Search

The opening of the gravitational wave window has significantly enhanced our capacity to explore the universe's most extreme and dynamic sector. In the mHz frequency range, a diverse range of compact objects, from the most massive black holes at the farthest reaches of the Universe to the lightest white dwarfs in our cosmic backyard, generate a complex and dynamic symphony of gravitational wave signals. Once recorded by gravitational wave detectors, these unique fingerprints have the potential to decipher the birth and growth of cosmic structures over a wide range of scales, from stellar binaries and stellar clusters to galaxies and large-scale structures. The TianQin space-borne gravitational wave mission is scheduled for launch in the 2030s, with an operational lifespan of five years. It will facilitate pivotal insights into the history of our universe. This document presents a concise overview of the detectable sources of TianQin, outlining their characteristics, the challenges they present, and the expected impact of the TianQin observatory on our understanding of them., Comment: TianQin Gravitational Wave Whitepaper, 72 pages, 30 figures

As a space-borne gravitational wave observatory, TianQin can observe a large variety of gravitational wave sources. The rich signals can be composed by different types of astronomical systems, like Galactic compact binaries, inspiral of stellar mass black holes, merger of massive black holes, and extreme mass ratio inspirals. The incoherent summation of these signals can also form a stochastic gravitational wave background. Using the future TianQin observation, it is possible to put stringent constraints on fundamental science, like the expansion history of our universe. In this work, we provide a brief review of these topics that contributes to the 7th International Workshop on the TianQin Science Mission., Comment: Prepared for the proceeding of the 7th International Workshop on the TianQin Science Mission. 12 pages, 2 figures

Deformable medical image registration is a crucial aspect of medical image analysis. In recent years, researchers have begun leveraging auxiliary tasks (such as supervised segmentation) to provide anatomical structure information for the primary registration task, addressing complex deformation challenges in medical image registration. In this work, we propose a multi-task learning framework based on multi-scale dual attention frequency fusion (DAFF-Net), which simultaneously achieves the segmentation masks and dense deformation fields in a single-step estimation. DAFF-Net consists of a global encoder, a segmentation decoder, and a coarse-to-fine pyramid registration decoder. During the registration decoding process, we design the dual attention frequency feature fusion (DAFF) module to fuse registration and segmentation features at different scales, fully leveraging the correlation between the two tasks. The DAFF module optimizes the features through global and local weighting mechanisms. During local weighting, it incorporates both high-frequency and low-frequency information to further capture the features that are critical for the registration task. With the aid of segmentation, the registration learns more precise anatomical structure information, thereby enhancing the anatomical consistency of the warped images after registration. Additionally, due to the DAFF module's outstanding ability to extract effective feature information, we extend its application to unsupervised registration. Extensive experiments on three public 3D brain magnetic resonance imaging (MRI) datasets demonstrate that the proposed DAFF-Net and its unsupervised variant outperform state-of-the-art registration methods across several evaluation metrics, demonstrating the effectiveness of our approach in deformable medical image registration.

Recent advances in text-to-image diffusion models have spurred significant interest in continuous story image generation. In this paper, we introduce Storynizor, a model capable of generating coherent stories with strong inter-frame character consistency, effective foreground-background separation, and diverse pose variation. The core innovation of Storynizor lies in its key modules: ID-Synchronizer and ID-Injector. The ID-Synchronizer employs an auto-mask self-attention module and a mask perceptual loss across inter-frame images to improve the consistency of character generation, vividly representing their postures and backgrounds. The ID-Injector utilize a Shuffling Reference Strategy (SRS) to integrate ID features into specific locations, enhancing ID-based consistent character generation. Additionally, to facilitate the training of Storynizor, we have curated a novel dataset called StoryDB comprising 100, 000 images. This dataset contains single and multiple-character sets in diverse environments, layouts, and gestures with detailed descriptions. Experimental results indicate that Storynizor demonstrates superior coherent story generation with high-fidelity character consistency, flexible postures, and vivid backgrounds compared to other character-specific methods.

Infrared small target detection (IRSTD) is widely used in civilian and military applications. However, IRSTD encounters several challenges, including the tendency for small and dim targets to be obscured by complex backgrounds. To address this issue, we propose the Gradient Network (GaNet), which aims to extract and preserve edge and gradient information of small targets. GaNet employs the Gradient Transformer (GradFormer) module, simulating central difference convolutions (CDC) to extract and integrate gradient features with deeper features. Furthermore, we propose a global feature extraction model (GFEM) that offers a comprehensive perspective to prevent the network from focusing solely on details while neglecting the background information. We compare the network with state-of-the-art (SOTA) approaches, and the results demonstrate that our method performs effectively. Our source code is available at https://github.com/greekinRoma/Gradient-Transformer.

Partial Label Learning (PLL) is a typical weakly supervised learning task, which assumes each training instance is annotated with a set of candidate labels containing the ground-truth label. Recent PLL methods adopt identification-based disambiguation to alleviate the influence of false positive labels and achieve promising performance. However, they require all classes in the test set to have appeared in the training set, ignoring the fact that new classes will keep emerging in real applications. To address this issue, in this paper, we focus on the problem of Partial Label Learning with Augmented Class (PLLAC), where one or more augmented classes are not visible in the training stage but appear in the inference stage. Specifically, we propose an unbiased risk estimator with theoretical guarantees for PLLAC, which estimates the distribution of augmented classes by differentiating the distribution of known classes from unlabeled data and can be equipped with arbitrary PLL loss functions. Besides, we provide a theoretical analysis of the estimation error bound of the estimator, which guarantees the convergence of the empirical risk minimizer to the true risk minimizer as the number of training data tends to infinity. Furthermore, we add a risk-penalty regularization term in the optimization objective to alleviate the influence of the over-fitting issue caused by negative empirical risk. Extensive experiments on benchmark, UCI and real-world datasets demonstrate the effectiveness of the proposed approach., Comment: 17 pages

In modern healthcare, the demand for autonomous robotic assistants has grown significantly, particularly in the operating room, where surgical tasks require precision and reliability. Robotic scrub nurses have emerged as a promising solution to improve efficiency and reduce human error during surgery. However, challenges remain in terms of accurately grasping and handing over surgical instruments, especially when dealing with complex or difficult objects in dynamic environments. In this work, we introduce a novel robotic scrub nurse system, RoboNurse-VLA, built on a Vision-Language-Action (VLA) model by integrating the Segment Anything Model 2 (SAM 2) and the Llama 2 language model. The proposed RoboNurse-VLA system enables highly precise grasping and handover of surgical instruments in real-time based on voice commands from the surgeon. Leveraging state-of-the-art vision and language models, the system can address key challenges for object detection, pose optimization, and the handling of complex and difficult-to-grasp instruments. Through extensive evaluations, RoboNurse-VLA demonstrates superior performance compared to existing models, achieving high success rates in surgical instrument handovers, even with unseen tools and challenging items. This work presents a significant step forward in autonomous surgical assistance, showcasing the potential of integrating VLA models for real-world medical applications. More details can be found at https://robonurse-vla.github.io.

