Search

This paper investigates the one-epoch overfitting phenomenon in Click-Through Rate (CTR) models, where performance notably declines at the start of the second epoch. Despite extensive research, the efficacy of multi-epoch training over the conventional one-epoch approach remains unclear. We identify the overfitting of the embedding layer, caused by high-dimensional data sparsity, as the primary issue. To address this, we introduce a novel and simple Multi-Epoch learning with Data Augmentation (MEDA) framework, suitable for both non-continual and continual learning scenarios, which can be seamlessly integrated into existing deep CTR models and may have potential applications to handle the "forgetting or overfitting" dilemma in the retraining and the well-known catastrophic forgetting problems. MEDA minimizes overfitting by reducing the dependency of the embedding layer on subsequent training data or the Multi-Layer Perceptron (MLP) layers, and achieves data augmentation through training the MLP with varied embedding spaces. Our findings confirm that pre-trained MLP layers can adapt to new embedding spaces, enhancing performance without overfitting. This adaptability underscores the MLP layers' role in learning a matching function focused on the relative relationships among embeddings rather than their absolute positions. To our knowledge, MEDA represents the first multi-epoch training strategy tailored for deep CTR prediction models. We conduct extensive experiments on several public and business datasets, and the effectiveness of data augmentation and superiority over conventional single-epoch training are fully demonstrated. Besides, MEDA has exhibited significant benefits in a real-world online advertising system.

Cross-modality transfer aims to leverage large pretrained models to complete tasks that may not belong to the modality of pretraining data. Existing works achieve certain success in extending classical finetuning to cross-modal scenarios, yet we still lack understanding about the influence of modality gap on the transfer. In this work, a series of experiments focusing on the source representation quality during transfer are conducted, revealing the connection between larger modality gap and lesser knowledge reuse which means ineffective transfer. We then formalize the gap as the knowledge misalignment between modalities using conditional distribution P(Y|X). Towards this problem, we present Modality kNowledge Alignment (MoNA), a meta-learning approach that learns target data transformation to reduce the modality knowledge discrepancy ahead of the transfer. Experiments show that out method enables better reuse of source modality knowledge in cross-modality transfer, which leads to improvements upon existing finetuning methods., Comment: ICML 2024

Cameras are essential vision instruments to capture images for pattern detection and measurement. Human-object interaction (HOI) detection is one of the most popular pattern detection approaches for captured human-centric visual scenes. Recently, Transformer-based models have become the dominant approach for HOI detection due to their advanced network architectures and thus promising results. However, most of them follow the one-stage design of vanilla Transformer, leaving rich geometric priors under-exploited and leading to compromised performance especially when occlusion occurs. Given that geometric features tend to outperform visual ones in occluded scenarios and offer information that complements visual cues, we propose a novel end-to-end Transformer-style HOI detection model, i.e., geometric features enhanced HOI detector (GeoHOI). One key part of the model is a new unified self-supervised keypoint learning method named UniPointNet that bridges the gap of consistent keypoint representation across diverse object categories, including humans. GeoHOI effectively upgrades a Transformer-based HOI detector benefiting from the keypoints similarities measuring the likelihood of human-object interactions as well as local keypoint patches to enhance interaction query representation, so as to boost HOI predictions. Extensive experiments show that the proposed method outperforms the state-of-the-art models on V-COCO and achieves competitive performance on HICO-DET. Case study results on the post-disaster rescue with vision-based instruments showcase the applicability of the proposed GeoHOI in real-world applications., Comment: Accepted to IEEE TIM

Identification of critical nodes is a prominent topic in the study of complex networks. Numerous methods have been proposed, yet most exhibit inherent limitations. Traditional approaches primarily analyze specific structural features of the network; however, node influence is typically the result of a combination of multiple factors. Machine learning-based methods struggle to effectively represent the complex characteristics of network structures through suitable embedding techniques and require substantial data for training, rendering them prohibitively costly for large-scale networks. To address these challenges, this paper presents an active learning model based on GraphSAGE and Transformer, named GNNTAL. This model is initially pre-trained on random or synthetic networks and subsequently fine-tuned on real-world networks by selecting a few representative nodes using K-Means clustering and uncertainty sampling. This approach offers two main advantages: (1) it significantly reduces training costs; (2) it simultaneously incorporates both local and global features. A series of comparative experiments conducted on twelve real-world networks demonstrate that GNNTAL achieves superior performance. Additionally, this paper proposes an influence maximization method based on the predictions of the GNNTAL model, which achieves optimal performance without the need for complex computations. Finally, the paper analyses certain limitations of the GNNTAL model and suggests potential solutions.

Language models (LMs) exhibit impressive performance and generalization capabilities. However, LMs struggle with the persistent challenge of catastrophic forgetting, which undermines their long-term sustainability in continual learning (CL). Existing approaches usually address the issue by incorporating old task data or task-wise inductive bias into LMs. However, old data and accurate task information are often unavailable or costly to collect, hindering the availability of current CL approaches for LMs. To address this limitation, we introduce $\textbf{MIGU}$ ($\textbf{M}$agn$\textbf{I}$tude-based $\textbf{G}$radient $\textbf{U}$pdating for continual learning), a rehearsal-free and task-label-free method that only updates the model parameters with large magnitudes of output in LMs' linear layers. MIGU is based on our observation that the L1-normalized magnitude distribution of the output in LMs' linear layers is different when the LM models deal with different task data. By imposing this simple constraint on the gradient update process, we can leverage the inherent behaviors of LMs, thereby unlocking their innate CL abilities. Our experiments demonstrate that MIGU is universally applicable to all three LM architectures (T5, RoBERTa, and Llama2), delivering state-of-the-art or on-par performance across continual finetuning and continual pre-training settings on four CL benchmarks. For example, MIGU brings a 15.2% average accuracy improvement over conventional parameter-efficient finetuning baselines in a 15-task CL benchmark. MIGU can also seamlessly integrate with all three existing CL types to further enhance performance. Code is available at https://github.com/wenyudu/MIGU., Comment: EMNLP 2024 Findings

In the field of medical imaging, particularly in tasks related to early disease detection and prognosis, understanding the reasoning behind AI model predictions is imperative for assessing their reliability. Conventional explanation methods encounter challenges in identifying decisive features in medical image classifications, especially when discriminative features are subtle or not immediately evident. To address this limitation, we propose an agent model capable of generating counterfactual images that prompt different decisions when plugged into a black box model. By employing this agent model, we can uncover influential image patterns that impact the black model's final predictions. Through our methodology, we efficiently identify features that influence decisions of the deep black box. We validated our approach in the rigorous domain of medical prognosis tasks, showcasing its efficacy and potential to enhance the reliability of deep learning models in medical image classification compared to existing interpretation methods. The code will be publicly available at https://github.com/ayanglab/DiffExplainer., Comment: MICCAI 2024

