arXiv subjects

Zhu Liu

Publications and source records attributed to Zhu Liu.

At least 37 records · Page 2Linked to original sources

arXiv2026

RSOD: Reliability-Guided Sonar Image Object Detection with Extremely Limited Labels

Object detection in sonar images is a key technology in underwater detection systems. Compared to natural images, sonar images contain fewer texture details and are more susceptible to noise, making it difficult for non-experts to distinguish subtle differences between classes. This leads to their inability to provide precise annotation data for sonar images. Therefore, designing effective object detection methods for sonar images with extremely limited labels is particularly important. To address this, we propose a teacher-student framework called RSOD, which aims to fully learn the characteristics of sonar images and develop a pseudo-label strategy suitable for these images to mitigate the impact of limited labels. First, RSOD calculates a reliability score by assessing the consistency of the teacher's predictions across different views. To leverage this score, we introduce an object mixed pseudo-label method to tackle the shortage of labeled data in sonar images. Finally, we optimize the performance of the student by implementing a reliability-guided adaptive constraint. By taking full advantage of unlabeled data, the student can perform well even in situations with extremely limited labels. Notably, on the UATD dataset, our method, using only 5% of labeled data, achieves results that can compete against those of our baseline algorithm trained on 100% labeled data. We also collected a new dataset to provide more valuable data for research in the field of sonar.

cs.CV↗

arXiv2025

VoiceCraft-X: Unifying Multilingual, Voice-Cloning Speech Synthesis and Speech Editing

We introduce VoiceCraft-X, an autoregressive neural codec language model which unifies multilingual speech editing and zero-shot Text-to-Speech (TTS) synthesis across 11 languages: English, Mandarin, Korean, Japanese, Spanish, French, German, Dutch, Italian, Portuguese, and Polish. VoiceCraft-X utilizes the Qwen3 large language model for phoneme-free cross-lingual text processing and a novel token reordering mechanism with time-aligned text and speech tokens to handle both tasks as a single sequence generation problem. The model generates high-quality, natural-sounding speech, seamlessly creating new audio or editing existing recordings within one framework. VoiceCraft-X shows robust performance in diverse linguistic settings, even with limited per-language data, underscoring the power of unified autoregressive approaches for advancing complex, real-world multilingual speech applications. Audio samples are available at https://zhishengzheng.com/voicecraft-x/.

eess.AS↗

arXiv2025

EAGLE: Episodic Appearance- and Geometry-aware Memory for Unified 2D-3D Visual Query Localization in Egocentric Vision

Egocentric visual query localization is vital for embodied AI and VR/AR, yet remains challenging due to camera motion, viewpoint changes, and appearance variations. We present EAGLE, a novel framework that leverages episodic appearance- and geometry-aware memory to achieve unified 2D-3D visual query localization in egocentric vision. Inspired by avian memory consolidation, EAGLE synergistically integrates segmentation guided by an appearance-aware meta-learning memory (AMM), with tracking driven by a geometry-aware localization memory (GLM). This memory consolidation mechanism, through structured appearance and geometry memory banks, stores high-confidence retrieval samples, effectively supporting both long- and short-term modeling of target appearance variations. This enables precise contour delineation with robust spatial discrimination, leading to significantly improved retrieval accuracy. Furthermore, by integrating the VQL-2D output with a visual geometry grounded Transformer (VGGT), we achieve a efficient unification of 2D and 3D tasks, enabling rapid and accurate back-projection into 3D space. Our method achieves state-ofthe-art performance on the Ego4D-VQ benchmark.

