Search

Zero-Shot Composed Image Retrieval (ZS-CIR) supports diverse tasks with a broad range of visual content manipulation intentions that can be related to domain, scene, object, and attribute. A key challenge for ZS-CIR is to accurately map image representation to a pseudo-word token that captures the manipulation intention relevant image information for generalized CIR. However, existing methods between the retrieval and pre-training stages lead to significant redundancy in the pseudo-word tokens. In this paper, we propose a novel denoising image-to-word mapping approach, named Denoise-I2W, for mapping images into denoising pseudo-word tokens that, without intention-irrelevant visual information, enhance accurate ZS-CIR. Specifically, a pseudo triplet construction module first automatically constructs pseudo triples (\textit{i.e.,} a pseudo-reference image, a pseudo-manipulation text, and a target image) for pre-training the denoising mapping network. Then, a pseudo-composed mapping module maps the pseudo-reference image to a pseudo-word token and combines it with the pseudo-manipulation text with manipulation intention. This combination aligns with the target image, facilitating denoising intention-irrelevant visual information for mapping. Our proposed Denoise-I2W is a model-agnostic and annotation-free approach. It demonstrates strong generalization capabilities across three state-of-the-art ZS-CIR models on four benchmark datasets. By integrating Denoise-I2W with existing best models, we obtain consistent and significant performance boosts ranging from 1.45\% to 4.17\% over the best methods without increasing inference costs. and achieve new state-of-the-art results on ZS-CIR. Our code is available at \url{https://github.com/Pter61/denoise-i2w-tmm}., Comment: This work was submitted to IJCAI 2024, with a score of weak accept and borderline accept

Singing voice synthesis (SVS) system is expected to generate high-fidelity singing voice from given music scores (lyrics, duration and pitch). Recently, diffusion models have performed well in this field. However, sacrificing inference speed to exchange with high-quality sample generation limits its application scenarios. In order to obtain high quality synthetic singing voice more efficiently, we propose a singing voice synthesis method based on the consistency model, ConSinger, to achieve high-fidelity singing voice synthesis with minimal steps. The model is trained by applying consistency constraint and the generation quality is greatly improved at the expense of a small amount of inference speed. Our experiments show that ConSinger is highly competitive with the baseline model in terms of generation speed and quality. Audio samples are available at https://keylxiao.github.io/consinger., Comment: Singing voice synthesis, Consistency models, diffusion models

Accurate classification of transients obtained from spectroscopic data are important to understand their nature and discover new classes of astronomical objects. For supernovae (SNe), SNID, NGSF (a Python version of SuperFit), and DASH are widely used in the community. Each tool provides its own metric to help determine classification, such as rlap of SNID, chi2/dof of NGSF, and Probability of DASH. However, we do not know how accurate these tools are, and they have not been tested with a large homogeneous dataset. Thus, in this work, we study the accuracy of these spectral classification tools using 4,646 SEDMachine spectra, which have accurate classifications obtained from the Zwicky Transient Facility Bright Transient Survey (BTS). Comparing our classifications with those from BTS, we have tested the classification accuracy in various ways. We find that NGSF has the best performance (overall Accuracy 87.6% when samples are split into SNe Ia and Non-Ia types), while SNID and DASH have similar performance with overall Accuracy of 79.3% and 76.2%, respectively. Specifically for SNe Ia, SNID can accurately classify them when rlap > 15 without contamination from other types, such as Ibc, II, SLSN, and other objects that are not SNe (Purity > 98%). For other types, determining their classification is often uncertain. We conclude that it is difficult to obtain an accurate classification from these tools alone. This results in additional human visual inspection effort being required in order to confirm the classification. To reduce this human visual inspection and to support the classification process for future large-scale surveys, this work provides supporting information, such as the accuracy of each tool as a function of its metric., Comment: 13 pages, 6 figures, and 6 tables; accepted for publication in PASP

We try to classify Hopf algebras with the dual Chevalley property of discrete corepresentation type over an algebraically closed field $\Bbb{k}$ with characteristic 0. For such Hopf algebra $H$, we characterize the link quiver of $H$ and determine the structures of the link-indecomposable component $H_{(1)}$ containing $\Bbb{k}1$. Besides, we construct an infinite-dimensional non-pointed non-cosemisimple link-indecomposable Hopf algebra $H(e_{\pm 1}, f_{\pm 1}, u, v)$ with the dual Chevalley property of discrete corepresentation type.

