.

physics.ao-ph↗

arXiv2024

Fantastic Semantics and Where to Find Them: Investigating Which Layers of Generative LLMs Reflect Lexical Semantics

Large language models have achieved remarkable success in general language understanding tasks. However, as a family of generative methods with the objective of next token prediction, the semantic evolution with the depth of these models are not fully explored, unlike their predecessors, such as BERT-like architectures. In this paper, we specifically investigate the bottom-up evolution of lexical semantics for a popular LLM, namely Llama2, by probing its hidden states at the end of each layer using a contextualized word identification task. Our experiments show that the representations in lower layers encode lexical semantics, while the higher layers, with weaker semantic induction, are responsible for prediction. This is in contrast to models with discriminative objectives, such as mask language modeling, where the higher layers obtain better lexical semantics. The conclusion is further supported by the monotonic increase in performance via the hidden states for the last meaningless symbols, such as punctuation, in the prompting strategy. Our codes are available at https://github.com/RyanLiut/LLM_LexSem.

cs.CL↗

arXiv2024

Moreau Envelope for Nonconvex Bi-Level Optimization: A Single-loop and Hessian-free Solution Strategy

This work focuses on addressing two major challenges in the context of large-scale nonconvex Bi-Level Optimization (BLO) problems, which are increasingly applied in machine learning due to their ability to model nested structures. These challenges involve ensuring computational efficiency and providing theoretical guarantees. While recent advances in scalable BLO algorithms have primarily relied on lower-level convexity simplification, our work specifically tackles large-scale BLO problems involving nonconvexity in both the upper and lower levels. We simultaneously address computational and theoretical challenges by introducing an innovative single-loop gradient-based algorithm, utilizing the Moreau envelope-based reformulation, and providing non-asymptotic convergence analysis for general nonconvex BLO problems. Notably, our algorithm relies solely on first-order gradient information, enhancing its practicality and efficiency, especially for large-scale BLO learning tasks. We validate our approach's effectiveness through experiments on various synthetic problems, two typical hyper-parameter learning tasks, and a real-world neural architecture search application, collectively demonstrating its superior performance.

math.OC↗

arXiv2024

Learn from the Past: A Proxy Guided Adversarial Defense Framework with Self Distillation Regularization

Adversarial Training (AT), pivotal in fortifying the robustness of deep learning models, is extensively adopted in practical applications. However, prevailing AT methods, relying on direct iterative updates for target model's defense, frequently encounter obstacles such as unstable training and catastrophic overfitting. In this context, our work illuminates the potential of leveraging the target model's historical states as a proxy to provide effective initialization and defense prior, which results in a general proxy guided defense framework, `LAST' ({\bf L}earn from the P{\bf ast}). Specifically, LAST derives response of the proxy model as dynamically learned fast weights, which continuously corrects the update direction of the target model. Besides, we introduce a self-distillation regularized defense objective, ingeniously designed to steer the proxy model's update trajectory without resorting to external teacher models, thereby ameliorating the impact of catastrophic overfitting on performance. Extensive experiments and ablation studies showcase the framework's efficacy in markedly improving model robustness (e.g., up to 9.2\% and 20.3\% enhancement in robust accuracy on CIFAR10 and CIFAR100 datasets, respectively) and training stability. These improvements are consistently observed across various model architectures, larger datasets, perturbation sizes, and attack modalities, affirming LAST's ability to consistently refine both single-step and multi-step AT strategies. The code will be available at~\url{https://github.com/callous-youth/LAST}.

cs.LG↗

arXiv2024

Rapid evolution of the recurrence time in the repeating partial tidal disruption event eRASSt J045650.3-203750

In this letter, we present the results from further X-ray and UV observations of the nuclear transient eRASSt J045650.3-203750 (hereafter J0456-20). We detected five repeating X-ray and UV flares from J0456-20, making it one of the most promising repeating partial tidal disruption event (pTDE) candidates. More importantly, we also found rapid changes in the recurrence time $T_\text{recur}$ of the X-ray flares by modelling the long-term X-ray light curve of J0456-20. $T_\text{recur}$ first decreased rapidly from about 300 days to around 230 days. It continued to decrease to around 190 days with an indication of a constant $T_\text{recur}$ evidenced from the latest three cycles. Our hydrodynamic simulations suggest that, in the repeating pTDE scenario, such rapid evolution of $T_\text{recur}$ could be reproduced if the original star is a $1~\mathrm{M}_\odot$ main-sequence star near the terminal age and loses nearly 80-90% of its mass during the initial encounter with a supermassive black hole (SMBH) of mass around $10^5~\mathrm{M}_\odot$. The inferred mass loss of 0.8-0.9 $\mathrm{M}_\odot$ is higher than the estimated value of around 0.13 $\mathrm{M}_\odot$ from observation, which could be explained if the radiation efficiency is low (i.e. $\ll0.1$). Our results indicate that repeating pTDEs could be effective tools to explore the dynamics around supermassive black holes beyond our own Galaxy.

astro-ph.HE↗

arXiv2024

A New Population of Mid-Infrared-Selected Tidal Disruption Events: Implications for Tidal Disruption Event Rates and Host Galaxy Properties