cs.CV↗

arXiv2025

Enhancing Infrared Vision: Progressive Prompt Fusion Network and Benchmark

We engage in the relatively underexplored task named thermal infrared image enhancement. Existing infrared image enhancement methods primarily focus on tackling individual degradations, such as noise, contrast, and blurring, making it difficult to handle coupled degradations. Meanwhile, all-in-one enhancement methods, commonly applied to RGB sensors, often demonstrate limited effectiveness due to the significant differences in imaging models. In sight of this, we first revisit the imaging mechanism and introduce a Progressive Prompt Fusion Network (PPFN). Specifically, the PPFN initially establishes prompt pairs based on the thermal imaging process. For each type of degradation, we fuse the corresponding prompt pairs to modulate the model's features, providing adaptive guidance that enables the model to better address specific degradations under single or multiple conditions. In addition, a Selective Progressive Training (SPT) mechanism is introduced to gradually refine the model's handling of composite cases to align the enhancement process, which not only allows the model to remove camera noise and retain key structural details, but also enhancing the overall contrast of the thermal image. Furthermore, we introduce the most high-quality, multi-scenarios infrared benchmark covering a wide range of scenarios. Extensive experiments substantiate that our approach not only delivers promising visual results under specific degradation but also significantly improves performance on complex degradation scenes, achieving a notable 8.76\% improvement. Code is available at https://github.com/Zihang-Chen/HM-TIR.

cs.CV↗

arXiv2025

4D-PreNet: A Unified Preprocessing Framework for 4D-STEM Data Analysis

Automated experimentation with real time data analysis in scanning transmission electron microscopy (STEM) often require end-to-end framework. The four-dimensional scanning transmission electron microscopy (4D-STEM) with high-throughput data acquisition has been constrained by the critical bottleneck results from data preprocessing. Pervasive noise, beam center drift, and elliptical distortions during high-throughput acquisition inevitably corrupt diffraction patterns, systematically biasing quantitative measurements. Yet, conventional correction algorithms are often material-specific and fail to provide a robust, generalizable solution. In this work, we present 4D-PreNet, an end-to-end deep-learning pipeline that integrates attention-enhanced U-Net and ResNet architectures to simultaneously perform denoising, center correction, and elliptical distortion calibration. The network is trained on large, simulated datasets encompassing a wide range of noise levels, drift magnitudes, and distortion types, enabling it to generalize effectively to experimental data acquired under varying conditions. Quantitative evaluations demonstrate that our pipeline reduces mean squared error by up to 50% during denoising and achieves sub-pixel center localization in the center detection task, with average errors below 0.04 pixels. The outputs are bench-marked against traditional algorithms, highlighting improvements in both noise suppression and restoration of diffraction patterns, thereby facilitating high-throughput, reliable 4D-STEM real-time analysis for automated characterization.

cs.CV↗

arXiv2025

A new Bowen Fluorescence Flare and Extreme Coronal Line Emitter discovered by SRG/eROSITA

The nuclear transient eRASSt J012026.5-292727 (J012026 hereafter) was discovered in the second SRG/eROSITA all-sky survey (eRASS2). The source appeared more than one order of magnitude brighter than the eRASS1 upper limits (peak eRASS2 0.2-2.3 keV flux of 1.14 x 10^-12 erg cm^-2 s^-1), and with a soft X-ray spectrum (photon index Gamma = 4.3). Over the following months, the X-ray flux started decaying, with significant flaring activity on both hour- and year-timescales. By inspecting the multiwavelength light curves of time-domain wide-field facilities, we detected a strong mid-infrared flare, evolving over 2 years, and a weaker optical counterpart. Follow-up optical spectroscopy revealed transient features, including redshifted Balmer lines (FWHM ~1500 km/s), strong Fe II emission, He II and Bowen lines, and high-ionization iron coronal lines. One spectrum showed a triple-peaked H-beta line, consistent with emission from a face-on elliptical disk. The spectroscopic features and the slow evolution of the event place J012026 within the classifications of Bowen fluorescence flares (BFFs) and extreme coronal line emitters (ECLEs). BFFs have been associated with rejuvenated accreting SMBHs, although the mechanism triggering the onset of the new accretion flow is still unclear, while ECLEs have been linked to the disruption of stars in gas-rich environments. The association of J012026 to both classes, combined with the multi-wavelength information, suggests that BFFs could be, at least in some cases, due to tidal disruption events (TDEs). The observed X-ray variability, uncommon in standard TDEs, adds complexity to these families of nuclear transients. These results highlight the diverse phenomenology of nuclear accretion events and demonstrate the value of systematic X-ray surveys, such as eROSITA and Einstein Probe, for uncovering such transients and characterizing their physical origin.