Recent advances indicate that diffusion models hold great promise in image super-resolution. While the latest methods are primarily based on latent diffusion models with convolutional neural networks, there are few attempts to explore transformers, which have demonstrated remarkable performance in image generation. In this work, we design an effective diffusion transformer for image super-resolution (DiT-SR) that achieves the visual quality of prior-based methods, but through a training-from-scratch manner. In practice, DiT-SR leverages an overall U-shaped architecture, and adopts a uniform isotropic design for all the transformer blocks across different stages. The former facilitates multi-scale hierarchical feature extraction, while the latter reallocates the computational resources to critical layers to further enhance performance. Moreover, we thoroughly analyze the limitation of the widely used AdaLN, and present a frequency-adaptive time-step conditioning module, enhancing the model's capacity to process distinct frequency information at different time steps. Extensive experiments demonstrate that DiT-SR outperforms the existing training-from-scratch diffusion-based SR methods significantly, and even beats some of the prior-based methods on pretrained Stable Diffusion, proving the superiority of diffusion transformer in image super-resolution., Comment: Code is available at https://github.com/kunncheng/DiT-SR

In the digital era, the ability to understand visually rich documents that integrate text, complex layouts, and imagery is critical. Traditional Key Information Extraction (KIE) methods primarily rely on Optical Character Recognition (OCR), which often introduces significant latency, computational overhead, and errors. Current advanced image-to-text approaches, which bypass OCR, typically yield plain text outputs without corresponding vision grounding. In this paper, we introduce STNet (See then Tell Net), a novel end-to-end model designed to deliver precise answers with relevant vision grounding. Distinctively, STNet utilizes a unique token to observe pertinent image areas, aided by a decoder that interprets physical coordinates linked to this token. Positioned at the outset of the answer text, the token allows the model to first see--observing the regions of the image related to the input question--and then tell--providing articulated textual responses. To enhance the model's seeing capabilities, we collect extensive structured table recognition datasets. Leveraging the advanced text processing prowess of GPT-4, we develop the TVG (TableQA with Vision Grounding) dataset, which not only provides text-based Question Answering (QA) pairs but also incorporates precise vision grounding for these pairs. Our approach demonstrates substantial advancements in KIE performance, achieving state-of-the-art results on publicly available datasets such as CORD, SROIE, and DocVQA. The code will also be made publicly available.

Cross-domain Recommendation (CDR) aims to alleviate the data sparsity and the cold-start problems in traditional recommender systems by leveraging knowledge from an informative source domain. However, previously proposed CDR models pursue an imprudent assumption that the entire information from the source domain is equally contributed to the target domain, neglecting the evil part that is completely irrelevant to users' intrinsic interest. To address this concern, in this paper, we propose a novel knowledge enhanced cross-domain recommendation framework named CoTrans, which remolds the core procedures of CDR models with: Compression on the knowledge from the source domain and Transfer of the purity to the target domain. Specifically, following the theory of Graph Information Bottleneck, CoTrans first compresses the source behaviors with the perception of information from the target domain. Then to preserve all the important information for the CDR task, the feedback signals from both domains are utilized to promote the effectiveness of the transfer procedure. Additionally, a knowledge-enhanced encoder is employed to narrow gaps caused by the non-overlapped items across separate domains. Comprehensive experiments on three widely used cross-domain datasets demonstrate that CoTrans significantly outperforms both single-domain and state-of-the-art cross-domain recommendation approaches., Comment: Accepted by CIKM 2024

Recent advancements in quantum polarization theory have propelled the exploration of topological insulators (TIs) into the realm of higher-order systems, leading to the study of the celebrated two-dimensional (2D) quadrupole and three-dimensional (3D) octupole TIs. Traditionally, these topological phases have been associated with the toroidal topology of the conventional Brillouin zone (BZ). This Letter reports on the discovery of a novel octupole topological insulating phase emerging within the framework of the Brillouin 3D real projective space ($\mathbb{RP}^3$). We theoretically propose the model and its corresponding topological invariant, experimentally construct this insulator within a topological circuit framework, and capture the octupole insulating phase as a localized impedance peak at the circuit's corner. Furthermore, our $\mathbb{RP}^3$ circuit stands out as a pioneering 3D model to simultaneously exhibit both intrinsic, termination-independent symmetry-protected topological phases (SPTPs) and extrinsic, termination-dependent boundary-obstructed topological phases (BOTPs), which broadly encompass 2D surface-obstructed topological phases (SOTPs) and 1D hinge-obstructed topological phases (HOTPs). Our results broaden the topological landscape and provide insights into the band theory within the manifold of the Brillouin $\mathbb{RP}^3$., Comment: 6 pages, 4 figures

This study explores the role of information entropy in understanding nuclear density distributions, including both stable configurations and non-traditional structures such as neutron halos and $\alpha$-clustering. By quantifying the uncertainty and disorder inherent in nucleon distributions in nuclear many-body systems, information entropy provides a macroscopic measure of the physical properties of the system. A more dispersed and disordered density distribution results in a higher value of information entropy. This intrinsic relationship between information entropy and system complexity allows us to quantify uncertainty and disorder in nuclear structures by analyzing various geometric parameters such as nuclear radius, diffuseness, neutron skin, and cluster structural features., Comment: 10 pages, 4 figures

Semantic trajectories, which enrich spatial-temporal data with textual information such as trip purposes or location activities, are key for identifying outlier behaviors critical to healthcare, social security, and urban planning. Traditional outlier detection relies on heuristic rules, which requires domain knowledge and limits its ability to identify unseen outliers. Besides, there lacks a comprehensive approach that can jointly consider multi-modal data across spatial, temporal, and textual dimensions. Addressing the need for a domain-agnostic model, we propose the Transferable Outlier Detection for Human Semantic Trajectories (TOD4Traj) framework.TOD4Traj first introduces a modality feature unification module to align diverse data feature representations, enabling the integration of multi-modal information and enhancing transferability across different datasets. A contrastive learning module is further pro-posed for identifying regular mobility patterns both temporally and across populations, allowing for a joint detection of outliers based on individual consistency and group majority patterns. Our experimental results have shown TOD4Traj's superior performance over existing models, demonstrating its effectiveness and adaptability in detecting human trajectory outliers across various datasets., Comment: This is an accepted paper on https://sigspatial2024.sigspatial.org/accepted-papers/