Understanding the agent's learning process, particularly the factors that contribute to its success or failure post-training, is crucial for comprehending the rationale behind the agent's decision-making process. Prior methods clarify the learning process by creating a structural causal model (SCM) or visually representing the distribution of value functions. Nevertheless, these approaches have constraints as they exclusively function in 2D-environments or with uncomplicated transition dynamics. Understanding the agent's learning process in complicated environments or tasks is more challenging. In this paper, we propose REVEAL-IT, a novel framework for explaining the learning process of an agent in complex environments. Initially, we visualize the policy structure and the agent's learning process for various training tasks. By visualizing these findings, we can understand how much a particular training task or stage affects the agent's performance in test. Then, a GNN-based explainer learns to highlight the most important section of the policy, providing a more clear and robust explanation of the agent's learning process. The experiments demonstrate that explanations derived from this framework can effectively help in the optimization of the training tasks, resulting in improved learning efficiency and final performance.

The primary goal of continual learning (CL) task in medical image segmentation field is to solve the "catastrophic forgetting" problem, where the model totally forgets previously learned features when it is extended to new categories (class-level) or tasks (task-level). Due to the privacy protection, the historical data labels are inaccessible. Prevalent continual learning methods primarily focus on generating pseudo-labels for old datasets to force the model to memorize the learned features. However, the incorrect pseudo-labels may corrupt the learned feature and lead to a new problem that the better the model is trained on the old task, the poorer the model performs on the new tasks. To avoid this problem, we propose a network by introducing the data-specific Mixture of Experts (MoE) structure to handle the new tasks or categories, ensuring that the network parameters of previous tasks are unaffected or only minimally impacted. To further overcome the tremendous memory costs caused by introducing additional structures, we propose a Low-Rank strategy which significantly reduces memory cost. We validate our method on both class-level and task-level continual learning challenges. Extensive experiments on multiple datasets show our model outperforms all other methods.

Training models on spatio-temporal (ST) data poses an open problem due to the complicated and diverse nature of the data itself, and it is challenging to ensure the model's performance directly trained on the original ST data. While limiting the variety of training data can make training easier, it can also lead to a lack of knowledge and information for the model, resulting in a decrease in performance. To address this challenge, we presented an innovative paradigm that incorporates three separate forms of curriculum learning specifically targeting from spatial, temporal, and quantile perspectives. Furthermore, our framework incorporates a stacking fusion module to combine diverse information from three types of curriculum learning, resulting in a strong and thorough learning process. We demonstrated the effectiveness of this framework with extensive empirical evaluations, highlighting its better performance in addressing complex ST challenges. We provided thorough ablation studies to investigate the effectiveness of our curriculum and to explain how it contributes to the improvement of learning efficiency on ST data., Comment: accept by sigspatial 2024

Traffic forecasting is crucial for smart cities and intelligent transportation initiatives, where deep learning has made significant progress in modeling complex spatio-temporal patterns in recent years. However, current public datasets have limitations in reflecting the ultra-dynamic nature of real-world scenarios, characterized by continuously evolving infrastructures, varying temporal distributions, and temporal gaps due to sensor downtimes or changes in traffic patterns. These limitations inevitably restrict the practical applicability of existing traffic forecasting datasets. To bridge this gap, we present XXLTraffic, the largest available public traffic dataset with the longest timespan and increasing number of sensor nodes over the multiple years observed in the data, curated to support research in ultra-dynamic forecasting. Our benchmark includes both typical time-series forecasting settings with hourly and daily aggregated data and novel configurations that introduce gaps and down-sample the training size to better simulate practical constraints. We anticipate the new XXLTraffic will provide a fresh perspective for the time-series and traffic forecasting communities. It would also offer a robust platform for developing and evaluating models designed to tackle ultra-dynamic and extremely long forecasting problems. Our dataset supplements existing spatio-temporal data resources and leads to new research directions in this domain.

Dynamic text-attributed graphs (DyTAGs) are prevalent in various real-world scenarios, where each node and edge are associated with text descriptions, and both the graph structure and text descriptions evolve over time. Despite their broad applicability, there is a notable scarcity of benchmark datasets tailored to DyTAGs, which hinders the potential advancement in many research fields. To address this gap, we introduce Dynamic Text-attributed Graph Benchmark (DTGB), a collection of large-scale, time-evolving graphs from diverse domains, with nodes and edges enriched by dynamically changing text attributes and categories. To facilitate the use of DTGB, we design standardized evaluation procedures based on four real-world use cases: future link prediction, destination node retrieval, edge classification, and textual relation generation. These tasks require models to understand both dynamic graph structures and natural language, highlighting the unique challenges posed by DyTAGs. Moreover, we conduct extensive benchmark experiments on DTGB, evaluating 7 popular dynamic graph learning algorithms and their variants of adapting to text attributes with LLM embeddings, along with 6 powerful large language models (LLMs). Our results show the limitations of existing models in handling DyTAGs. Our analysis also demonstrates the utility of DTGB in investigating the incorporation of structural and textual dynamics. The proposed DTGB fosters research on DyTAGs and their broad applications. It offers a comprehensive benchmark for evaluating and advancing models to handle the interplay between dynamic graph structures and natural language. The dataset and source code are available at https://github.com/zjs123/DTGB., Comment: 28 pages, 13 figures

Large language models (LLMs) have shown promising efficacy across various tasks, becoming powerful tools in numerous aspects of human life. However, Transformer-based LLMs suffer a performance degradation when modeling long-term contexts due to they discard some information to reduce computational overhead. In this work, we propose a simple yet effective method to enable LLMs to take a deep breath, encouraging them to summarize information contained within discrete text chunks. Specifically, we segment the text into multiple chunks and insert special token at the end of each chunk. We then modify the attention mask to integrate the chunk's information into the corresponding token. This facilitates LLMs to interpret information not only from historical individual tokens but also from the token, aggregating the chunk's semantic information. Experiments on language modeling and out-of-domain downstream tasks validate the superiority of our approach.