astro-ph.HE↗

arXiv2025

RefTok: Reference-Based Tokenization for Video Generation

Effectively handling temporal redundancy remains a key challenge in learning video models. Prevailing approaches often treat each set of frames independently, failing to effectively capture the temporal dependencies and redundancies inherent in videos. To address this limitation, we introduce RefTok, a novel reference-based tokenization method capable of capturing complex temporal dynamics and contextual information. Our method encodes and decodes sets of frames conditioned on an unquantized reference frame. When decoded, RefTok preserves the continuity of motion and the appearance of objects across frames. For example, RefTok retains facial details despite head motion, reconstructs text correctly, preserves small patterns, and maintains the legibility of handwriting from the context. Across 4 video datasets (K600, UCF-101, BAIR Robot Pushing, and DAVIS), RefTok significantly outperforms current state-of-the-art tokenizers (Cosmos and MAGVIT) and improves all evaluated metrics (PSNR, SSIM, LPIPS) by an average of 36.7% at the same or higher compression ratios. When a video generation model is trained using RefTok's latents on the BAIR Robot Pushing task, the generations not only outperform MAGVIT-B but the larger MAGVIT-L, which has 4x more parameters, across all generation metrics by an average of 27.9%.

cs.CV↗

arXiv2025

GLTW: Joint Improved Graph Transformer and LLM via Three-Word Language for Knowledge Graph Completion

Knowledge Graph Completion (KGC), which aims to infer missing or incomplete facts, is a crucial task for KGs. However, integrating the vital structural information of KGs into Large Language Models (LLMs) and outputting predictions deterministically remains challenging. To address this, we propose a new method called GLTW, which encodes the structural information of KGs and merges it with LLMs to enhance KGC performance. Specifically, we introduce an improved Graph Transformer (iGT) that effectively encodes subgraphs with both local and global structural information and inherits the characteristics of language model, bypassing training from scratch. Also, we develop a subgraph-based multi-classification training objective, using all entities within KG as classification objects, to boost learning efficiency.Importantly, we combine iGT with an LLM that takes KG language prompts as input.Our extensive experiments on various KG datasets show that GLTW achieves significant performance gains compared to SOTA baselines.

cs.CL↗

arXiv2025

From the New World of Word Embeddings: A Comparative Study of Small-World Lexico-Semantic Networks in LLMs

Lexico-semantic networks represent words as nodes and their semantic relatedness as edges. While such networks are traditionally constructed using embeddings from encoder-based models or static vectors, embeddings from decoder-only large language models (LLMs) remain underexplored. Unlike encoder models, LLMs are trained with a next-token prediction objective, which does not directly encode the meaning of the current token. In this paper, we construct lexico-semantic networks from the input embeddings of LLMs with varying parameter scales and conduct a comparative analysis of their global and local structures. Our results show that these networks exhibit small-world properties, characterized by high clustering and short path lengths. Moreover, larger LLMs yield more intricate networks with less small-world effects and longer paths, reflecting richer semantic structures and relations. We further validate our approach through analyses of common conceptual pairs, structured lexical relations derived from WordNet, and a cross-lingual semantic network for qualitative words.