Most tidal disruption events (TDEs) are currently found in time-domain optical and soft X-ray surveys, both of which are prone to significant obscuration. The infrared (IR), however, is a powerful probe of dust-enshrouded environments, and hence, we recently performed a systematic search of NEOWISE mid-IR data for nearby, obscured TDEs within roughly 200 Mpc. We identified 18 TDE candidates in galactic nuclei, using difference imaging to uncover nuclear variability amongst significant host galaxy emission. These candidates were selected based on the following IR light curve properties: (1) $L_\mathrm{W2}\gtrsim10^{42}$ erg s$^{-1}$ at peak, (2) fast rise, followed by a slow, monotonic decline, (3) no significant prior variability, and (4) no evidence for AGN activity in WISE colors. The majority of these sources showed no variable optical counterpart, suggesting that optical surveys indeed miss numerous obscured TDEs. Using narrow line ionization levels and variability arguments, we identified 6 sources as possible underlying AGN, yielding a total of 12 TDEs in our gold sample. This gold sample yields a lower limit on the IR-selected TDE rate of $2.0\pm0.3\times10^{-5}$ galaxy$^{-1}$ year$^{-1}$ ($1.3\pm0.2\times10^{-7}$ Mpc$^{-3}$ year$^{-1}$), which is comparable to optical and X-ray TDE rates. The IR-selected TDE host galaxies do not show a green valley overdensity nor a preference for quiescent, Balmer strong galaxies, which are both overrepresented in optical and X-ray TDE samples. This IR-selected sample represents a new population of dusty TDEs that have historically been missed by optical and X-ray surveys and helps alleviate tensions between observed and theoretical TDE rates and the so-called missing energy problem.

astro-ph.HE↗

arXiv2023

Near-real-time monitoring of global ocean carbon sink

Mitigation of climate change will highly rely on a carbon emission trajectory that achieves carbon neutrality by the 2050s. The ocean plays a critical role in modulating climate change by sequestering CO2 from the atmosphere. Relying on the multidisciplinary cutting-edge methodologies and technologies, the near-real-time monitoring of global ocean carbon sinks from January 2022 to July 2023 aims to provide the world's latest assessment of monthly and gridded global ocean carbon sinks based on machine learning and other data science technologies. The project will help us find a robust route to deal with climate change, which will significantly promote the ocean carbon sinks research and will be of great interest for policy makers, researchers, and the public. This research aims to build up an integrated machine learning framework and methodology for assessing global ocean carbon neutral process; development of near-real-time dataset; development of visualization platform; research papers published in international prestigious journals; an executive report openly accessible to policy makers and the public.

physics.ao-ph↗

arXiv2023

Optimization-Inspired Learning with Architecture Augmentations and Control Mechanisms for Low-Level Vision

In recent years, there has been a growing interest in combining learnable modules with numerical optimization to solve low-level vision tasks. However, most existing approaches focus on designing specialized schemes to generate image/feature propagation. There is a lack of unified consideration to construct propagative modules, provide theoretical analysis tools, and design effective learning mechanisms. To mitigate the above issues, this paper proposes a unified optimization-inspired learning framework to aggregate Generative, Discriminative, and Corrective (GDC for short) principles with strong generalization for diverse optimization models. Specifically, by introducing a general energy minimization model and formulating its descent direction from different viewpoints (i.e., in a generative manner, based on the discriminative metric and with optimality-based correction), we construct three propagative modules to effectively solve the optimization models with flexible combinations. We design two control mechanisms that provide the non-trivial theoretical guarantees for both fully- and partially-defined optimization formulations. Under the support of theoretical guarantees, we can introduce diverse architecture augmentation strategies such as normalization and search to ensure stable propagation with convergence and seamlessly integrate the suitable modules into the propagation respectively. Extensive experiments across varied low-level vision tasks validate the efficacy and adaptability of GDC. The codes are available at https://github.com/LiuZhu-CV/GDC-OptimizationLearning

cs.CV↗

arXiv2023

Enhancing Infrared Small Target Detection Robustness with Bi-Level Adversarial Framework

The detection of small infrared targets against blurred and cluttered backgrounds has remained an enduring challenge. In recent years, learning-based schemes have become the mainstream methodology to establish the mapping directly. However, these methods are susceptible to the inherent complexities of changing backgrounds and real-world disturbances, leading to unreliable and compromised target estimations. In this work, we propose a bi-level adversarial framework to promote the robustness of detection in the presence of distinct corruptions. We first propose a bi-level optimization formulation to introduce dynamic adversarial learning. Specifically, it is composited by the learnable generation of corruptions to maximize the losses as the lower-level objective and the robustness promotion of detectors as the upper-level one. We also provide a hierarchical reinforced learning strategy to discover the most detrimental corruptions and balance the performance between robustness and accuracy. To better disentangle the corruptions from salient features, we also propose a spatial-frequency interaction network for target detection. Extensive experiments demonstrate our scheme remarkably improves 21.96% IOU across a wide array of corruptions and notably promotes 4.97% IOU on the general benchmark. The source codes are available at https://github.com/LiuZhu-CV/BALISTD.

cs.CV↗

arXiv2023

AutoPCF: Efficient Product Carbon Footprint Accounting with Large Language Models

The product carbon footprint (PCF) is crucial for decarbonizing the supply chain, as it measures the direct and indirect greenhouse gas emissions caused by all activities during the product's life cycle. However, PCF accounting often requires expert knowledge and significant time to construct life cycle models. In this study, we test and compare the emergent ability of five large language models (LLMs) in modeling the 'cradle-to-gate' life cycles of products and generating the inventory data of inputs and outputs, revealing their limitations as a generalized PCF knowledge database. By utilizing LLMs, we propose an automatic AI-driven PCF accounting framework, called AutoPCF, which also applies deep learning algorithms to automatically match calculation parameters, and ultimately calculate the PCF. The results of estimating the carbon footprint for three case products using the AutoPCF framework demonstrate its potential in achieving automatic modeling and estimation of PCF with a large reduction in modeling time from days to minutes.

cs.AI↗