We consider an online decision-making problem with a reward function defined over graph-structured data. We formally formulate the problem as an instance of graph action bandit. We then propose \texttt{GNN-TS}, a Graph Neural Network (GNN) powered Thompson Sampling (TS) algorithm which employs a GNN approximator for estimating the mean reward function and the graph neural tangent features for uncertainty estimation. We prove that, under certain boundness assumptions on the reward function, GNN-TS achieves a state-of-the-art regret bound which is (1) sub-linear of order $\tilde{\mathcal{O}}((\tilde{d} T)^{1/2})$ in the number of interaction rounds, $T$, and a notion of effective dimension $\tilde{d}$, and (2) independent of the number of graph nodes. Empirical results validate that our proposed \texttt{GNN-TS} exhibits competitive performance and scales well on graph action bandit problems.

This paper presents a novel approach to causal discovery through a divide-and-conquer framework. By decomposing the problem into smaller subproblems defined on Markov blankets, the proposed DCDILP method first explores in parallel the local causal graphs of these subproblems. However, this local discovery phase encounters systematic challenges due to the presence of hidden confounders (variables within each Markov blanket may be influenced by external variables). Moreover, aggregating these local causal graphs in a consistent global graph defines a large size combinatorial optimization problem. DCDILP addresses these challenges by: i) restricting the local subgraphs to causal links only related with the central variable of the Markov blanket; ii) formulating the reconciliation of local causal graphs as an integer linear programming method. The merits of the approach, in both terms of causal discovery accuracy and scalability in the size of the problem, are showcased by experiments and comparisons with the state of the art.

The quantum Griffiths singularity (QGS) is a phenomenon driven by quenched disorders that break conventional scaling invariance and result in a divergent dynamical critical exponent during quantum phase transitions (QPT). While this phenomenon has been well-documented in low-dimensional conventional superconductors and in three-dimensional (3D) magnetic metal systems, its presence in 3D superconducting systems and in unconventional high-temperature superconductors (high-Tc SCs) remains unclear. In this study, we report the observation of robust QGS in the superconductor-metal transition (SMT) of both quasi-2D and 3D anisotropic unconventional high-Tc superconductor CaFe1-xNixAsF (x < 5%) bulk single crystals, where the QGS states persist to up to 5.3 K. A comprehensive quantum phase diagram is established that delineates the 3D anisotropic QGS of SMT induced by perpendicular and parallel magnetic field. Our findings reveal the universality of QGS in 3D superconducting systems and unconventional high-Tc SCs, thereby substantially expanding the range of applicability of QGS., Comment: 17 pages, 4 figures

Energy-efficient spintronic devices require a large spin-orbit torque (SOT) and low damping to excite magnetic precession. In conventional devices with heavy-metal/ferromagnet bilayers, reducing the ferromagnet thickness to $\sim$1 nm enhances the SOT but dramatically increases damping. Here, we investigate an alternative approach based on a 10 nm thick single-layer ferromagnet to attain both low damping and a sizable SOT. Instead of relying on a single interface, we continuously break the bulk inversion symmetry with a vertical compositional gradient of two ferromagnetic elements: Fe with low intrinsic damping and Ni with sizable spin-orbit coupling. We find low effective damping parameters of $\alpha_\mathrm{eff} < 5\times10^{-3}$ in the FeNi alloy films, despite the steep compositional gradients. Moreover, we reveal a sizable anti-damping SOT efficiency of $\theta_\mathrm{AD} \approx 0.05$, even without an intentional compositional gradient. Through depth-resolved x-ray diffraction, we identify a lattice strain gradient as crucial symmetry breaking that underpins the SOT. Our findings provide fresh insights into damping and SOTs in single-layer ferromagnets for power-efficient spintronic devices.

A Relational Database Management System (RDBMS) is one of the fundamental software that supports a wide range of applications, making it critical to identify bugs within these systems. There has been active research on testing RDBMS, most of which employ crash or use metamorphic relations as the oracle. Although existing approaches can detect bugs in RDBMS, they are far from comprehensively evaluating the RDBMS's correctness (i.e., with respect to the semantics of SQL). In this work, we propose a method to test the semantic conformance of RDBMS i.e., whether its behavior respects the intended semantics of SQL. Specifically, we have formally defined the semantics of SQL and implemented them in Prolog. Then, the Prolog implementation serves as the reference RDBMS, enabling differential testing on existing RDBMS. We applied our approach to four widely-used and thoroughly tested RDBMSs, i.e., MySQL, TiDB, SQLite, and DuckDB. In total, our approach uncovered 19 bugs and 11 inconsistencies, which are all related to violating the SQL specification or missing/unclear specification, thereby demonstrating the effectiveness and applicability of our approach.

Contrastive Language-Image Pre-Training (CLIP) has shown impressive performance in short-term Person Re-Identification (ReID) due to its ability to extract high-level semantic features of pedestrians, yet its direct application to Cloth-Changing Person Re-Identification (CC-ReID) faces challenges due to CLIP's image encoder overly focusing on clothes clues. To address this, we propose a novel framework called CLIP-Driven Cloth-Agnostic Feature Learning (CCAF) for CC-ReID. Accordingly, two modules were custom-designed: the Invariant Feature Prompting (IFP) and the Clothes Feature Minimization (CFM). These modules guide the model to extract cloth-agnostic features positively and attenuate clothes-related features negatively. Specifically, IFP is designed to extract fine-grained semantic features unrelated to clothes from the raw image, guided by the cloth-agnostic text prompts. This module first covers the clothes in the raw image at the pixel level to obtain the shielding image and then utilizes CLIP's knowledge to generate cloth-agnostic text prompts. Subsequently, it aligns the raw image-text and the raw image-shielding image in the feature space, emphasizing discriminative clues related to identity but unrelated to clothes. Furthermore, CFM is designed to examine and weaken the image encoder's ability to extract clothes features. It first generates text prompts corresponding to clothes pixels. Then, guided by these clothes text prompts, it iteratively examines and disentangles clothes features from pedestrian features, ultimately retaining inherent discriminative features. Extensive experiments have demonstrated the effectiveness of the proposed CCAF, achieving new state-of-the-art performance on several popular CC-ReID benchmarks without any additional inference time.

Large-scale pretrained models have proven immensely valuable in handling data-intensive modalities like text and image. However, fine-tuning these models for certain specialized modalities, such as protein sequence and cosmic ray, poses challenges due to the significant modality discrepancy and scarcity of labeled data. In this paper, we propose an end-to-end method, PaRe, to enhance cross-modal fine-tuning, aiming to transfer a large-scale pretrained model to various target modalities. PaRe employs a gating mechanism to select key patches from both source and target data. Through a modality-agnostic Patch Replacement scheme, these patches are preserved and combined to construct data-rich intermediate modalities ranging from easy to hard. By gradually intermediate modality generation, we can not only effectively bridge the modality gap to enhance stability and transferability of cross-modal fine-tuning, but also address the challenge of limited data in the target modality by leveraging enriched intermediate modality data. Compared with hand-designed, general-purpose, task-specific, and state-of-the-art cross-modal fine-tuning approaches, PaRe demonstrates superior performance across three challenging benchmarks, encompassing more than ten modalities.