cs.CL↗

arXiv2025

The population of tidal disruption events discovered with eROSITA

This paper presents a systematic study of X-ray-selected canonical tidal disruption events (TDEs) discovered in the western Galactic hemisphere of the first two eROSITA all-sky surveys (eRASS1 and eRASS2) performed between Dec 2019 and Dec 2020. We compiled a TDE sample from the catalog of eROSITA's extragalactic transients and variables eRO-ExTra, which includes X-ray sources with a variability significance and fractional amplitude over four between eRASS1 and eRASS2, not associated with known AGNs. Each X-ray source is associated with an optical counterpart from the Legacy Survey DR10. Canonical TDEs were selected based on their X-ray light-curve properties (single flare or decline), soft X-ray spectra ($Γ>3$), and the absence of archival X-ray variability and AGN signatures in their host photometry and spectroscopy. The sample includes 31 X-ray-selected TDE candidates with redshifts of $0.02< z<0.34$ and luminosities of $5.7 \times 10^{41}<L_X<5.3 \times 10^{44}$ erg/s in the 0.2-6.0 keV rest frame, of which 30 are canonical TDEs and one is an off-nuclear TDE candidate. The derived X-ray luminosity function is best fit by a double power law with a luminosity break at $10^{44}$ erg/s, corresponding to the Eddington-limiting prediction. This corresponds to a TDE volumetric rate of $ (2.3^{+1.2}_{-0.9})\times10^{-7}\,Mpc^{-3} yr^{-1}$ ($\approx1.2\times 10^{-5}$ events per galaxy per year). TDE host galaxies show a green-valley overdensity. In addition, 20%, 30%, and 15% of the sample exhibit flares in the optical, mid-infrared (mid-IR), or radio bands, respectively. We discuss the differences between X-ray, optical, and mid-IR TDE populations and the origins of multiwavelength flares in the context of the obscuring envelope and stream-stream collision models. Finally, we highlight TDE subpopulations that are not included in the canonical sample and should be explored in the future.

astro-ph.HE↗

arXiv2025

Low latency global carbon budget reveals a continuous decline of the land carbon sink during the 2023/24 El Nino event

The high growth rate of atmospheric CO2 in 2023 was found to be caused by a severe reduction of the global net land carbon sink. Here we update the global CO2 budget from January 1st to July 1st 2024, during which El Niño drought conditions continued to prevail in the Tropics but ceased by March 2024. We used three dynamic global vegetation models (DGVMs), machine learning emulators of ocean models, three atmospheric inversions driven by observations from the second Orbiting Carbon Observatory (OCO-2) satellite, and near-real-time fossil CO2 emissions estimates. In a one-year period from July 2023 to July 2024 covering the El Niño 2023/24 event, we found a record-high CO2 growth rate of 3.66~$\pm$~0.09 ppm~yr$^{-1}$ ($\pm$~1 standard deviation) since 1979. Yet, the CO2 growth rate anomaly obtained after removing the long term trend is 1.1 ppm~yr$^{-1}$, which is marginally smaller than the July--July growth rate anomalies of the two major previous El Niño events in 1997/98 and 2015/16. The atmospheric CO2 growth rate anomaly was primarily driven by a 2.24 GtC~yr$^{-1}$ reduction in the net land sink including 0.3 GtC~yr$^{-1}$ of fire emissions, partly offset by a 0.38 GtC~yr$^{-1}$ increase in the ocean sink relative to the 2015--2022 July--July mean. The tropics accounted for 97.5\% of the land CO2 flux anomaly, led by the Amazon (50.6\%), central Africa (34\%), and Southeast Asia (8.2\%), with extra-tropical sources in South Africa and southern Brazil during April--July 2024. Our three DGVMs suggest greater tropical CO2 losses in 2023/2024 than during the two previous large El Niño in 1997/98 and 2015/16, whereas inversions indicate losses more comparable to 2015/16. Overall, this update of the low latency budget highlights the impact of recent El Niño droughts in explaining the high CO2 growth rate until July 2024.

physics.ao-ph↗

arXiv2025

Discovery of extreme Quasi-Periodic Eruptions in a newly accreting massive black hole