Large Language Models (LLMs) like GPT-4, LLaMA, and Qwen have demonstrated remarkable success across a wide range of applications. However, these models remain inherently vulnerable to prompt injection attacks, which can bypass existing safety mechanisms, highlighting the urgent need for more robust attack detection methods and comprehensive evaluation benchmarks. To address these challenges, we introduce GenTel-Safe, a unified framework that includes a novel prompt injection attack detection method, GenTel-Shield, along with a comprehensive evaluation benchmark, GenTel-Bench, which compromises 84812 prompt injection attacks, spanning 3 major categories and 28 security scenarios. To prove the effectiveness of GenTel-Shield, we evaluate it together with vanilla safety guardrails against the GenTel-Bench dataset. Empirically, GenTel-Shield can achieve state-of-the-art attack detection success rates, which reveals the critical weakness of existing safeguarding techniques against harmful prompts. For reproducibility, we have made the code and benchmarking dataset available on the project page at https://gentellab.github.io/gentel-safe.github.io/.

Despite significant advancements in large language models (LLMs) that enhance robot agents' understanding and execution of natural language (NL) commands, ensuring the agents adhere to user-specified constraints remains challenging, particularly for complex commands and long-horizon tasks. To address this challenge, we present three key insights, equivalence voting, constrained decoding, and domain-specific fine-tuning, which significantly enhance LLM planners' capability in handling complex tasks. Equivalence voting ensures consistency by generating and sampling multiple Linear Temporal Logic (LTL) formulas from NL commands, grouping equivalent LTL formulas, and selecting the majority group of formulas as the final LTL formula. Constrained decoding then uses the generated LTL formula to enforce the autoregressive inference of plans, ensuring the generated plans conform to the LTL. Domain-specific fine-tuning customizes LLMs to produce safe and efficient plans within specific task domains. Our approach, Safe Efficient LLM Planner (SELP), combines these insights to create LLM planners to generate plans adhering to user commands with high confidence. We demonstrate the effectiveness and generalizability of SELP across different robot agents and tasks, including drone navigation and robot manipulation. For drone navigation tasks, SELP outperforms state-of-the-art planners by 10.8% in safety rate (i.e., finishing tasks conforming to NL commands) and by 19.8% in plan efficiency. For robot manipulation tasks, SELP achieves 20.4% improvement in safety rate. Our datasets for evaluating NL-to-LTL and robot task planning will be released in github.com/lt-asset/selp.

Deep Multi-agent Reinforcement Learning (MARL) relies on neural networks with numerous parameters in multi-agent scenarios, often incurring substantial computational overhead. Consequently, there is an urgent need to expedite training and enable model compression in MARL. This paper proposes the utilization of dynamic sparse training (DST), a technique proven effective in deep supervised learning tasks, to alleviate the computational burdens in MARL training. However, a direct adoption of DST fails to yield satisfactory MARL agents, leading to breakdowns in value learning within deep sparse value-based MARL models. Motivated by this challenge, we introduce an innovative Multi-Agent Sparse Training (MAST) framework aimed at simultaneously enhancing the reliability of learning targets and the rationality of sample distribution to improve value learning in sparse models. Specifically, MAST incorporates the Soft Mellowmax Operator with a hybrid TD-($\lambda$) schema to establish dependable learning targets. Additionally, it employs a dual replay buffer mechanism to enhance the distribution of training samples. Building upon these aspects, MAST utilizes gradient-based topology evolution to exclusively train multiple MARL agents using sparse networks. Our comprehensive experimental investigation across various value-based MARL algorithms on multiple benchmarks demonstrates, for the first time, significant reductions in redundancy of up to $20\times$ in Floating Point Operations (FLOPs) for both training and inference, with less than $3\%$ performance degradation.

Vision-language foundation models (e.g., CLIP) have shown remarkable performance across a wide range of tasks. However, deploying these models may be unreliable when significant distribution gaps exist between the training and test data. The training-free test-time dynamic adapter (TDA) is a promising approach to address this issue by storing representative test samples to guide the classification of subsequent ones. However, TDA only naively maintains a limited number of reference samples in the cache, leading to severe test-time catastrophic forgetting when the cache is updated by dropping samples. In this paper, we propose a simple yet effective method for DistributiOnal Test-time Adaptation (Dota). Instead of naively memorizing representative test samples, Dota continually estimates the distributions of test samples, allowing the model to continually adapt to the deployment environment. The test-time posterior probabilities are then computed using the estimated distributions based on Bayes' theorem for adaptation purposes. To further enhance the adaptability on the uncertain samples, we introduce a new human-in-the-loop paradigm which identifies uncertain samples, collects human-feedback, and incorporates it into the Dota framework. Extensive experiments validate that Dota enables CLIP to continually learn, resulting in a significant improvement compared to current state-of-the-art methods., Comment: In submission

The accomplished functions of a variety of quantum devices are closely associated with the controlling of exciton transport. To this end we study the exciton transport of the two-dimensional system consisting of two-level multichains with various coupling configurations in a cavity. Two types of the chains are considered, including Tavis-Cummings and Su-Schrieffer-Heeger chain. Two conformations of the coupling between chains are considered, including square and triangle type. The effects of the inter-chain coupling, dimerization parameter, the cavity, the length of chains, and the number of chains on the exciton transport are in detail investigated for different coupling configurations of the multi-chain system through spectra and steady-state dynamics. The results show that in the absence of a cavity the exciton transport effciency is decided by the distribution of population of exciton on whole chains. However, when the cavity is considered the exciton transport currents and effciency of the system is controlled by the cavity-dressed energy level crossings and anticrossings near zero-energy modes, at which the coherent excitation and Landau-Zener transitions occur. Therefore, the exciton transport can be enhanced or suppressed at the crossings and anticrossings, in which the polariton acts as crucial role. Besides, it is discovered that the exciton transport effciency is closely related with the parity of both the length and the number of chains. This work is important for the understanding of the exciton transport mechanism in the multichain-cavity system, and provides theoretical basis for excitonic devices with controllable and effcient exciton transport.