Tellegen medium has long been a topic of debate, with its existence being contested over several decades. It was first proposed by Tellegen in 1948 and is characterized by a real-valued cross coupling between electric and magnetic responses, distinguishing it from the well-known chiral medium that has imaginary coupling coefficients. Significantly, Tellegen responses are closely linked to axion dynamics, an extensively studied subject in condensed matter physics. Here, we report the realization of Tellegen metamaterials in the microwave region through a judicious combination of subwavelength metallic resonators, gyromagnetic materials, and permanent magnet discs. We observe the key signature of the Tellegen response, i.e. a Kerr rotation for reflected wave, while the polarization remains the same in the transmission direction. The retrieved effective Tellegen parameter is several orders of magnitude greater than that of natural materials. Our work opens door to a variety of nonreciprocal photonic devices and may provide a platform for studying axion physics., Comment: 19 pages, 4 figures

Driven by the demand for cross-sentence and large-scale relation extraction, document-level relation extraction (DocRE) has attracted increasing research interest. Despite the continuous improvement in performance, we find that existing DocRE models which initially perform well may make more mistakes when merely changing the entity names in the document, hindering the generalization to novel entity names. To this end, we systematically investigate the robustness of DocRE models to entity name variations in this work. We first propose a principled pipeline to generate entity-renamed documents by replacing the original entity names with names from Wikidata. By applying the pipeline to DocRED and Re-DocRED datasets, we construct two novel benchmarks named Env-DocRED and Env-Re-DocRED for robustness evaluation. Experimental results show that both three representative DocRE models and two in-context learned large language models consistently lack sufficient robustness to entity name variations, particularly on cross-sentence relation instances and documents with more entities. Finally, we propose an entity variation robust training method which not only improves the robustness of DocRE models but also enhances their understanding and reasoning capabilities. We further verify that the basic idea of this method can be effectively transferred to in-context learning for DocRE as well., Comment: Accepted to ACL 2024 Findings

We study source-free unsupervised domain adaptation (SFUDA) for semantic segmentation, which aims to adapt a source-trained model to the target domain without accessing the source data. Many works have been proposed to address this challenging problem, among which uncertainty-based self-training is a predominant approach. However, without comprehensive denoising mechanisms, they still largely fall into biased estimates when dealing with different domains and confirmation bias. In this paper, we observe that pseudo-label noise is mainly contained in unstable samples in which the predictions of most pixels undergo significant variations during self-training. Inspired by this, we propose a novel mechanism to denoise unstable samples with stable ones. Specifically, we introduce the Stable Neighbor Denoising (SND) approach, which effectively discovers highly correlated stable and unstable samples by nearest neighbor retrieval and guides the reliable optimization of unstable samples by bi-level learning. Moreover, we compensate for the stable set by object-level object paste, which can further eliminate the bias caused by less learned classes. Our SND enjoys two advantages. First, SND does not require a specific segmentor structure, endowing its universality. Second, SND simultaneously addresses the issues of class, domain, and confirmation biases during adaptation, ensuring its effectiveness. Extensive experiments show that SND consistently outperforms state-of-the-art methods in various SFUDA semantic segmentation settings. In addition, SND can be easily integrated with other approaches, obtaining further improvements., Comment: 2024 Conference on Computer Vision and Pattern Recognition

POLAR-2 is a dedicated gamma-ray polarimeter currently foreseen to be launched towards the China Space Station around 2027. The design of the detector is based on the legacy of its predecessor mission POLAR which was launched in 2016. POLAR-2 aims to measure the polarization of the Gamma-ray Burst prompt emission within the 30-800 keV energy range. Thanks to its high sensitivity to gamma-ray polarization, as well as its large effective area, POLAR-2 will provide the most precise measurements of this type to date. Such measurements are key to improve our understanding of the astrophysical processes responsible for Gamma-Ray Bursts. The detector consists of a segmented array of plastic scintillator bars, each one of which is read out by a Silicon PhotoMultiplier channel. The flight model of POLAR-2 will contain a total of 6400 scintillators. These are divided into 100 groups of 64 bars each, in so-called polarimeter modules. In recent years, the collaboration has designed and produced the first prototypes of these polarimeter modules and subjected these to space qualification tests. In addition, in April 2023, the first of these modules were calibrated using fully polarized gamma-ray beams at the European Synchrotron Radiation Facility (ESRF) in France. In this work, we will present the results of this calibration campaign and compare these to the simulated performance of the POLAR-2 modules. Potential improvements to the design are also discussed. Finally, the measurements are used, in combination with the verified simulation framework, to estimate the scientific performance of the full POLAR-2 detector and compare it to its predecessor., Comment: Accepted for publication in JINST

Typical BCS superconductors are microscopically homogeneous in real space governed by the coherent Cooper pairs with high phase stiffness of superfluid density, which is characterized by a coherence length. However, a periodic oscillation of superconducting order parameter may develop driven by breaking the time-reversal or translational invariance. To date, such modulated orders were specific to each material systems, with a periodicity much larger than the lattice constant. Here we report the direct observation of a uniform lattice-scale pair density wave (PDW) in single-layer FeSe/SrTiO3 films, enforced by peculiar interfacial structure of crystal symmetries breaking. Our spectroscopic imaging scanning tunneling microscopy unravels a spatial modulation of Cooper-pairing gap within a single unit-cell, depending on inequivalent atomic sites. Prominent periodic variation of superfluid density is visualized via Josephson current by a superconducting tip, indicating a real-space oscillation of phase stiffness. Such a lattice-scale superconducting modulation, which coexists with a larger length scale of PDW order, indicates the lattice-scale variation of both pairing strength and phase stiffness. Our findings provide new insights into the intertwined density-wave orders of quasiparticle character in correlated electronic systems, and provoke future studies on the unconventional pairing interaction and phase stiffness in the two-dimensional limit., Comment: 15 pages, 4 figures