Quasi-periodic eruptions (QPEs) are rapid, recurring X-ray bursts from supermassive black holes, believed to result from interactions between accretion disks and surrounding matter. The galaxy SDSS1335+0728, previously stable for two decades, exhibited an increase in optical brightness in December 2019, followed by persistent Active Galactic Nucleus (AGN)-like variability for 5 years, suggesting the activation of a $\sim$10$^6\;M_\odot$ black hole. From February 2024, X-ray emission has been detected, revealing extreme $\sim$4.5-day QPEs with the highest fluxes and amplitudes, longest time scales, largest integrated energies, and a $\sim$25-day super-period. Low-significance UV variations are reported for the first time in a QPE host, likely related to the long timescales and large radii from which the emission originates. This discovery broadens the possible formation channels for QPEs, suggesting they are not linked solely to tidal disruption events but more generally to newly formed accretion flows, which we are witnessing in real time in a turn-on AGN candidate.

astro-ph.HE↗

arXiv2025

A Top-down Graph-based Tool for Modeling Classical Semantic Maps: A Crosslinguistic Case Study of Supplementary Adverbs

Semantic map models (SMMs) construct a network-like conceptual space from cross-linguistic instances or forms, based on the connectivity hypothesis. This approach has been widely used to represent similarity and entailment relationships in cross-linguistic concept comparisons. However, most SMMs are manually built by human experts using bottom-up procedures, which are often labor-intensive and time-consuming. In this paper, we propose a novel graph-based algorithm that automatically generates conceptual spaces and SMMs in a top-down manner. The algorithm begins by creating a dense graph, which is subsequently pruned into maximum spanning trees, selected according to metrics we propose. These evaluation metrics include both intrinsic and extrinsic measures, considering factors such as network structure and the trade-off between precision and coverage. A case study on cross-linguistic supplementary adverbs demonstrates the effectiveness and efficiency of our model compared to human annotations and other automated methods. The tool is available at https://github.com/RyanLiut/SemanticMapModel.

cs.CL↗

arXiv2025

DEAL: Data-Efficient Adversarial Learning for High-Quality Infrared Imaging

Thermal imaging is often compromised by dynamic, complex degradations caused by hardware limitations and unpredictable environmental factors. The scarcity of high-quality infrared data, coupled with the challenges of dynamic, intricate degradations, makes it difficult to recover details using existing methods. In this paper, we introduce thermal degradation simulation integrated into the training process via a mini-max optimization, by modeling these degraded factors as adversarial attacks on thermal images. The simulation is dynamic to maximize objective functions, thus capturing a broad spectrum of degraded data distributions. This approach enables training with limited data, thereby improving model performance.Additionally, we introduce a dual-interaction network that combines the benefits of spiking neural networks with scale transformation to capture degraded features with sharp spike signal intensities. This architecture ensures compact model parameters while preserving efficient feature representation. Extensive experiments demonstrate that our method not only achieves superior visual quality under diverse single and composited degradation, but also delivers a significant reduction in processing when trained on only fifty clear images, outperforming existing techniques in efficiency and accuracy. The source code will be available at https://github.com/LiuZhu-CV/DEAL.

cs.CV↗

arXiv2025

CRPO: Confidence-Reward Driven Preference Optimization for Machine Translation

Large language models (LLMs) have shown great potential in natural language processing tasks, but their application to machine translation (MT) remains challenging due to pretraining on English-centric data and the complexity of reinforcement learning from human feedback (RLHF). Direct Preference Optimization (DPO) has emerged as a simpler and more efficient alternative, but its performance depends heavily on the quality of preference data. To address this, we propose Confidence-Reward driven Preference Optimization (CRPO), a novel method that combines reward scores with model confidence to improve data selection for fine-tuning. CRPO selects challenging sentence pairs where the model is uncertain or underperforms, leading to more effective learning. While primarily designed for LLMs, CRPO also generalizes to encoder-decoder models like NLLB, demonstrating its versatility. Empirical results show that CRPO outperforms existing methods such as RS-DPO, RSO and MBR score in both translation accuracy and data efficiency.