In materials science, data-driven methods accelerate material discovery and optimization while reducing costs and improving success rates. Symbolic regression is a key to extracting material descriptors from large datasets, in particular the Sure Independence Screening and Sparsifying Operator (SISSO) method. While SISSO needs to store the entire expression space to impose heavy memory demands, it limits the performance in complex problems. To address this issue, we propose a RF-SISSO algorithm by combining Random Forests (RF) with SISSO. In this algorithm, the Random Forest algorithm is used for prescreening, capturing non-linear relationships and improving feature selection, which may enhance the quality of the input data and boost the accuracy and efficiency on regression and classification tasks. For a testing on the SISSO's verification problem for 299 materials, RF-SISSO demonstrates its robust performance and high accuracy. RF-SISSO can maintain the testing accuracy above 0.9 across all four training sample sizes and significantly enhancing regression efficiency, especially in training subsets with smaller sample sizes. For the training subset with 45 samples, the efficiency of RF-SISSO was 265 times higher than that of original SISSO. As collecting large datasets would be both costly and time-consuming in the practical experiments, it is thus believed that RF-SISSO may benefit scientific researches by offering a high predicting accuracy with limited data efficiently.

As Large Language Models (LLMs) grow increasingly adept at managing complex tasks, the evaluation set must keep pace with these advancements to ensure it remains sufficiently discriminative. Item Discrimination (ID) theory, which is widely used in educational assessment, measures the ability of individual test items to differentiate between high and low performers. Inspired by this theory, we propose an ID-induced prompt synthesis framework for evaluating LLMs to ensure the evaluation set can continually update and refine according to model abilities. Our data synthesis framework prioritizes both breadth and specificity. It can generate prompts that comprehensively evaluate the capabilities of LLMs while revealing meaningful performance differences between models, allowing for effective discrimination of their relative strengths and weaknesses across various tasks and domains. To produce high-quality data, we incorporate a self-correct mechanism into our generalization framework, and develop two models to predict prompt discrimination and difficulty score to facilitate our data synthesis framework, contributing valuable tools to evaluation data synthesis research. We apply our generated data to evaluate five SOTA models. Our data achieves an average score of 51.92, accompanied by a variance of 10.06. By contrast, previous works (i.e., SELF-INSTRUCT and WizardLM) obtain an average score exceeding 67, with a variance below 3.2. The results demonstrate that the data generated by our framework is more challenging and discriminative compared to previous works. We will release a dataset of over 3,000 carefully crafted prompts to facilitate evaluation research of LLMs., Comment: NeurIPS 2024

Accurate identification and categorization of suicidal events can yield better suicide precautions, reducing operational burden, and improving care quality in high-acuity psychiatric settings. Pre-trained language models offer promise for identifying suicidality from unstructured clinical narratives. We evaluated the performance of four BERT-based models using two fine-tuning strategies (multiple single-label and single multi-label) for detecting coexisting suicidal events from 500 annotated psychiatric evaluation notes. The notes were labeled for suicidal ideation (SI), suicide attempts (SA), exposure to suicide (ES), and non-suicidal self-injury (NSSI). RoBERTa outperformed other models using multiple single-label classification strategy (acc=0.86, F1=0.78). MentalBERT (acc=0.83, F1=0.74) also exceeded BioClinicalBERT (acc=0.82, F1=0.72) which outperformed BERT (acc=0.80, F1=0.70). RoBERTa fine-tuned with single multi-label classification further improved the model performance (acc=0.88, F1=0.81). The findings highlight that the model optimization, pretraining with domain-relevant data, and the single multi-label classification strategy enhance the model performance of suicide phenotyping. Keywords: EHR-based Phenotyping; Natural Language Processing; Secondary Use of EHR Data; Suicide Classification; BERT-based Model; Psychiatry; Mental Health, Comment: submitted to AMIA Informatics Summit 2025 as a conference paper

Scattering obscures information carried by wave by producing a speckle pattern, posing a common challenge across various fields, including microscopy and astronomy. Traditional methods for extracting information from speckles often rely on significant physical assumptions, complex devices, or intricate algorithms. Recently, machine learning has emerged as a scalable and widely adopted tool for interpreting speckle patterns. However, most current machine learning techniques depend heavily on supervised training with extensive labeled datasets, which is problematic when labels are unavailable. To address this, we propose a strategy based on unsupervised learning for speckle recognition and evaluation, enabling to capture high-level information, such as object classes, directly from speckles without labeled data. By deriving invariant features from speckles, this method allows for the classification of speckles and facilitates diverse applications in image sensing. We experimentally validated our strategy through two significant applications: a noninvasive glucose monitoring system capable of differentiating time-lapse glucose concentrations, and a high-throughput communication system utilizing multimode fibers in dynamic environments. The versatility of this method holds promise for a broad range of far-reaching applications, including biomedical diagnostics, quantum network decoupling, and remote sensing.

Privacy leakage and Byzantine failures are two adverse factors to the intelligent decision-making process of multi-agent systems (MASs). Considering the presence of these two issues, this paper targets the resolution of a class of nonconvex optimization problems under the Polyak-{\L}ojasiewicz (P-{\L}) condition. To address this problem, we first identify and construct the adversary system model. To enhance the robustness of stochastic gradient descent methods, we mask the local gradients with Gaussian noises and adopt a resilient aggregation method self-centered clipping (SCC) to design a differentially private (DP) decentralized Byzantine-resilient algorithm, namely DP-SCC-PL, which simultaneously achieves differential privacy and Byzantine resilience. The convergence analysis of DP-SCC-PL is challenging since the convergence error can be contributed jointly by privacy-preserving and Byzantine-resilient mechanisms, as well as the nonconvex relaxation, which is addressed via seeking the contraction relationships among the disagreement measure of reliable agents before and after aggregation, together with the optimal gap. Theoretical results reveal that DP-SCC-PL achieves consensus among all reliable agents and sublinear (inexact) convergence with well-designed step-sizes. It has also been proved that if there are no privacy issues and Byzantine agents, then the asymptotic exact convergence can be recovered. Numerical experiments verify the utility, resilience, and differential privacy of DP-SCC-PL by tackling a nonconvex optimization problem satisfying the P-{\L} condition under various Byzantine attacks., Comment: 13 pages, 13 figures

This paper introduces the model structure used in the SVDD 2024 Challenge. The SVDD 2024 challenge has been introduced this year for the first time. Singing voice deepfake detection (SVDD) which faces complexities due to informal speech intonations and varying speech rates. In this paper, we propose the XWSB system, which achieved SOTA per-formance in the SVDD challenge. XWSB stands for XLS-R, WavLM, and SLS Blend, representing the integration of these technologies for the purpose of SVDD. Specifically, we used the best performing model structure XLS-R&SLS from the ASVspoof DF dataset, and applied SLS to WavLM to form the WavLM&SLS structure. Finally, we integrated two models to form the XWSB system. Experimental results show that our system demonstrates advanced recognition capabilities in the SVDD challenge, specifically achieving an EER of 2.32% in the CtrSVDD track. The code and data can be found at https://github.com/QiShanZhang/XWSB_for_ SVDD2024.