Reconfigurable Intelligent Surfaces (RISs) are a novel form of ultra-low power devices that are capable to increase the communication data rates as well as the cell coverage in a cost- and energy-efficient way. This is attributed to their programmable operation that enables them to dynamically manipulate the wireless propagation environment, a feature that has lately inspired numerous research investigations and applications. To pave the way to the formal standardization of RISs, the European Telecommunications Standards Institute (ETSI) launched the Industry Specification Group (ISG) on the RIS technology in September 2021. This article provides a comprehensive overview of the status of the work conducted by the ETSI ISG RIS, covering typical deployment scenarios of reconfigurable metasurfaces, use cases and operating applications, requirements, emerging hardware architectures and operating modes, as well as the latest insights regarding future directions of RISs and the resulting smart wireless environments., Comment: 7 pages, 5 figures, submitted to an IEEE Magazine

Time series self-supervised learning (SSL) aims to exploit unlabeled data for pre-training to mitigate the reliance on labels. Despite the great success in recent years, there is limited discussion on the potential noise in the time series, which can severely impair the performance of existing SSL methods. To mitigate the noise, the de facto strategy is to apply conventional denoising methods before model training. However, this pre-processing approach may not fully eliminate the effect of noise in SSL for two reasons: (i) the diverse types of noise in time series make it difficult to automatically determine suitable denoising methods; (ii) noise can be amplified after mapping raw data into latent space. In this paper, we propose denoising-aware contrastive learning (DECL), which uses contrastive learning objectives to mitigate the noise in the representation and automatically selects suitable denoising methods for every sample. Extensive experiments on various datasets verify the effectiveness of our method. The code is open-sourced., Comment: Accepted to 33rd International Joint Conference on Artificial Intelligence (IJCAI 2024)

The value of supervised dimensionality reduction lies in its ability to uncover meaningful connections between data features and labels. Common dimensionality reduction methods embed a set of fixed, latent points, but are not capable of generalizing to an unseen test set. In this paper, we provide an out-of-sample extension method for the random forest-based supervised dimensionality reduction method, RF-PHATE, combining information learned from the random forest model with the function-learning capabilities of autoencoders. Through quantitative assessment of various autoencoder architectures, we identify that networks that reconstruct random forest proximities are more robust for the embedding extension problem. Furthermore, by leveraging proximity-based prototypes, we achieve a 40% reduction in training time without compromising extension quality. Our method does not require label information for out-of-sample points, thus serving as a semi-supervised method, and can achieve consistent quality using only 10% of the training data., Comment: 7 pages, 3 figures

Our goal is to $\textit{efficiently}$ discover a compact set of temporal logic rules to explain irregular events of interest. We introduce a neural-symbolic rule induction framework within the temporal point process model. The negative log-likelihood is the loss that guides the learning, where the explanatory logic rules and their weights are learned end-to-end in a $\textit{differentiable}$ way. Specifically, predicates and logic rules are represented as $\textit{vector embeddings}$, where the predicate embeddings are fixed and the rule embeddings are trained via gradient descent to obtain the most appropriate compositional representations of the predicate embeddings. To make the rule learning process more efficient and flexible, we adopt a $\textit{sequential covering algorithm}$, which progressively adds rules to the model and removes the event sequences that have been explained until all event sequences have been covered. All the found rules will be fed back to the models for a final rule embedding and weight refinement. Our approach showcases notable efficiency and accuracy across synthetic and real datasets, surpassing state-of-the-art baselines by a wide margin in terms of efficiency.

We report data analysis results about the outburst evolution and spectral properties during the hard state of the recently discovered X-ray transient Swift J1727.8-163 as observed by \emph{Insight}-HXMT and NuSTAR. We find that the broadband X-ray spectrum of Swift J1727.8-163 is more complex than the most typical spectral patterns of black hole X-ray binary systems, with not only a comparatively weaker reflection component but also an additional spectral continuum component, manifesting itself as a hard X-ray tail beyond the thermal Comptonization description detectable below 100 keV. This additional component can be phenomenologically well fitted by adding an extra power-law model with high energy exponential cutoff in the 2-120 keV energy band. We made an attempt to explain the broadband X-ray spectral continuum with a thermal/non-thermal hybrid plasma corona scenario , and find an ultra high compactness parameter ($l_{\rm s}\sim2000$) and a steep non-thermal electron distribution ($\Gamma_{\rm inj}>4$), suggesting the source was accreting with high Eddington rates and that the electron acceleration mechanism is not very efficient. We also present a detailed multi-epoch analysis of spectral properties using \emph{Insight}-HXMT data to investigate the evolution of the key physical properties regarding the disk and corona during the hard states. No significant variation is found with the inner disk radius and the coronal temperature during this time period, and the weak reflection and hard X-ray tail features are persistent. We discuss the physical implications of our spectral analysis results in the context of disk-corona relation, particle acceleration, and jet contribution, during the rise of a black hole X-ray binary in outburst., Comment: 16 pages, 6 figures

Despite the impressive capability of large language models (LLMs), knowing when to trust their generations remains an open challenge. The recent literature on uncertainty quantification of natural language generation (NLG) utilises a conventional natural language inference (NLI) classifier to measure the semantic dispersion of LLMs responses. These studies employ logits of NLI classifier for semantic clustering to estimate uncertainty. However, logits represent the probability of the predicted class and barely contain feature information for potential clustering. Alternatively, CLIP (Contrastive Language-Image Pre-training) performs impressively in extracting image-text pair features and measuring their similarity. To extend its usability, we propose Contrastive Semantic Similarity, the CLIP-based feature extraction module to obtain similarity features for measuring uncertainty for text pairs. We apply this method to selective NLG, which detects and rejects unreliable generations for better trustworthiness of LLMs. We conduct extensive experiments with three LLMs on several benchmark question-answering datasets with comprehensive evaluation metrics. Results show that our proposed method performs better in estimating reliable responses of LLMs than comparable baselines. Results show that our proposed method performs better in estimating reliable responses of LLMs than comparable baselines. The code are available at \url{https://github.com/AoShuang92/css_uq_llms}., Comment: The paper is accepted by The Conference on Uncertainty in Artificial Intelligence (UAI), 2024

Modern high-stakes systems, such as healthcare or robotics, often generate vast streaming event sequences. Our goal is to design an efficient, plug-and-play tool to elicit logic tree-based explanations from Large Language Models (LLMs) to provide customized insights into each observed event sequence. Built on the temporal point process model for events, our method employs the likelihood function as a score to evaluate generated logic trees. We propose an amortized Expectation-Maximization (EM) learning framework and treat the logic tree as latent variables. In the E-step, we evaluate the posterior distribution over the latent logic trees using an LLM prior and the likelihood of the observed event sequences. LLM provides a high-quality prior for the latent logic trees, however, since the posterior is built over a discrete combinatorial space, we cannot get the closed-form solution. We propose to generate logic tree samples from the posterior using a learnable GFlowNet, which is a diversity-seeking generator for structured discrete variables. The M-step employs the generated logic rules to approximate marginalization over the posterior, facilitating the learning of model parameters and refining the tunable LLM prior parameters. In the online setting, our locally built, lightweight model will iteratively extract the most relevant rules from LLMs for each sequence using only a few iterations. Empirical demonstrations showcase the promising performance and adaptability of our framework.