Due to the recurrent structure of RNN, the long information propagation path poses limitations in capturing long-term dependencies, gradient explosion/vanishing issues, and inefficient sequential execution. Based on this, we propose a novel paradigm called Parallel Gated Network (PGN) as the new successor to RNN. PGN directly captures information from previous time steps through the designed Historical Information Extraction (HIE) layer and leverages gated mechanisms to select and fuse it with the current time step information. This reduces the information propagation path to $\mathcal{O}(1)$, effectively addressing the limitations of RNN. To enhance PGN's performance in long-range time series forecasting tasks, we propose a novel temporal modeling framework called Temporal PGN (TPGN). TPGN incorporates two branches to comprehensively capture the semantic information of time series. One branch utilizes PGN to capture long-term periodic patterns while preserving their local characteristics. The other branch employs patches to capture short-term information and aggregate the global representation of the series. TPGN achieves a theoretical complexity of $\mathcal{O}(\sqrt{L})$, ensuring efficiency in its operations. Experimental results on five benchmark datasets demonstrate the state-of-the-art (SOTA) performance and high efficiency of TPGN, further confirming the effectiveness of PGN as the new successor to RNN in long-range time series forecasting. The code is available in this repository: \url{https://github.com/Water2sea/TPGN}.

Fast Radio Bursts (FRBs) are millisecond-duration events detected from beyond the Milky Way. FRB emission characteristics favor highly magnetized neutron stars, or magnetars, as the sources, as evidenced by FRB-like bursts from a galactic magnetar, and the star-forming nature of FRB host galaxies. However, the processes that produce FRB sources remain unknown. Although galactic magnetars are often linked to core-collapse supernovae (CCSNe), it's uncertain what determines which supernovae result in magnetars. The galactic environments of FRB sources can be harnessed to probe their progenitors. Here, we present the stellar population properties of 30 FRB host galaxies discovered by the Deep Synoptic Array. Our analysis shows a significant deficit of low-mass FRB hosts compared to the occurrence of star-formation in the universe, implying that FRBs are a biased tracer of star-formation, preferentially selecting massive star-forming galaxies. This bias may be driven by galaxy metallicity, which is positively correlated with stellar mass. Metal-rich environments may favor the formation of magnetar progenitors through stellar mergers, as higher metallicity stars are less compact and more likely to fill their Roche lobes, leading to unstable mass transfer. Although massive stars do not have convective interiors to generate strong magnetic fields by dynamo, merger remnants are thought to have the requisite internal magnetic-field strengths to result in magnetars. The preferential occurrence of FRBs in massive star-forming galaxies suggests that CCSN of merger remnants preferentially forms magnetars., Comment: Accepted for publication in Nature. The final version will be published by the journal

Transient surveys routinely detect supernovae (SNe) without obvious host galaxies. To understand the demographics of these "hostless" SNe and to constrain the possible host properties, we identify 161 SNe reported to the Transient Name Server since 2016 that do not have hosts cataloged from pre-explosion wide-field galaxy surveys. Using forced aperture photometry, we detect excess flux around only 56 of these SNe. Both thermonuclear and core-collapse (CC) SNe are present in our sample. Compared to flux-limited SNe samples with known hosts, superluminous supernovae (SLSNe), particularly hydrogen-deficient SLSNe, are over-represented here relative to all other SNe types; among CC SNe, there is also a higher fraction of interacting SNe than non-interacting. On the low-luminosity side, seven SNe have host absolute magnitude upper limits fainter than M_g=-12, about 1 per cent of the Small Magellanic Cloud's luminosity; the faintest limits are close to the luminosity of globular clusters or ultra-faint dwarf galaxies (M_g~-8). Fitting multi-band forced photometry, 11 SNe have host stellar masses <10^6 Msun assuming quiescent hosts, and 13 SNe have host stellar masses <10^5 Msun assuming star-forming hosts. The spatial distribution of hostless SNe indicates that the majority are not associated with known galaxy groups and clusters, ruling out intracluster stellar light as the primary contributor of such SNe. Hostless Type Ia SNe tend to be more luminous and slow-fading than SNe Ia with known host galaxies, implying a hidden population of low-mass and star-forming hosts. We conclude that any undetected host galaxies are likely star-forming dwarfs in the field., Comment: Accepted for publication in MNRAS

