Search

The frustrated magnet $\alpha$-RuCl3 is one of the prime candidates for realizing a Kitaev quantum spin liquid (QSL). However, the existence of a field-induced intermediate QSL phase in this material remains under debate. Here, we employ sign-free numerically exact quantum Monte Carlo simulations to investigate the Kitaev-Heisenberg (KH) model on the honeycomb lattice with $K=-2J$ under an applied magnetic field along the z-direction. Our findings reveal that the system undergoes a direct quantum phase transition from a zigzag magnetically ordered phase to a spin-polarized phase at zero temperature, which belongs to the 3D XY universality class. At finite temperatures, a Berezinskii-Kosterlitz-Thouless transition line separates the spin-polarized phase from a quasi-long-range ordered state, eventually terminating at the quantum critical point. Our results convincingly show that there is no intermediate QSL phase in the KH model with a z-direction magnetic field, which we believe will shed important light on understanding experimental observations in $\alpha$-RuCl3., Comment: 4.5 pages, 5 figures

Cognitive diagnosis aims to infer students' mastery levels based on their historical response logs. However, existing cognitive diagnosis models (CDMs), which rely on ID embeddings, often have to train specific models on specific domains. This limitation may hinder their directly practical application in various target domains, such as different subjects (e.g., Math, English and Physics) or different education platforms (e.g., ASSISTments, Junyi Academy and Khan Academy). To address this issue, this paper proposes the language representation favored zero-shot cross-domain cognitive diagnosis (LRCD). Specifically, LRCD first analyzes the behavior patterns of students, exercises and concepts in different domains, and then describes the profiles of students, exercises and concepts using textual descriptions. Via recent advanced text-embedding modules, these profiles can be transformed to vectors in the unified language space. Moreover, to address the discrepancy between the language space and the cognitive diagnosis space, we propose language-cognitive mappers in LRCD to learn the mapping from the former to the latter. Then, these profiles can be easily and efficiently integrated and trained with existing CDMs. Extensive experiments show that training LRCD on real-world datasets can achieve commendable zero-shot performance across different target domains, and in some cases, it can even achieve competitive performance with some classic CDMs trained on the full response data on target domains. Notably, we surprisingly find that LRCD can also provide interesting insights into the differences between various subjects (such as humanities and sciences) and sources (such as primary and secondary education).

Measurement-only quantum circuits offer a versatile platform for realizing intriguing quantum phases of matter. However, gapless symmetry-protected topological (gSPT) states remain insufficiently explored in these settings. In this Letter, we generalize the notion of gSPT to the critical steady state by investigating measurement-only circuits. Using large-scale Clifford circuit simulations, we investigate the steady-state phase diagram across several families of measurement-only circuits that exhibit topological nontrivial edge states at criticality. In the Ising cluster circuits, we uncover a symmetry-enriched non-unitary critical point, termed symmetry-enriched percolation, characterized by both topologically nontrivial edge states and string operator. Additionally, we demonstrate the realization of a steady-state gSPT phase in a $\mathbb Z_4$ circuit model. This phase features topological edge modes and persists within steady-state critical phases under symmetry-preserving perturbations. Furthermore, we provide a unified theoretical framework by mapping the system to the Majorana loop model, offering deeper insights into the underlying mechanisms., Comment: 5.5 pages with supplemental materials, 16 figures

Flight trajectory data plays a vital role in the traffic management community, especially for downstream tasks such as trajectory prediction, flight recognition, and anomaly detection. Existing works often utilize handcrafted features and design models for different tasks individually, which heavily rely on domain expertise and are hard to extend. We argue that different flight analysis tasks share the same useful features of the trajectory. Jointly learning a unified representation for flight trajectories could be beneficial for improving the performance of various tasks. However, flight trajectory representation learning (TRL) faces two primary challenges, \ie unbalanced behavior density and 3D spatial continuity, which disable recent general TRL methods. In this paper, we propose Flight2Vec , a flight-specific representation learning method to address these challenges. Specifically, a behavior-adaptive patching mechanism is used to inspire the learned representation to pay more attention to behavior-dense segments. Moreover, we introduce a motion trend learning technique that guides the model to memorize not only the precise locations, but also the motion trend to generate better representations. Extensive experimental results demonstrate that Flight2Vec significantly improves performance in downstream tasks such as flight trajectory prediction, flight recognition, and anomaly detection., Comment: Accepted by AAAI 2025

Consensus is becoming increasingly important in wireless networks. Partially synchronous BFT consensus, a significant branch of consensus, has made considerable progress in wired networks. However, its implementation in wireless networks, especially in dynamic ad hoc wireless networks, remains challenging. Existing wireless synchronous consensus protocols, despite being well-developed, are not readily adaptable to partially synchronous settings. Additionally, reliable communication, a cornerstone of BFT consensus, can lead to high message and time complexity in wireless networks. To address these challenges, we propose a wireless communication protocol called ReduceCatch (Reduce and Catch) that supports reliable 1-to-N, N-to-1, and N-to-N communications. We employ ReduceCatch to tailor three partially synchronous BFT consensus protocols (PBFT, Tendermint, and HotStuff) for seamless adaptation from wired to ad hoc wireless networks. To evaluate the performance of the ReduceCatch-enabled consensus protocols, we develop a three-layer wireless consensus testbed, based on which we implement 20 distinct consensus protocols and measure their latency and throughput. The experimental results demonstrate the superiority of the ReduceCatch-based consensus protocol in terms of latency and throughput., Comment: Accepted to IEEE INFOCOM 2025, 10 pages, 7 figures