Multiple-Choice Questions (MCQs) constitute a critical area of research in the study of Large Language Models (LLMs). Previous works have investigated the selection bias problem in MCQs within few-shot scenarios, in which the LLM's performance may be influenced by the presentation of answer choices, leaving the selection bias during Supervised Fine-Tuning (SFT) unexplored. In this paper, we reveal that selection bias persists in the SFT phase , primarily due to the LLM's inadequate Multiple Choice Symbol Binding (MCSB) ability. This limitation implies that the model struggles to associate the answer options with their corresponding symbols (e.g., A/B/C/D) effectively. To enhance the model's MCSB capability, we first incorporate option contents into the loss function and subsequently adjust the weights of the option symbols and contents, guiding the model to understand the option content of the current symbol. Based on this, we introduce an efficient SFT algorithm for MCQs, termed Point-wise Intelligent Feedback (PIF). PIF constructs negative instances by randomly combining the incorrect option contents with all candidate symbols, and proposes a point-wise loss to provide feedback on these negative samples into LLMs. Our experimental results demonstrate that PIF significantly reduces the model's selection bias by improving its MCSB capability. Remarkably, PIF exhibits a substantial enhancement in the accuracy for MCQs., Comment: Accept at ACL2024 Main

The generalization bound is a crucial theoretical tool for assessing the generalizability of learning methods and there exist vast literatures on generalizability of normal learning, adversarial learning, and data poisoning. Unlike other data poison attacks, the backdoor attack has the special property that the poisoned triggers are contained in both the training set and the test set and the purpose of the attack is two-fold. To our knowledge, the generalization bound for the backdoor attack has not been established. In this paper, we fill this gap by deriving algorithm-independent generalization bounds in the clean-label backdoor attack scenario. Precisely, based on the goals of backdoor attack, we give upper bounds for the clean sample population errors and the poison population errors in terms of the empirical error on the poisoned training dataset. Furthermore, based on the theoretical result, a new clean-label backdoor attack is proposed that computes the poisoning trigger by combining adversarial noise and indiscriminate poison. We show its effectiveness in a variety of settings.

This survey investigates the multifaceted nature of forgetting in machine learning, drawing insights from neuroscientific research that posits forgetting as an adaptive function rather than a defect, enhancing the learning process and preventing overfitting. This survey focuses on the benefits of forgetting and its applications across various machine learning sub-fields that can help improve model performance and enhance data privacy. Moreover, the paper discusses current challenges, future directions, and ethical considerations regarding the integration of forgetting mechanisms into machine learning models.

Recent strides in large language models (LLMs) have yielded remarkable performance, leveraging reinforcement learning from human feedback (RLHF) to significantly enhance generation and alignment capabilities. However, RLHF encounters numerous challenges, including the objective mismatch issue, leading to suboptimal performance in Natural Language Understanding (NLU) tasks. To address this limitation, we propose a novel Reinforcement Learning framework enhanced with Label-sensitive Reward (RLLR) to amplify the performance of LLMs in NLU tasks. By incorporating label-sensitive pairs into reinforcement learning, our method aims to adeptly capture nuanced label-sensitive semantic features during RL, thereby enhancing natural language understanding. Experiments conducted on five diverse foundation models across eight tasks showcase promising results. In comparison to Supervised Fine-tuning models (SFT), RLLR demonstrates an average performance improvement of 1.54%. Compared with RLHF models, the improvement averages at 0.69%. These results reveal the effectiveness of our method for LLMs in NLU tasks. Code and data available at: https://github.com/MagiaSN/ACL2024_RLLR., Comment: Accept at ACL2024 Main

It is increasingly recognized that participation bias can pose problems for genetic studies. Recently, to overcome the challenge that genetic information of non-participants is unavailable, it is shown that by comparing the IBD (identity by descent) shared and not-shared segments among the participants, one can estimate the genetic component underlying participation. That, however, does not directly address how to adjust estimates of heritability and genetic correlation for phenotypes correlated with participation. Here, for phenotypes whose mean differences between population and sample are known, we demonstrate a way to do so by adopting a statistical framework that separates out the genetic and non-genetic correlations between participation and these phenotypes. Crucially, our method avoids making the assumption that the effect of the genetic component underlying participation is manifested entirely through these other phenotypes. Applying the method to 12 UK Biobank phenotypes, we found 8 have significant genetic correlations with participation, including body mass index, educational attainment, and smoking status. For most of these phenotypes, without adjustments, estimates of heritability and the absolute value of genetic correlation would have underestimation biases.

Fine urban change segmentation using multi-temporal remote sensing images is essential for understanding human-environment interactions in urban areas. Although there have been advances in high-quality land cover datasets that reveal the physical features of urban landscapes, the lack of fine-grained land use datasets hinders a deeper understanding of how human activities are distributed across the landscape and the impact of these activities on the environment, thus constraining proper technique development. To address this, we introduce FUSU, the first fine-grained land use change segmentation dataset for Fine-grained Urban Semantic Understanding. FUSU features the most detailed land use classification system to date, with 17 classes and 30 billion pixels of annotations. It includes bi-temporal high-resolution satellite images with 0.2-0.5 m ground sample distance and monthly optical and radar satellite time series, covering 847 km^2 across five urban areas in the southern and northern of China with different geographical features. The fine-grained land use pixel-wise annotations and high spatial-temporal resolution data provide a robust foundation for developing proper deep learning models to provide contextual insights on human activities and urbanization. To fully leverage FUSU, we propose a unified time-series architecture for both change detection and segmentation. We benchmark FUSU on various methods for several tasks. Dataset and code are available at: https://github.com/yuanshuai0914/FUSU.