We use the latest dataset of supernova (SN) host galaxies to investigate how the host properties -- stellar mass, star formation rate, metallicity, absolute magnitude, and colour -- differ across SN types, with redshift-driven selection effects controlled. SN Ib and Ic host galaxies, on average, are more massive, metal-rich, and redder than SN II hosts. For subtypes, SN Ibn and Ic-BL have bluer hosts than their normal SN Ib and Ic siblings; SN IIb has consistent host properties with SN Ib, while hosts of SN IIn are more metal-rich than those of SN II. Hydrogen-deficient superluminous supernovae feature bluer and lower luminosity hosts than most subtypes of core-collapse supernova (CC SN). Assuming simple proportionality of CC SN rates and host star formation rates (SFRs) does not recover the observed mean host properties; either a population of long-lived progenitors or a metallicity-dependent SN production efficiency better reproduces the observed host properties. Assuming the latter case, the rates of SN II are insensitive to host metallicity, but the rates of SN Ib and Ic are substantially enhanced in metal-rich hosts by a factor of ~10 per dex increase in metallicity. Hosts of SN Ia are diverse in their observed properties; subtypes including SN Ia-91T, Ia-02cx, and Ia-CSM prefer star-forming hosts, while subtypes like SN Ia-91bg and Ca-rich prefer quiescent hosts. The rates of SN Ia-91T, Ia-02cx, and Ia-CSM are closely dependent on, or even proportional to, their host SFRs, indicating relatively short-lived progenitors. Conversely, the rates of SN Ia-91bg and Ca-rich transients are proportional to the total stellar mass, favoring long-lived progenitors., Comment: Accepted for publication in MNRAS

Driver distraction remains a leading cause of traffic accidents, posing a critical threat to road safety globally. As intelligent transportation systems evolve, accurate and real-time identification of driver distraction has become essential. However, existing methods struggle to capture both global contextual and fine-grained local features while contending with noisy labels in training datasets. To address these challenges, we propose DSDFormer, a novel framework that integrates the strengths of Transformer and Mamba architectures through a Dual State Domain Attention (DSDA) mechanism, enabling a balance between long-range dependencies and detailed feature extraction for robust driver behavior recognition. Additionally, we introduce Temporal Reasoning Confident Learning (TRCL), an unsupervised approach that refines noisy labels by leveraging spatiotemporal correlations in video sequences. Our model achieves state-of-the-art performance on the AUC-V1, AUC-V2, and 100-Driver datasets and demonstrates real-time processing efficiency on the NVIDIA Jetson AGX Orin platform. Extensive experimental results confirm that DSDFormer and TRCL significantly improve both the accuracy and robustness of driver distraction detection, offering a scalable solution to enhance road safety.

We present the first homogeneous release of several thousand Type Ia supernovae (SNe Ia), all having spectroscopic classification, and spectroscopic redshifts for half the sample. This release, named the "DR2", contains 3628 nearby (z < 0.3) SNe Ia discovered, followed and classified by the Zwicky Transient Facility survey between March 2018 and December 2020. Of these, 3000 have good-to-excellent sampling and 2667 pass standard cosmology light-curve quality cuts. This release is thus the largest SN Ia release to date, increasing by an order of magnitude the number of well characterized low-redshift objects. With the "DR2", we also provide a volume-limited (z < 0.06) sample of nearly a thousand SNe Ia. With such a large, homogeneous and well controlled dataset, we are studying key current questions on SN cosmology, such as the linearity SNe Ia standardization, the SN and host dependencies, the diversity of the SN Ia population, and the accuracy of the current light-curve modeling. These, and more, are studied in detail in a series of articles associated with this release. Alongside the SN Ia parameters, we publish our force-photometry gri-band light curves, 5138 spectra, local and global host properties, observing logs, and a python tool to ease use and access of these data. The photometric accuracy of the "DR2" is not yet suited for cosmological parameter inference, which will follow as "DR2.5" release. We nonetheless demonstrate that the multi-thousand SN Ia Hubble Diagram has a typical 0.15 mag scatter., Comment: ZTF SN Ia DR2 release paper. Submitted to A&A (ZTF DR2 Special Issue). Already 1 response to referee