Diffusion transformers have gained substantial interest in diffusion generative modeling due to their outstanding performance. However, their high computational cost, arising from the quadratic computational complexity of attention mechanisms and multi-step inference, presents a significant bottleneck. To address this challenge, we propose TokenCache, a novel post-training acceleration method that leverages the token-based multi-block architecture of transformers to reduce redundant computations among tokens across inference steps. TokenCache specifically addresses three critical questions in the context of diffusion transformers: (1) which tokens should be pruned to eliminate redundancy, (2) which blocks should be targeted for efficient pruning, and (3) at which time steps caching should be applied to balance speed and quality. In response to these challenges, TokenCache introduces a Cache Predictor that assigns importance scores to tokens, enabling selective pruning without compromising model performance. Furthermore, we propose an adaptive block selection strategy to focus on blocks with minimal impact on the network's output, along with a Two-Phase Round-Robin (TPRR) scheduling policy to optimize caching intervals throughout the denoising process. Experimental results across various models demonstrate that TokenCache achieves an effective trade-off between generation quality and inference speed for diffusion transformers. Our code will be publicly available.

The stable periodic patterns present in time series data serve as the foundation for conducting long-horizon forecasts. In this paper, we pioneer the exploration of explicitly modeling this periodicity to enhance the performance of models in long-term time series forecasting (LTSF) tasks. Specifically, we introduce the Residual Cycle Forecasting (RCF) technique, which utilizes learnable recurrent cycles to model the inherent periodic patterns within sequences, and then performs predictions on the residual components of the modeled cycles. Combining RCF with a Linear layer or a shallow MLP forms the simple yet powerful method proposed in this paper, called CycleNet. CycleNet achieves state-of-the-art prediction accuracy in multiple domains including electricity, weather, and energy, while offering significant efficiency advantages by reducing over 90% of the required parameter quantity. Furthermore, as a novel plug-and-play technique, the RCF can also significantly improve the prediction accuracy of existing models, including PatchTST and iTransformer. The source code is available at: https://github.com/ACAT-SCUT/CycleNet., Comment: NeurIPS 2024 Spotlight

We develop a microscopic theory of the spin Seebeck effect (SSE) at the interface of a bilayer system of a ferromagnetic insulator and graphene. We compare the tunneling spin current at the interface due to the SSE and the spin pumping (SP), where the SSE and SP are induced by the temperature gradient and the microwave irradiation, respectively. We demonstrate that the thermally driven SSE exhibits a quantum oscillation pattern similar to that predicted in coherently driven SP. Additionally, we show a peak shift of the quantum oscillation due to the contribution of thermally excited magnons with higher frequencies, which becomes particularly pronounced at higher temperatures.

This paper presents a novel weakly supervised semantic segmentation method for radar segmentation, where the existing LiDAR semantic segmentation models are employed to generate semantic labels, which then serve as supervision signals for training a radar semantic segmentation model. The obtained radar semantic segmentation model outperforms LiDAR-based models, providing more consistent and robust segmentation under all-weather conditions, particularly in the snow, rain and fog. To mitigate potential errors in LiDAR semantic labels, we design a dedicated refinement scheme that corrects erroneous labels based on structural features and distribution patterns. The semantic information generated by our radar segmentation model is used in two downstream tasks, achieving significant performance improvements. In large-scale radar-based localization using OpenStreetMap, it leads to localization error reduction by 20.55\% over prior methods. For the odometry task, it improves translation accuracy by 16.4\% compared to the second-best method, securing the first place in the radar odometry competition at the Radar in Robotics workshop of ICRA 2024, Japan

Electroencephalogram-based brain-computer interface (BCI) has potential applications in various fields, but their development is hindered by limited data and significant cross-individual variability. Inspired by the principles of learning and memory in the human hippocampus, we propose a multi-task (MT) classification model, called AM-MTEEG, which combines learning-based impulsive neural representations with bidirectional associative memory (AM) for cross-individual BCI classification tasks. The model treats the EEG classification of each individual as an independent task and facilitates feature sharing across individuals. Our model consists of an impulsive neural population coupled with a convolutional encoder-decoder to extract shared features and a bidirectional associative memory matrix to map features to class. Experimental results in two BCI competition datasets show that our model improves average accuracy compared to state-of-the-art models and reduces performance variance across individuals, and the waveforms reconstructed by the bidirectional associative memory provide interpretability for the model's classification results. The neuronal firing patterns in our model are highly coordinated, similarly to the neural coding of hippocampal neurons, indicating that our model has biological similarities.

We present spectroscopic and photometric observations of Bernhard-2, which was previously identified as a candidate system to host a misaligned circumbinary disk. Our spectroscopic measurements confirm that Bernhard-2 indeed contains an eccentric ($e=0.69 \pm 0.08$) binary and thus that the periodic variability in the photometric light curve is best explained by the occultation by the misaligned circumbinary disk. By modeling the spectral energy distributions at different phases, we infer the system age to be $\sim 20\,$Myr and the masses of the two binary components to be $\sim 1.1\,M_\odot$ and $\sim 0.9\,M_\odot$, respectively. Our new photometric observations show clear deviations from the model prediction based on the archival data, suggesting ongoing precession of the circumbinary disk. The H$\alpha$ line of Bernhard-2 also shows an inverse P-Cygni profile at epochs close to the pericenter passage, which could be attributed to the pulsed accretion around the pericenter. Bernhard-2 therefore closely resembles the well studied KH 15D system. Further detailed observations and studies of such rare systems can provide useful information about disk physics and evolution., Comment: 10 pages, 4 figures, submitted to AAS Journals, comments welcome

Field-of-View (FoV) adaptive streaming significantly reduces bandwidth requirement of immersive point cloud video (PCV) by only transmitting visible points in a viewer's FoV. The traditional approaches often focus on trajectory-based 6 degree-of-freedom (6DoF) FoV predictions. The predicted FoV is then used to calculate point visibility. Such approaches do not explicitly consider video content's impact on viewer attention, and the conversion from FoV to point visibility is often error-prone and time-consuming. We reformulate the PCV FoV prediction problem from the cell visibility perspective, allowing for precise decision-making regarding the transmission of 3D data at the cell level based on the predicted visibility distribution. We develop a novel spatial visibility and object-aware graph model that leverages the historical 3D visibility data and incorporates spatial perception, neighboring cell correlation, and occlusion information to predict the cell visibility in the future. Our model significantly improves the long-term cell visibility prediction, reducing the prediction MSE loss by up to 50% compared to the state-of-the-art models while maintaining real-time performance (more than 30fps) for point cloud videos with over 1 million points.