Remote Sensing Image-Text Retrieval (RSITR) is pivotal for knowledge services and data mining in the remote sensing (RS) domain. Considering the multi-scale representations in image content and text vocabulary can enable the models to learn richer representations and enhance retrieval. Current multi-scale RSITR approaches typically align multi-scale fused image features with text features, but overlook aligning image-text pairs at distinct scales separately. This oversight restricts their ability to learn joint representations suitable for effective retrieval. We introduce a novel Multi-Scale Alignment (MSA) method to overcome this limitation. Our method comprises three key innovations: (1) Multi-scale Cross-Modal Alignment Transformer (MSCMAT), which computes cross-attention between single-scale image features and localized text features, integrating global textual context to derive a matching score matrix within a mini-batch, (2) a multi-scale cross-modal semantic alignment loss that enforces semantic alignment across scales, and (3) a cross-scale multi-modal semantic consistency loss that uses the matching matrix from the largest scale to guide alignment at smaller scales. We evaluated our method across multiple datasets, demonstrating its efficacy with various visual backbones and establishing its superiority over existing state-of-the-art methods. The GitHub URL for our project is: https://github.com/yr666666/MSA, Comment: 16 pages, 9 figures

Owing to the broad energy coverage of Insight-HXMT in the hard X-ray band, we detected the highest energy of pulsation exceeding 200 keV around the 2017-2018 outburst peak of the first Galactic pulsating ultraluminous X-ray source (PULX) Swift J0243.6+6124, which is the highest energy detected from PULXs to date. We also obtained the highest energy of pulsation of every exposure during the outburst in 2017-2018, and found the highest energy is roughly positively correlated with luminosity. Using our newly developed method, we identified the critical luminosity being $4\times 10^{38}\, \rm erg\,s^{-1}$ when the main peaks of the low and high energy pulse profiles became aligned, which separates the fan-beam dominated and pencil-beam dominated accretion regimes. Above the critical luminosity, the phase of the main peak shifted gradually from 0.5 to 0.8 until the outburst peak in all energy bands is reached, which is in agreement with the phase shift found previously at low energies. Our result is consistent with what is derived from spectral analysis., Comment: 9 pages, 9 figures, published in RAA

The rapid advancement of Large Language Models (LLMs) has significantly impacted human-computer interaction, epitomized by the release of GPT-4o, which introduced comprehensive multi-modality capabilities. In this paper, we first explored the deployment strategies, economic considerations, and sustainability challenges associated with the state-of-the-art LLMs. More specifically, we discussed the deployment debate between Retrieval-Augmented Generation (RAG) and fine-tuning, highlighting their respective advantages and limitations. After that, we quantitatively analyzed the requirement of xPUs in training and inference. Additionally, for the tokenomics of LLM services, we examined the balance between performance and cost from the quality of experience (QoE)'s perspective of end users. Lastly, we envisioned the future hybrid architecture of LLM processing and its corresponding sustainability concerns, particularly in the environmental carbon footprint impact. Through these discussions, we provided a comprehensive overview of the operational and strategic considerations essential for the responsible development and deployment of LLMs., Comment: Accepted by IEEE CTSoc-NCT

As one of the most energetic and brightest events, gamma-ray bursts (GRBs) have been used as a standard candle for cosmological probe. Based on the relevant features of GRBs light curves, a plateau phase followed a decay phase, we obtain X-ray samples of 31 GRBs and optical samples of 50 GRBs, which are thought to be caused by the same physical mechanism. We standardize GRBs using the two-dimension fundamental plane relation of the rest-frame luminosity of the plateau emission ($L_{b,z}$) and the end time of plateau ($T_{b,z}$) $L_{b,z}-T_{b,z}$, as well as the three-dimension fundamental plane correlation including the peak energy ($E_{p,i}$) $L_{b,z}-T_{b,z}-E_{p,i}$. For the cosmological probes, we consider the $\omega$CDM model in which the dark energy consists of one component, and mainly focus on the $X_1X_2$CDM model in which the dark energy is made up of two independent components. We obtain the constraints on the related parameters of the cosmological models using the type Ia supernovae (SNe Ia) data and selected X-ray and optical samples. For the $X_1X_2$CDM model, we find that the values of the equations of state parameters of two dark energies, $\omega_1$ and $\omega_2$, are very close. We also conduct the comparison between the models using the Bayesian information criterion, and find that the $\omega$CDM model is favoured., Comment: 13 pages, 8 figures and 3 tables, accepted for publication in Astronomy & Astrophysics

As the field of image generation rapidly advances, traditional diffusion models and those integrated with multimodal large language models (LLMs) still encounter limitations in interpreting complex prompts and preserving image consistency pre and post-editing. To tackle these challenges, we present an innovative image editing framework that employs the robust Chain-of-Thought (CoT) reasoning and localizing capabilities of multimodal LLMs to aid diffusion models in generating more refined images. We first meticulously design a CoT process comprising instruction decomposition, region localization, and detailed description. Subsequently, we fine-tune the LISA model, a lightweight multimodal LLM, using the CoT process of Multimodal LLMs and the mask of the edited image. By providing the diffusion models with knowledge of the generated prompt and image mask, our models generate images with a superior understanding of instructions. Through extensive experiments, our model has demonstrated superior performance in image generation, surpassing existing state-of-the-art models. Notably, our model exhibits an enhanced ability to understand complex prompts and generate corresponding images, while maintaining high fidelity and consistency in images before and after generation.

Textual-edge Graphs (TEGs), characterized by rich text annotations on edges, are increasingly significant in network science due to their ability to capture rich contextual information among entities. Existing works have proposed various edge-aware graph neural networks (GNNs) or let language models directly make predictions. However, they often fall short of fully capturing the contextualized semantics on edges and graph topology, respectively. This inadequacy is particularly evident in link prediction tasks that require a comprehensive understanding of graph topology and semantics between nodes. In this paper, we present a novel framework - Link2Doc, designed especially for link prediction on textual-edge graphs. Specifically, we propose to summarize neighborhood information between node pairs as a human-written document to preserve both semantic and topology information. A self-supervised learning model is then utilized to enhance GNN's text-understanding ability from language models. Empirical evaluations, including link prediction, edge classification, parameter analysis, runtime comparison, and ablation studies, on four real-world datasets demonstrate that Link2Doc achieves generally better performance against existing edge-aware GNNs and pre-trained language models in predicting links on TEGs.