The cores of stars are the cosmic furnaces where light elements are fused into heavier nuclei. The fusion of hydrogen to helium initially powers all stars. The ashes of the fusion reactions are then predicted to serve as fuel in a series of stages, eventually transforming massive stars into a structure of concentric shells. These are composed of natal hydrogen on the outside, and consecutively heavier compositions inside, predicted to be dominated by helium, carbon/oxygen, oxygen/neon/magnesium, and oxygen/silicon/sulphur. Silicon and sulphur are fused into inert iron, leading to the collapse of the core and either a supernova explosion or the direct formation of a black hole. Stripped stars, where the outer hydrogen layer has been removed and the internal He-rich layer (in Wolf-Rayet WN stars) or even the C/O layer below it (in Wolf-Rayet WC/WO stars) are exposed, provide evidence for this shell structure, and the cosmic element production mechanism it reflects. The types of supernova explosions that arise from stripped stars embedded in shells of circumstellar material (most notably Type Ibn supernovae from stars with outer He layers, and Type Icn supernovae from stars with outer C/O layers) confirm this scenario. However, direct evidence for the most interior shells, which are responsible for the production of elements heavier than oxygen, is lacking. Here, we report the discovery of the first-of-its-kind supernova arising from a star peculiarly stripped all the way to the silicon and sulphur-rich internal layer. Whereas the concentric shell structure of massive stars is not under debate, it is the first time that such a thick, massive silicon and sulphur-rich shell, expelled by the progenitor shortly before the SN explosion, has been directly revealed., Comment: 48 pages, 12 figures and 10 tables. Submitted to a high-impact journal. The reduced spectra and photometry will be made available via the journal webpage and the WISeREP archive after the acceptance of the paper

Blind image deblurring is a challenging low-level vision task that involves estimating the unblurred image when the blur kernel is unknown. In this paper, we present a self-supervised multi-scale blind image deblurring method to jointly estimate the latent image and the blur kernel via alternating optimization. In the image estimation step, we construct a multi-scale generator network with multiple inputs and multiple outputs to collaboratively estimate latent images at various scales, supervised by an image pyramid constructed from only the blurred image. This generator places architectural constraints on the network and avoids the need for mathematical expression of image priors. In the blur kernel estimation step, the blur kernel at each scale is independently estimated with a direct solution to a quadratic regularized least-squares model for its flexible adaptation to the proposed multi-scale generator for image estimation. Thanks to the collaborative estimation across multiple scales, our method avoids the computationally intensive coarse-to-fine propagation and additional image deblurring processes used in traditional mathematical optimization-based methods. Quantitative and qualitative experimental results on synthetic and realistic datasets demonstrate the superior performance of our method, especially for handling large and real-world blurs., Comment: 21 pages, 17 figures, 94 references

Biological age scores are an emerging tool to characterize aging by estimating chronological age based on physiological biomarkers. Various scores have shown associations with aging-related outcomes. This study assessed the relation between an age score based on brain MRI images (BrainAge) and an age score based on metabolomic biomarkers (MetaboAge). We trained a federated deep learning model to estimate BrainAge in three cohorts. The federated BrainAge model yielded significantly lower error for age prediction across the cohorts than locally trained models. Harmonizing the age interval between cohorts further improved BrainAge accuracy. Subsequently, we compared BrainAge with MetaboAge using federated association and survival analyses. The results showed a small association between BrainAge and MetaboAge as well as a higher predictive value for the time to mortality of both scores combined than for the individual scores. Hence, our study suggests that both aging scores capture different aspects of the aging process.