Recent research demonstrates that the nascent fine-tuning-as-a-service business model exposes serious safety concerns -- fine-tuning over a few harmful data uploaded by the users can compromise the safety alignment of the model. The attack, known as harmful fine-tuning, has raised a broad research interest among the community. However, as the attack is still new, \textbf{we observe from our miserable submission experience that there are general misunderstandings within the research community.} We in this paper aim to clear some common concerns for the attack setting, and formally establish the research problem. Specifically, we first present the threat model of the problem, and introduce the harmful fine-tuning attack and its variants. Then we systematically survey the existing literature on attacks/defenses/mechanical analysis of the problem. Finally, we outline future research directions that might contribute to the development of the field. Additionally, we present a list of questions of interest, which might be useful to refer to when reviewers in the peer review process question the realism of the experiment/attack/defense setting. A curated list of relevant papers is maintained and made accessible at: \url{https://github.com/git-disl/awesome_LLM-harmful-fine-tuning-papers}.

We propose a novel unsupervised cross-modal homography estimation framework, based on interleaved modality transfer and self-supervised homography prediction, named InterNet. InterNet integrates modality transfer and self-supervised homography estimation, introducing an innovative interleaved optimization framework to alternately promote both components. The modality transfer gradually narrows the modality gaps, facilitating the self-supervised homography estimation to fully leverage the synthetic intra-modal data. The self-supervised homography estimation progressively achieves reliable predictions, thereby providing robust cross-modal supervision for the modality transfer. To further boost the estimation accuracy, we also formulate a fine-grained homography feature loss to improve the connection between two components. Furthermore, we employ a simple yet effective distillation training technique to reduce model parameters and improve cross-domain generalization ability while maintaining comparable performance. Experiments reveal that InterNet achieves the state-of-the-art (SOTA) performance among unsupervised methods, and even outperforms many supervised methods such as MHN and LocalTrans.

Segment Anything Model (SAM) has recently gained much attention for its outstanding generalization to unseen data and tasks. Despite its promising prospect, the vulnerabilities of SAM, especially to universal adversarial perturbation (UAP) have not been thoroughly investigated yet. In this paper, we propose DarkSAM, the first prompt-free universal attack framework against SAM, including a semantic decoupling-based spatial attack and a texture distortion-based frequency attack. We first divide the output of SAM into foreground and background. Then, we design a shadow target strategy to obtain the semantic blueprint of the image as the attack target. DarkSAM is dedicated to fooling SAM by extracting and destroying crucial object features from images in both spatial and frequency domains. In the spatial domain, we disrupt the semantics of both the foreground and background in the image to confuse SAM. In the frequency domain, we further enhance the attack effectiveness by distorting the high-frequency components (i.e., texture information) of the image. Consequently, with a single UAP, DarkSAM renders SAM incapable of segmenting objects across diverse images with varying prompts. Experimental results on four datasets for SAM and its two variant models demonstrate the powerful attack capability and transferability of DarkSAM., Comment: This paper has been accepted by the 38th Annual Conference on Neural Information Processing Systems (NeurIPS'24)

In this paper, we completely classify the canonical threefolds on the Noether line with geometric genus $p_g \ge 11$ by studying their moduli spaces. For every such moduli space, we establish an explicit stratification, estimate the number of its irreducible components and prove the dimension formula. A new and unexpected phenomenon is that the number of irreducible components grows linearly with the geometric genus, while the moduli space of canonical surfaces on the Noether line with any prescribed geometric genus has at most two irreducible components. The key idea in the proof is to relate the canonical threefolds on the Noether line to the simple fibrations in $(1, 2)$-surfaces by proving a conjecture stated by two of the authors in [CP]., Comment: Comments are welcome

In the smoothed particle dynamics (SPH) method, the characteristics of a target particle are interpolated based on the information from its neighboring particles. Consequently, a uniform initial distribution of particles significantly enhances the accuracy of SPH calculations. This aspect is particularly critical in Eulerian SPH, where particles are stationary throughout the simulation. To address this, we introduce a physics-driven complex relaxation method for multi-body systems. Through a series of two-dimensional and three-dimensional case studies, we demonstrate that this method is capable of achieving a globally uniform particle distribution, especially at the interfaces between contacting bodies, and ensuring improved zero-order consistency. Moreover, the effectiveness and reliability of the complex relaxation method in enhancing the accuracy of physical simulations are further validated., Comment: 38 pages and 25 figures

Large-scale pre-trained Vision-Language Models (VLMs) have gained prominence in various visual and multimodal tasks, yet the deployment of VLMs on downstream application platforms remains challenging due to their prohibitive requirements of training samples and computing resources. Fine-tuning and quantization of VLMs can substantially reduce the sample and computation costs, which are in urgent need. There are two prevailing paradigms in quantization, Quantization-Aware Training (QAT) can effectively quantize large-scale VLMs but incur a huge training cost, while low-bit Post-Training Quantization (PTQ) suffers from a notable performance drop. We propose a method that balances fine-tuning and quantization named ``Prompt for Quantization'' (P4Q), in which we design a lightweight architecture to leverage contrastive loss supervision to enhance the recognition performance of a PTQ model. Our method can effectively reduce the gap between image features and text features caused by low-bit quantization, based on learnable prompts to reorganize textual representations and a low-bit adapter to realign the distributions of image and text features. We also introduce a distillation loss based on cosine similarity predictions to distill the quantized model using a full-precision teacher. Extensive experimental results demonstrate that our P4Q method outperforms prior arts, even achieving comparable results to its full-precision counterparts. For instance, our 8-bit P4Q can theoretically compress the CLIP-ViT/B-32 by 4 $\times$ while achieving 66.94\% Top-1 accuracy, outperforming the learnable prompt fine-tuned full-precision model by 2.24\% with negligible additional parameters on the ImageNet dataset.

Quantum simulators are ideal platforms to investigate quantum phenomena that are inaccessible through conventional means, such as the limited resources of classical computers to address large quantum systems or due to constraints imposed by fundamental laws of nature. Here, through a digitized adiabatic evolution, we report an experimental simulation of antiferromagnetic (AFM) and ferromagnetic (FM) phase formation induced by spontaneous symmetry breaking (SSB) in a three-generation Cayley tree-like superconducting lattice. We develop a digital quantum annealing algorithm to mimic the system dynamics, and observe the emergence of signatures of SSB-induced phase transition through a connected correlation function. We demonstrate that the signature of phase transition from classical AFM to quantum FM happens in systems undergoing zero-temperature adiabatic evolution with only nearest-neighbor interacting systems, the shortest range of interaction possible. By harnessing properties of the bipartite Renyi entropy as an entanglement witness, we observe the formation of entangled quantum FM and AFM phases. Our results open perspectives for new advances in condensed matter physics and digitized quantum annealing.