Generating high-quality 3D assets from text and images has long been challenging, primarily due to the absence of scalable 3D representations capable of capturing intricate geometry distributions. In this work, we introduce Direct3D, a native 3D generative model scalable to in-the-wild input images, without requiring a multiview diffusion model or SDS optimization. Our approach comprises two primary components: a Direct 3D Variational Auto-Encoder (D3D-VAE) and a Direct 3D Diffusion Transformer (D3D-DiT). D3D-VAE efficiently encodes high-resolution 3D shapes into a compact and continuous latent triplane space. Notably, our method directly supervises the decoded geometry using a semi-continuous surface sampling strategy, diverging from previous methods relying on rendered images as supervision signals. D3D-DiT models the distribution of encoded 3D latents and is specifically designed to fuse positional information from the three feature maps of the triplane latent, enabling a native 3D generative model scalable to large-scale 3D datasets. Additionally, we introduce an innovative image-to-3D generation pipeline incorporating semantic and pixel-level image conditions, allowing the model to produce 3D shapes consistent with the provided conditional image input. Extensive experiments demonstrate the superiority of our large-scale pre-trained Direct3D over previous image-to-3D approaches, achieving significantly better generation quality and generalization ability, thus establishing a new state-of-the-art for 3D content creation. Project page: https://nju-3dv.github.io/projects/Direct3D/.

Despite persistent efforts to understand the dynamics of creativity of scientists over careers in terms of productivity, impact, and prize, little is known about the dynamics of scientists' disruptive efforts that affect individual academic careers and drive scientific advance. Drawing on millions of data over six decades and across nineteen disciplines, associating the publication records of individual scientists with the disruption index, we systematically quantify the temporal pattern of disruptive ideas over individual scientific careers, providing a detailed understanding of the macro phenomenon of scientific stagnation from the individual perspective. We start by checking the relationship between disruption-based and citation-based publication profiles. Next, we observe the finite inequality in the disruptive productivity of scientists, diminishing gradually as the level of disruption increases. We then identify the initial burst phenomenon in disruption dynamics. It is further revealed that while early engagement in high disruption frictions away initial productivity, compared to initial advantage in productivity or impact, initial high disruption ensures more subsequent academic viability evidenced by a longer career span and relatively final higher productivity, but does not necessarily guarantee academic success throughout careers. Further analysis shows that increasing disruptive work is uncorrelated to overall productivity but negatively correlated with the overall impact. However, increasing disruptive work in the early career is associated with higher overall productivity, yet lower overall productivity in the later career. Our research underscores the urgent need for a policy shift that encourages a balance between the pursuit of disruptive efforts and the achievement of impactful outcomes.

In practical applications of human pose estimation, low-resolution inputs frequently occur, and existing state-of-the-art models perform poorly with low-resolution images. This work focuses on boosting the performance of low-resolution models by distilling knowledge from a high-resolution model. However, we face the challenge of feature size mismatch and class number mismatch when applying knowledge distillation to networks with different input resolutions. To address this issue, we propose a novel cross-domain knowledge distillation (CDKD) framework. In this framework, we construct a scale-adaptive projector ensemble (SAPE) module to spatially align feature maps between models of varying input resolutions. It adopts a projector ensemble to map low-resolution features into multiple common spaces and adaptively merges them based on multi-scale information to match high-resolution features. Additionally, we construct a cross-class alignment (CCA) module to solve the problem of the mismatch of class numbers. By combining an easy-to-hard training (ETHT) strategy, the CCA module further enhances the distillation performance. The effectiveness and efficiency of our approach are demonstrated by extensive experiments on two common benchmark datasets: MPII and COCO. The code is made available in supplementary material., Comment: 11 pages, 5 figures

We report the magnetic properties of newly synthesized, single crystals of $\mathrm{TbTi_3Bi_4}$ whose crystal structure is highlighted by the stacking of terbium-based zigzag chains and titanium-based kagome lattices. This compound demonstrates extreme easy-axis magnetic anisotropy due to the crystalline-electric-field effect which aligns the $\mathrm{Tb^{3+}}$ moments along the zigzag chain direction. As the result of the strong single-ion anisotropy and multiple magnetic interactions, $\mathrm{TbTi_3Bi_4}$ behaves as a quasi-one-dimensional Ising magnet with a remarkable antiferromagnetic ordering at $T_\mathrm{N}$ = 20.4 K. When a magnetic field is applied along the direction of the zigzag chain, multiple meta-magnetic transitions occur between 1/3 and other magnetization plateaus. We have created a field-temperature phase diagram and mapped out the complex magnetic structures resulting from frustration., Comment: 10 pages, 10 figures

The paper is concerned with the principal eigenvalue of some linear elliptic operators with drift in two dimensional space. We provide a refined description of the asymptotic behavior for the principal eigenvalue as the drift rate approaches infinity. Under some non-degeneracy assumptions, our results illustrate that these asymptotic behaviors are completely determined by some connected components in the omega-limit set of the system of ordinary differential equations associated with the drift term, which includes stable fixed points, stable limit cycles, hyperbolic saddles connecting homoclinic orbits, and families of closed orbits. Some discussions on degenerate cases are also included., Comment: 53 pages, 9 figures

Band crossing points, such as Weyl and Dirac points, play a crucial role in the topological classification of materials and guide the exploration of exotic topological phases. The Berry dipole, a three-dimensional band crossing point beyond the Chern class, hosts a dipolar Berry curvature field and gives rise to numerous nontrivial quantum geometric effects. It has been proposed that the Berry dipole exhibits oriented Landau levels, whose spectrum critically relies on the orientation of the applied magnetic field. However, experimental demonstration of this phenomenon has remained elusive. Here we experimentally demonstrate oriented Landau levels by carefully engineering an inhomogeneous acoustic lattice. We observe distinct Landau level spectra and different propagation properties when the orientation of the pseudomagnetic field is reversed. Notably, we discover a new type of helical zero modes whose existence critically depends on the magnetic field's orientation. Our work paves the way for studying band crossings beyond Chern-class crossing points, including Berry multipoles and even-dimensional monopoles. Furthermore, it offers new insight for exploring topological devices.

Capsule endoscopes, predominantly serving diagnostic functions, provide lucid internal imagery but are devoid of surgical or therapeutic capabilities. Consequently, despite lesion detection, physicians frequently resort to traditional endoscopic or open surgical procedures for treatment, resulting in more complex, potentially risky interventions. To surmount these limitations, this study introduces a chained flexible capsule endoscope (FCE) design concept, specifically conceived to navigate the inherent volume constraints of capsule endoscopes whilst augmenting their therapeutic functionalities. The FCE's distinctive flexibility originates from a conventional rotating joint design and the incision pattern in the flexible material. In vitro experiments validated the passive navigation ability of the FCE in rugged intestinal tracts. Further, the FCE demonstrates consistent reptile-like peristalsis under the influence of an external magnetic field, and possesses the capability for film expansion and disintegration under high-frequency electromagnetic stimulation. These findings illuminate a promising path toward amplifying the therapeutic capacities of capsule endoscopes without necessitating a size compromise.