We present volume-limited samples of cataclysmic variables (CVs) and AM CVn binaries jointly selected from SRG/eROSITA eRASS1 and \textit{Gaia} DR3 using an X-ray + optical color-color diagram (the ``X-ray Main Sequence"). This tool identifies all CV subtypes, including magnetic and low-accretion rate systems, in contrast to most previous surveys. We find 23 CVs, 3 of which are AM CVns, out to 150 pc in the Western Galactic Hemisphere. Our 150 pc sample is spectroscopically verified and complete down to $L_X = 1.3\times 10^{29} \;\textrm{erg s}^{-1}$ in the 0.2--2.3 keV band, and we also present CV candidates out to 300 pc and 1000 pc. We discovered two previously unknown systems in our 150 pc sample: the third nearest AM CVn and a magnetic period bouncer. We find the mean $L_X$ of CVs to be $\langle L_X \rangle \approx 4.6\times 10^{30} \;\textrm{erg s}^{-1}$, in contrast to previous surveys which yielded $\langle L_X \rangle \sim 10^{31}-10^{32} \;\textrm{erg s}^{-1}$. We construct X-ray luminosity functions that, for the first time, flatten out at $L_X\sim 10^{30} \; \textrm{erg s}^{-1}$. We find average number, mass, and luminosity densities of $\rho_\textrm{N, CV} = (3.7 \pm 0.7) \times 10^{-6} \textrm{pc}^{-3}$, $\rho_M = (5.0 \pm 1.0) \times 10^{-5} M_\odot^{-1}$, and $\rho_{L_X} = (2.3 \pm 0.4) \times 10^{26} \textrm{erg s}^{-1}M_\odot^{-1}$, respectively, in the solar neighborhood. Our uniform selection method also allows us to place meaningful estimates on the space density of AM CVns, $\rho_\textrm{N, AM CVn} = (5.5 \pm 3.7) \times 10^{-7} \textrm{pc}^{-3}$. Magnetic CVs and period bouncers make up $35\%$ and $25\%$ of our sample, respectively. This work, through a novel discovery technique, shows that the observed number densities of CVs and AM CVns, as well as the fraction of period bouncers, are still in tension with population synthesis estimates., Comment: Submitted to PASP, comments welcome

Current text-video retrieval methods mainly rely on cross-modal matching between queries and videos to calculate their similarity scores, which are then sorted to obtain retrieval results. This method considers the matching between each candidate video and the query, but it incurs a significant time cost and will increase notably with the increase of candidates. Generative models are common in natural language processing and computer vision, and have been successfully applied in document retrieval, but their application in multimodal retrieval remains unexplored. To enhance retrieval efficiency, in this paper, we introduce a model-based video indexer named T2VIndexer, which is a sequence-to-sequence generative model directly generating video identifiers and retrieving candidate videos with constant time complexity. T2VIndexer aims to reduce retrieval time while maintaining high accuracy. To achieve this goal, we propose video identifier encoding and query-identifier augmentation approaches to represent videos as short sequences while preserving their semantic information. Our method consistently enhances the retrieval efficiency of current state-of-the-art models on four standard datasets. It enables baselines with only 30\%-50\% of the original retrieval time to achieve better retrieval performance on MSR-VTT (+1.0%), MSVD (+1.8%), ActivityNet (+1.5%), and DiDeMo (+0.2%). The code is available at https://github.com/Lilidamowang/T2VIndexer-generativeSearch.

Knowledge-based visual question answering requires external knowledge beyond visible content to answer the question correctly. One limitation of existing methods is that they focus more on modeling the inter-modal and intra-modal correlations, which entangles complex multimodal clues by implicit embeddings and lacks interpretability and generalization ability. The key challenge to solve the above problem is to separate the information and process it separately at the functional level. By reusing each processing unit, the generalization ability of the model to deal with different data can be increased. In this paper, we propose Independent Inference Units (IIU) for fine-grained multi-modal reasoning to decompose intra-modal information by the functionally independent units. Specifically, IIU processes each semantic-specific intra-modal clue by an independent inference unit, which also collects complementary information by communication from different units. To further reduce the impact of redundant information, we propose a memory update module to maintain semantic-relevant memory along with the reasoning process gradually. In comparison with existing non-pretrained multi-modal reasoning models on standard datasets, our model achieves a new state-of-the-art, enhancing performance by 3%, and surpassing basic pretrained multi-modal models. The experimental results show that our IIU model is effective in disentangling intra-modal clues as well as reasoning units to provide explainable reasoning evidence. Our code is available at https://github.com/Lilidamowang/IIU.