The sharp increase in data-related expenses has motivated research into condensing datasets while retaining the most informative features. Dataset distillation has thus recently come to the fore. This paradigm generates synthetic dataset that are representative enough to replace the original dataset in training a neural network. To avoid redundancy in these synthetic datasets, it is crucial that each element contains unique features and remains diverse from others during the synthesis stage. In this paper, we provide a thorough theoretical and empirical analysis of diversity within synthesized datasets. We argue that enhancing diversity can improve the parallelizable yet isolated synthesizing approach. Specifically, we introduce a novel method that employs dynamic and directed weight adjustment techniques to modulate the synthesis process, thereby maximizing the representativeness and diversity of each synthetic instance. Our method ensures that each batch of synthetic data mirrors the characteristics of a large, varying subset of the original dataset. Extensive experiments across multiple datasets, including CIFAR, Tiny-ImageNet, and ImageNet-1K, demonstrate the superior performance of our method, highlighting its effectiveness in producing diverse and representative synthetic datasets with minimal computational expense.

Video anomaly detection (VAD) often learns the distribution of normal samples and detects the anomaly through measuring significant deviations, but the undesired generalization may reconstruct a few anomalies thus suppressing the deviations. Meanwhile, most VADs cannot cope with cross-dataset validation for new target domains, and few-shot methods must laboriously rely on model-tuning from the target domain to complete domain adaptation. To address these problems, we propose a novel VAD method with a motion-guided memory module to achieve cross-dataset validation with zero-shot. First, we add Gaussian blur to the raw appearance images, thereby constructing the global pseudo-anomaly, which serves as the input to the network. Then, we propose multi-scale residual channel attention to deblur the pseudo-anomaly in normal samples. Next, memory items are obtained by recording the motion features in the training phase, which are used to retrieve the motion features from the raw information in the testing phase. Lastly, our method can ignore the blurred real anomaly through attention and rely on motion memory items to increase the normality gap between normal and abnormal motion. Extensive experiments on three benchmark datasets demonstrate the effectiveness of the proposed method. Compared with cross-domain methods, our method achieves competitive performance without adaptation during testing., Comment: 13 pages, 11 figures

Window-based transformers have demonstrated outstanding performance in super-resolution tasks due to their adaptive modeling capabilities through local self-attention (SA). However, they exhibit higher computational complexity and inference latency than convolutional neural networks. In this paper, we first identify that the adaptability of the Transformers is derived from their adaptive spatial aggregation and advanced structural design, while their high latency results from the computational costs and memory layout transformations associated with the local SA. To simulate this aggregation approach, we propose an effective convolution-based linear focal separable attention (FSA), allowing for long-range dynamic modeling with linear complexity. Additionally, we introduce an effective dual-branch structure combined with an ultra-lightweight information exchange module (IEM) to enhance the aggregation of information by the Token Mixer. Finally, with respect to the structure, we modify the existing spatial-gate-based feedforward neural networks by incorporating a self-gate mechanism to preserve high-dimensional channel information, enabling the modeling of more complex relationships. With these advancements, we construct a convolution-based Transformer framework named the linear adaptive mixer network (LAMNet). Extensive experiments demonstrate that LAMNet achieves better performance than existing SA-based Transformer methods while maintaining the computational efficiency of convolutional neural networks, which can achieve a \(3\times\) speedup of inference time. The code will be publicly available at: https://github.com/zononhzy/LAMNet.

The demand for low-power devices is on the rise as semiconductor engineering approaches the quantum limit and quantum computing continues to advance. Two-dimensional (2D) superconductors, thanks to their rich physical properties, hold significant promise for both fundamental physics and potential applications in superconducting integrated circuits and quantum computation. Here, we report a gate-controlled superconducting switch in GaSe/NbSe$_2$ van der Waals (vdW) heterostructure. By injecting high-energy electrons into NbSe$_2$ under an electric field, a non-equilibrium state is induced, resulting in significant modulation of the superconducting properties. Owing to the intrinsic polarization of ferroelectric GaSe, a much steeper subthreshold slope and asymmetric modulation are achieved, which is beneficial to the device performance. Based on these results, a superconducting switch is realized that can reversibly and controllably switch between the superconducting and normal state under an electric field. Our findings highlight a significant high-energy injection effect from band engineering in 2D vdW heterostructures combining superconductors and ferroelectric semiconductors, and demonstrate the potential applications for superconducting integrated circuits., Comment: 19 pages, 5 figures

Topological physics provides novel insights for designing functional photonic devices, such as magnetic-free optical diodes, which are important in optical engineering and quantum information processing. Past efforts mostly focus on the topological edge modes in two-dimensional (2D) photonic Chern lattices, which, however, require delicate fabrication and temporal modulation. In particular, the 1D nonreciprocal edge mode needs to be embedded in a 2D lattice, contradicting with the compactness of integrated photonics. To address these challenges, we investigate the optical nonreciprocity of the 1D Su-Schrieffer-Heeger (SSH) superradiance lattices in room-temperature atoms. The probe fields propagating in two opposite directions perceive two different SSH topological phases, which have different absorption spectra due to the interplay between the Zak phase and the thermal motion of atoms, resulting in optical nonreciprocity. Our findings reveal the relationship between 1D topological matter and optical nonreciprocity, simplifying the design of topologically resilient nonreciprocal devices., Comment: 4 figures

Semantic communication technology emerges as a pivotal bridge connecting AI with classical communication. The current semantic communication systems are generally modeled as an Auto-Encoder (AE). AE lacks a deep integration of AI principles with communication strategies due to its inability to effectively capture channel dynamics. This gap makes it difficult to justify the need for joint source-channel coding (JSCC) and to explain why performance improves. This paper begins by exploring lossless and lossy communication, highlighting that the inclusion of data distortion distinguishes semantic communication from classical communication. It breaks the conditions for the separation theorem to hold and explains why the amount of data transferred by semantic communication is less. Therefore, employing JSCC becomes imperative for achieving optimal semantic communication. Moreover, a Variational Source-Channel Coding (VSCC) method is proposed for constructing semantic communication systems based on data distortion theory, integrating variational inference and channel characteristics. Using a deep learning network, we develop a semantic communication system employing the VSCC method and demonstrate its capability for semantic transmission. We also establish semantic communication systems of equivalent complexity employing the AE method and the VAE method. Experimental results reveal that the VSCC model offers superior interpretability compared to AE model, as it clearly captures the semantic features of the transmitted data, represented as the variance of latent variables in our experiments. In addition, VSCC model exhibits superior semantic transmission capabilities compared to VAE model. At the same level of data distortion evaluated by PSNR, VSCC model exhibits stronger human interpretability, which can be partially assessed by SSIM.