cs.CL↗

arXiv2025

Infrared and Visible Image Fusion: From Data Compatibility to Task Adaption

Infrared-visible image fusion (IVIF) is a critical task in computer vision, aimed at integrating the unique features of both infrared and visible spectra into a unified representation. Since 2018, the field has entered the deep learning era, with an increasing variety of approaches introducing a range of networks and loss functions to enhance visual performance. However, challenges such as data compatibility, perception accuracy, and efficiency remain. Unfortunately, there is a lack of recent comprehensive surveys that address this rapidly expanding domain. This paper fills that gap by providing a thorough survey covering a broad range of topics. We introduce a multi-dimensional framework to elucidate common learning-based IVIF methods, from visual enhancement strategies to data compatibility and task adaptability. We also present a detailed analysis of these approaches, accompanied by a lookup table clarifying their core ideas. Furthermore, we summarize performance comparisons, both quantitatively and qualitatively, focusing on registration, fusion, and subsequent high-level tasks. Beyond technical analysis, we discuss potential future directions and open issues in this area. For further details, visit our GitHub repository: https://github.com/RollingPlain/IVIF_ZOO.

cs.CV↗

arXiv2025

Beyond Speaker Identity: Text Guided Target Speech Extraction

Target Speech Extraction (TSE) traditionally relies on explicit clues about the speaker's identity like enrollment audio, face images, or videos, which may not always be available. In this paper, we propose a text-guided TSE model StyleTSE that uses natural language descriptions of speaking style in addition to the audio clue to extract the desired speech from a given mixture. Our model integrates a speech separation network adapted from SepFormer with a bi-modality clue network that flexibly processes both audio and text clues. To train and evaluate our model, we introduce a new dataset TextrolMix with speech mixtures and natural language descriptions. Experimental results demonstrate that our method effectively separates speech based not only on who is speaking, but also on how they are speaking, enhancing TSE in scenarios where traditional audio clues are absent. Demos are at: https://mingyue66.github.io/TextrolMix/demo/

eess.AS↗

arXiv2025

Science objectives of the Einstein Probe mission

The Einstein Probe (EP) is an interdisciplinary mission of time-domain and X-ray astronomy. Equipped with a wide-field lobster-eye X-ray focusing imager, EP will discover cosmic X-ray transients and monitor the X-ray variability of known sources in 0.5-4 keV, at a combination of detecting sensitivity and cadence that is not accessible to the previous and current wide-field monitoring missions. EP can perform quick characterisation of transients or outbursts with a Wolter-I X-ray telescope onboard. In this paper, the science objectives of the Einstein Probe mission are presented. EP is expected to enlarge the sample of previously known or predicted but rare types of transients with a wide range of timescales. Among them, fast extragalactic transients will be surveyed systematically in soft X-rays, which include γ-ray bursts and their variants, supernova shock breakouts, and the predicted X-ray transients associated with binary neutron star mergers. EP will detect X-ray tidal disruption events and outbursts from active galactic nuclei, possibly at an early phase of the flares for some. EP will monitor the variability and outbursts of X-rays from white dwarfs, neutron stars and black holes in our and neighbouring galaxies at flux levels fainter than those detectable by the current instruments, and is expected to discover new objects. A large sample of stellar X-ray flares will also be detected and characterised. In the era of multi-messenger astronomy, EP has the potential of detecting the possible X-ray counterparts of gravitational wave events, neutrino sources, and ultra-high energy γ-ray and cosmic ray sources. EP is expected to help advance the studies of extreme objects/phenomena and their underlying physical processes revealed in the dynamic X-ray universe, as well as studies in other areas of X-ray astronomy.

astro-ph.HE↗