Let $\Bbbk$ be an algebraically closed field of characteristic 0 and $H$ a finite-dimensional Hopf algebra over $\Bbbk$ with the dual Chevalley property. In this paper, we show that $\operatorname{gr}^c(H)$ is of tame corepresentation type if and only if $\operatorname{gr}^c(H)\cong (\Bbbk\langle x,y\rangle/I)^* \times H^\prime$ for some finite-dimensional semisimple Hopf algebra $H^\prime$ and some special ideals $I$. Then, by the method of link quiver and bosonization, we discuss which of the above ideals will occur when $(\Bbbk\langle x,y\rangle/I)^* \times H_0$ is a Hopf algebra of tame corepresentation type under some assumptions., Comment: arXiv admin note: substantial text overlap with arXiv:2308.09553

Let $G$ be a Borel graph all of whose finite subgraphs embed into the $d$-dimensional grid with diagonals. We show that then $G$ itself admits a Borel embedding into the Schreier graph of a free Borel action of $\mathbb Z^{O(d)}$. This strengthens an earlier result of the authors, in which $O(d)$ is replaced by $O(\rho \log \rho)$, where $\rho$ is the polynomial growth rate of $G$., Comment: 10 pages

Recent work shows that documents from encyclopedias serve as helpful auxiliary information for zero-shot learning. Existing methods align the entire semantics of a document with corresponding images to transfer knowledge. However, they disregard that semantic information is not equivalent between them, resulting in a suboptimal alignment. In this work, we propose a novel network to extract multi-view semantic concepts from documents and images and align the matching rather than entire concepts. Specifically, we propose a semantic decomposition module to generate multi-view semantic embeddings from visual and textual sides, providing the basic concepts for partial alignment. To alleviate the issue of information redundancy among embeddings, we propose the local-to-semantic variance loss to capture distinct local details and multiple semantic diversity loss to enforce orthogonality among embeddings. Subsequently, two losses are introduced to partially align visual-semantic embedding pairs according to their semantic relevance at the view and word-to-patch levels. Consequently, we consistently outperform state-of-the-art methods under two document sources in three standard benchmarks for document-based zero-shot learning. Qualitatively, we show that our model learns the interpretable partial association., Comment: Accepted to ACM International Conference on Multimedia (MM) 2024

Let $v$ be a finite place of $\mathbb{F}_q(\theta)$. In this paper, we interpret $v$-adic arithmetic gamma values in terms of the $v$-adic crystalline-de Rham periods of Carlitz motives with Complex Multiplication, and establish an Ogus-type Chowla-Selberg formula. Furthermore, we prove the algebraic independence of these $v$-adic periods by determining the dimension of the motivic Galois groups through an adaptation and refinement of existing methods. As a consequence, all algebraic relations among $v$-adic arithmetic gamma values over $\mathbb{F}_q(\theta)$ can be derived from standard functional equations together with Thakur's analogue of the Gross-Koblitz formula.

Recent booming development of Generative Artificial Intelligence (GenAI) has facilitated an emerging model commercialization for the purpose of reinforcement on model performance, such as licensing or trading Deep Neural Network (DNN) models. However, DNN model trading may trigger concerns of the unauthorized replications or misuses over the model, so that the benefit of the model ownership will be violated. Model identity auditing is a challenging issue in protecting intellectual property of DNN models and verifying the integrity and ownership of models for guaranteeing trusts in transactions is one of the critical obstacles. In this paper, we focus on the above issue and propose a novel Accumulator-enabled Auditing for Distributed Identity of DNN Model (A2-DIDM) that utilizes blockchain and zero-knowledge techniques to protect data and function privacy while ensuring the lightweight on-chain ownership verification. The proposed model presents a scheme of identity records via configuring model weight checkpoints with corresponding zero-knowledge proofs, which incorporates predicates to capture incremental state changes in model weight checkpoints. Our scheme ensures both computational integrity of DNN training process and programmability, so that the uniqueness of the weight checkpoint sequence in a DNN model is preserved, ensuring the correctness of the model identity auditing. In addition, A2-DIDM also addresses privacy protections in distributed identity via a proposed method of accumulators. We systematically analyze the security and robustness of our proposed model and further evaluate the effectiveness and usability of auditing DNN model identities.