Multi-modal large language models (MLLMs) have shown impressive capabilities as a general-purpose interface for various visual and linguistic tasks. However, building a unified MLLM for multi-task learning in the medical field remains a thorny challenge. To mitigate the tug-of-war problem of multi-modal multi-task optimization, recent advances primarily focus on improving the LLM components, while neglecting the connector that bridges the gap between modalities. In this paper, we introduce Uni-Med, a novel medical generalist foundation model which consists of a universal visual feature extraction module, a connector mixture-of-experts (CMoE) module, and an LLM. Benefiting from the proposed CMoE that leverages a well-designed router with a mixture of projection experts at the connector, Uni-Med achieves efficient solution to the tug-of-war problem and can perform six different medical tasks including question answering, visual question answering, report generation, referring expression comprehension, referring expression generation and image classification. To the best of our knowledge, Uni-Med is the first effort to tackle multi-task interference at the connector. Extensive ablation experiments validate the effectiveness of introducing CMoE under any configuration, with up to an average 8% performance gains. We further provide interpretation analysis of the tug-of-war problem from the perspective of gradient optimization and parameter statistics. Compared to previous state-of-the-art medical MLLMs, Uni-Med achieves competitive or superior evaluation metrics on diverse tasks. Code, data and model will be soon available at GitHub.

Distributed learning is essential to train machine learning algorithms across heterogeneous agents while maintaining data privacy. We conduct an asymptotic analysis of Unified Distributed SGD (UD-SGD), exploring a variety of communication patterns, including decentralized SGD and local SGD within Federated Learning (FL), as well as the increasing communication interval in the FL setting. In this study, we assess how different sampling strategies, such as i.i.d. sampling, shuffling, and Markovian sampling, affect the convergence speed of UD-SGD by considering the impact of agent dynamics on the limiting covariance matrix as described in the Central Limit Theorem (CLT). Our findings not only support existing theories on linear speedup and asymptotic network independence, but also theoretically and empirically show how efficient sampling strategies employed by individual agents contribute to overall convergence in UD-SGD. Simulations reveal that a few agents using highly efficient sampling can achieve or surpass the performance of the majority employing moderately improved strategies, providing new insights beyond traditional analyses focusing on the worst-performing agent., Comment: To appear in NeurIPS 2024

The curvature of ODE trajectories in diffusion models hinders their ability to generate high-quality images in a few number of function evaluations (NFE). In this paper, we propose a novel and effective approach to reduce trajectory curvature by utilizing adaptive conditions. By employing a extremely light-weight quantized encoder, our method incurs only an additional 1% of training parameters, eliminates the need for extra regularization terms, yet achieves significantly better sample quality. Our approach accelerates ODE sampling while preserving the downstream task image editing capabilities of SDE techniques. Extensive experiments verify that our method can generate high quality results under extremely limited sampling costs. With only 6 NFE, we achieve 5.14 FID on CIFAR-10, 6.91 FID on FFHQ 64x64 and 3.10 FID on AFHQv2.

For the discretization of symmetric, divergence-conforming stress tensors in continuum mechanics, we prove inf-sup stability bounds which are uniform in polynomial degree and mesh size for the Hu--Zhang finite element in two dimensions. This is achieved via an explicit construction of a bounded right inverse of the divergence operator, with the crucial component being the construction of bounded Poincar\'e operators for the stress elasticity complex which are polynomial-preserving, in the Bernstein--Gelfand--Gelfand framework of the finite element exterior calculus. We also construct $hp$-bounded projection operators satisfying a commuting diagram property and $hp$-stable Hodge decompositions. Numerical examples are provided.

We present photometric and spectroscopic observations of SN2020xga and SN2022xgc, two hydrogen-poor superluminous supernovae (SLSNe-I) at $z = 0.4296$ and $z = 0.3103$ respectively, that show an additional set of broad Mg II absorption lines, blueshifted by a few thousand km s$^{-1}$ with respect to the host galaxy absorption system. Previous work interpreted this as due to resonance line scattering of the SLSN continuum by rapidly expanding CSM expelled shortly before the explosion. The peak rest-frame $g$-band magnitude of SN2020xga is $-22.30 \pm 0.04$ mag and of SN2022xgc is $-21.97 \pm 0.05$ mag, placing them among the brightest SLSNe-I. We use high-quality spectra from ultraviolet to near-infrared wavelengths to model the Mg II line profiles and infer the properties of the CSM shells. We find that the CSM shell of SN2020xga resides at $\sim 1.3 \times 10^{16} \rm cm$ moving with a maximum velocity of $4275~\rm km~s^{-1}$, and the shell of SN2022xgc is located at $\sim 0.8 \times 10^{16} \rm cm$ reaching up to $4400~\rm km~s^{-1}$. These shells were expelled $\sim 11$ and $\sim 5$ months before explosion for SN2020xga and SN2022xgc respectively, possibly as a result of Luminous Blue Variable-like eruptions or pulsational pair instability (PPI) mass loss. We also analyze optical photometric data and model the light curves considering powering from the magnetar spin-down mechanism. The results support very energetic magnetars, approaching the mass-shedding limit, powering these SNe with ejecta masses of $\sim 7-9 \rm~M_\odot$. The ejecta masses inferred from the magnetar modeling are not consistent with the PPI scenario pointing towards stars $> 50~\rm M_\odot$ He-core, hence alternative scenarios such as fallback accretion are discussed., Comment: 25 pages text, 8 pages appendix, 21 figures. Submitted to A&A

Policy gradient methods are widely used in reinforcement learning. Yet, the nonconvexity of policy optimization imposes significant challenges in understanding the global convergence of policy gradient methods. For a class of finite-horizon Markov Decision Processes (MDPs) with general state and action spaces, we develop a framework that provides a set of easily verifiable assumptions to ensure the Kurdyka-Lojasiewicz (KL) condition of the policy optimization. Leveraging the KL condition, policy gradient methods converge to the globally optimal policy with a non-asymptomatic rate despite nonconvexity. Our results find applications in various control and operations models, including entropy-regularized tabular MDPs, Linear Quadratic Regulator (LQR) problems, stochastic inventory models, and stochastic cash balance problems, for which we show an $\epsilon$-optimal policy can be obtained using a sample size in $\tilde{\mathcal{O}}(\epsilon^{-1})$ and polynomial in terms of the planning horizon by stochastic policy gradient methods. Our result establishes the first sample complexity for multi-period inventory systems with Markov-modulated demands and stochastic cash balance problems in the literature.