Medical imaging is limited by acquisition time and scanning equipment. CT and MR volumes, reconstructed with thicker slices, are anisotropic with high in-plane resolution and low through-plane resolution. We reveal an intriguing phenomenon that due to the mentioned nature of data, performing slice-wise interpolation from the axial view can yield greater benefits than performing super-resolution from other views. Based on this observation, we propose an Inter-Intra-slice Interpolation Network (I$^3$Net), which fully explores information from high in-plane resolution and compensates for low through-plane resolution. The through-plane branch supplements the limited information contained in low through-plane resolution from high in-plane resolution and enables continual and diverse feature learning. In-plane branch transforms features to the frequency domain and enforces an equal learning opportunity for all frequency bands in a global context learning paradigm. We further propose a cross-view block to take advantage of the information from all three views online. Extensive experiments on two public datasets demonstrate the effectiveness of I$^3$Net, and noticeably outperforms state-of-the-art super-resolution, video frame interpolation and slice interpolation methods by a large margin. We achieve 43.90dB in PSNR, with at least 1.14dB improvement under the upscale factor of $\times$2 on MSD dataset with faster inference. Code is available at https://github.com/DeepMed-Lab-ECNU/Medical-Image-Reconstruction.

Latent Diffusion Models (LDMs) enable a wide range of applications but raise ethical concerns regarding illegal utilization.Adding watermarks to generative model outputs is a vital technique employed for copyright tracking and mitigating potential risks associated with AI-generated content. However, post-hoc watermarking techniques are susceptible to evasion. Existing watermarking methods for LDMs can only embed fixed messages. Watermark message alteration requires model retraining. The stability of the watermark is influenced by model updates and iterations. Furthermore, the current reconstruction-based watermark removal techniques utilizing variational autoencoders (VAE) and diffusion models have the capability to remove a significant portion of watermarks. Therefore, we propose a novel technique called DiffuseTrace. The goal is to embed invisible watermarks in all generated images for future detection semantically. The method establishes a unified representation of the initial latent variables and the watermark information through training an encoder-decoder model. The watermark information is embedded into the initial latent variables through the encoder and integrated into the sampling process. The watermark information is extracted by reversing the diffusion process and utilizing the decoder. DiffuseTrace does not rely on fine-tuning of the diffusion model components. The watermark is embedded into the image space semantically without compromising image quality. The encoder-decoder can be utilized as a plug-in in arbitrary diffusion models. We validate through experiments the effectiveness and flexibility of DiffuseTrace. DiffuseTrace holds an unprecedented advantage in combating the latest attacks based on variational autoencoders and Diffusion Models.

In principle, the probability of configurations, determined by the system's partition function or wave function, encapsulates essential information about phases and phase transitions. Despite the exponentially large configuration space, we show that the generic correlation of distances between configurations, with a degree of freedom proportional to the lattice size, can probe phase transitions using importance sampling procedures like Monte Carlo simulations. The distribution of sampled distances varies significantly across different phases, suggesting universal critical behavior for uncertainty and participation entropy. For various classical spin models with different phases and transitions, finite-size analysis based on these quantities accurately identifies phase transitions and critical points. Notably, in all cases, the critical exponent derived from the uncertainty of distances equals the anomalous dimension governing real-space correlation decay. Thus, configuration space correlations, defined by distance uncertainties, share the same decay ratio as real-space correlations, determining the universality class of phase transitions. This work applies to diverse lattice models with different local degrees of freedom, e.g., two levels for Ising-like models, discrete multi-levels for q-state clock models, and continuous local levels for the XY model, offering a robust, alternative method for understanding complex phases and transitions., Comment: 17 figures, 15 pages

Generating radiology reports automatically reduces the workload of radiologists and helps the diagnoses of specific diseases. Many existing methods take this task as modality transfer process. However, since the key information related to disease accounts for a small proportion in both image and report, it is hard for the model to learn the latent relation between the radiology image and its report, thus failing to generate fluent and accurate radiology reports. To tackle this problem, we propose a memory-based cross-modal semantic alignment model (MCSAM) following an encoder-decoder paradigm. MCSAM includes a well initialized long-term clinical memory bank to learn disease-related representations as well as prior knowledge for different modalities to retrieve and use the retrieved memory to perform feature consolidation. To ensure the semantic consistency of the retrieved cross modal prior knowledge, a cross-modal semantic alignment module (SAM) is proposed. SAM is also able to generate semantic visual feature embeddings which can be added to the decoder and benefits report generation. More importantly, to memorize the state and additional information while generating reports with the decoder, we use learnable memory tokens which can be seen as prompts. Extensive experiments demonstrate the promising performance of our proposed method which generates state-of-the-art performance on the MIMIC-CXR dataset., Comment: 12 pages, 8 figures

The evolution of Large Language Models (LLMs) like ChatGPT and GPT-4 has sparked discussions on the advent of Artificial General Intelligence (AGI). However, replicating such advancements in open-source models has been challenging. This paper introduces InternLM2, an open-source LLM that outperforms its predecessors in comprehensive evaluations across 6 dimensions and 30 benchmarks, long-context modeling, and open-ended subjective evaluations through innovative pre-training and optimization techniques. The pre-training process of InternLM2 is meticulously detailed, highlighting the preparation of diverse data types including text, code, and long-context data. InternLM2 efficiently captures long-term dependencies, initially trained on 4k tokens before advancing to 32k tokens in pre-training and fine-tuning stages, exhibiting remarkable performance on the 200k ``Needle-in-a-Haystack" test. InternLM2 is further aligned using Supervised Fine-Tuning (SFT) and a novel Conditional Online Reinforcement Learning from Human Feedback (COOL RLHF) strategy that addresses conflicting human preferences and reward hacking. By releasing InternLM2 models in different training stages and model sizes, we provide the community with insights into the model's evolution.

In this paper, we show that all simple outerplanar graphs $G$ with minimum degree at least $2$ and positive Lin-Lu-Yau Ricci curvature on every edge have maximum degree at most $9$. Furthermore, if $G$ is maximally outerplanar, then $G$ has at most $10$ vertices. Both upper bounds are sharp., Comment: 10 pages

High-cadence, multiwavelength observations have continuously revealed the diversity of tidal disruption events (TDEs), thus greatly advancing our knowledge and understanding of TDEs. In this work, we conducted an intensive optical-UV and X-ray follow-up campaign of TDE AT2023lli, and found a remarkable month-long bump in its UV/optical light curve nearly two months prior to maximum brightness. The bump represents the longest separation time from the main peak among known TDEs to date. The main UV/optical outburst declines as $t^{-4.10}$, making it one of the fastest decaying optically selected TDEs. Furthermore, we detected sporadic X-ray emission 30 days after the UV/optical peak, accompanied by a reduction in the period of inactivity. It is proposed that the UV/optical bump could be caused by the self-intersection of the stream debris, whereas the primary peak is generated by the reprocessed emission of the accretion process. In addition, our results suggest that episodic X-ray radiation during the initial phase of decline may be due to the patched obscurer surrounding the accretion disk, a phenomenon associated with the inhomogeneous reprocessing process. The double TDE scenario, in which two stars are disrupted in sequence, is also a possible explanation for producing the observed early bump and main peak. We anticipate that the multicolor light curves of TDEs, especially in the very early stages, and the underlying physics can be better understood in the near future with the assistance of dedicated surveys such as the deep high-cadence survey of the 2.5-meter Wide Field Survey Telescope (WFST)., Comment: 14 pages, 8 figures,accepted for publication by ApJL

Multi-peaked supernovae with precursors, dramatic light-curve rebrightenings, and spectral transformation are rare, but are being discovered in increasing numbers by modern night-sky transient surveys like the Zwicky Transient Facility (ZTF). Here, we present the observations and analysis of SN 2023aew, which showed a dramatic increase in brightness following an initial luminous (-17.4 mag) and long (~100 days) unusual first peak (possibly precursor). SN 2023aew was classified as a Type IIb supernova during the first peak but changed its type to resemble a stripped-envelope supernova (SESN) after the marked rebrightening. We present comparisons of SN 2023aew's spectral evolution with SESN subtypes and argue that it is similar to SNe Ibc during its main peak. P-Cygni Balmer lines are present during the first peak, but vanish during the second peak's photospheric phase, before H$\alpha$ resurfaces again during the nebular phase. The nebular lines ([O I], [Ca II], Mg I], H$\alpha$) exhibit a double-peaked structure which hints towards a clumpy or non-spherical ejecta. We analyze the second peak in the light curve of SN 2023aew and find it to be broader than normal SESNe as well as requiring a very high $^{56}$Ni mass to power the peak luminosity. We discuss the possible origins of SN 2023aew including an eruption scenario where a part of the envelope is ejected during the first peak which also powers the second peak of the light curve through SN-CSM interaction., Comment: 22 pages, 11 figures, 5 tables