Multimodal Large Language Models (MLLMs) have made significant strides in visual understanding and generation tasks. However, generating interleaved image-text content remains a challenge, which requires integrated multimodal understanding and generation abilities. While the progress in unified models offers new solutions, existing benchmarks are insufficient for evaluating these methods due to data size and diversity limitations. To bridge this gap, we introduce GATE OpenING (OpenING), a comprehensive benchmark comprising 5,400 high-quality human-annotated instances across 56 real-world tasks. OpenING covers diverse daily scenarios such as travel guide, design, and brainstorming, offering a robust platform for challenging interleaved generation methods. In addition, we present IntJudge, a judge model for evaluating open-ended multimodal generation methods. Trained with a novel data pipeline, our IntJudge achieves an agreement rate of 82. 42% with human judgments, outperforming GPT-based evaluators by 11.34%. Extensive experiments on OpenING reveal that current interleaved generation methods still have substantial room for improvement. Key findings on interleaved image-text generation are further presented to guide the development of next-generation models. The OpenING is open-sourced at https://opening-benchmark.github.io., Comment: 53 pages, 19 figures

We study 1+1 dimensional relativistic non-resistive magnetohydrodynamics (MHD) with longitudinal boost invariance and shear stress tensor. Several analytical solutions that describe the fluid temperature evolution under the equation of state (EoS) $\varepsilon=3p$ are derived, relevant to relativistic heavy-ion collisions. Extending the Victor-Bjorken ideal MHD flow to include non-zero shear viscosity, two perturbative analytical solutions for the first-order (Navier-Stokes) approximation are obtained. For small, power-law evolving external magnetic fields, our solutions are stable and show that both magnetic field and shear viscosity cause fluid heating with an early temperature peak, align with the numerical results. In the second-order (Israel-Stewart) theory, our findings show that the combined presence of magnetic field and shear viscosity leads to a slow cooling rate of fluid temperature, with initial shear stress significantly affecting temperature evolution of QGP., Comment: 12 pages, 7 figures. Comments are welcome

Large Language Models (LLMs) have revolutionized natural language processing, but their susceptibility to biases poses significant challenges. This comprehensive review examines the landscape of bias in LLMs, from its origins to current mitigation strategies. We categorize biases as intrinsic and extrinsic, analyzing their manifestations in various NLP tasks. The review critically assesses a range of bias evaluation methods, including data-level, model-level, and output-level approaches, providing researchers with a robust toolkit for bias detection. We further explore mitigation strategies, categorizing them into pre-model, intra-model, and post-model techniques, highlighting their effectiveness and limitations. Ethical and legal implications of biased LLMs are discussed, emphasizing potential harms in real-world applications such as healthcare and criminal justice. By synthesizing current knowledge on bias in LLMs, this review contributes to the ongoing effort to develop fair and responsible AI systems. Our work serves as a comprehensive resource for researchers and practitioners working towards understanding, evaluating, and mitigating bias in LLMs, fostering the development of more equitable AI technologies.

Measurement-induced phase transitions (MIPT), characterizing abrupt changes in entanglement properties in quantum many-body systems subjected to unitary evolution with interspersed projective measurements, have garnered increasing interest. In this work, we generalize the Kibble-Zurek (KZ) driven critical dynamics that has achieved great success in traditional quantum and classical phase transitions to MIPT. By linearly changing the measurement probability $p$ to cross the critical point $p_c$ with driving velocity $R$, we identify the dynamic scaling relation of the entanglement entropy $S$ versus $R$ at $p_c$. For decreasing $p$ from the area-law phase, $S$ satisfies $S\propto \ln R$; while for increasing $p$ from the volume-law phase, $S$ satisfies $S\propto R^{1/r}$ in which $r=z+1/\nu$ with $z$ and $\nu$ being the dynamic and correlation length exponents, respectively. Moreover, we find that the driven dynamics from the volume-law phase violates the adiabatic-impulse scenario of the KZ mechanism. In spite of this, a unified finite-time scaling (FTS) form can be developed to describe these scaling behaviors. Besides, the dynamic scaling of the entanglement entropy of an auxiliary qubit $S_Q$ is also investigated to further confirm the universality of the FTS form. By successfully establishing the driven dynamic scaling theory of this newfashioned entanglement transition, we bring a new fundamental perspective into MIPT that can be detected in fast-developing quantum computers., Comment: 6+6 pages

Recent years have witnessed measurement-induced entanglement phase transitions attracting significant attention, yet the feedback-induced skin effect in tilted fields remains understudied. This work investigates entanglement relaxation and dynamical transitions in a fermionic chain subject to generalized monitoring and an applied tilted field. We show that the feedback-induced skin effect persists with tilting, though relaxation time increases. For small tilts, bipartite entanglement exhibits a widened metastable phase, transitioning from a logarithmic-law to an area-law phase. In contrast, strong tilts accelerate relaxation, leading to a single area-law phase. Moreover, due to the unique properties of the tilted chain, we examine the impact of the boundary on entanglement relaxation. This work not only deepens our understanding of the role of feedback in measurement-induced entanglement phase transitions but also enhances our comprehension of the non-Hermitian skin effect beyond the no-click limit., Comment: Any comments are welcome!

As data privacy and security attract increasing attention, Federated Recommender System (FRS) offers a solution that strikes a balance between providing high-quality recommendations and preserving user privacy. However, the presence of statistical heterogeneity in FRS, commonly observed due to personalized decision-making patterns, can pose challenges. To address this issue and maximize the benefit of collaborative filtering (CF) in FRS, it is intuitive to consider clustering clients (users) as well as items into different groups and learning group-specific models. Existing methods either resort to client clustering via user representations-risking privacy leakage, or employ classical clustering strategies on item embeddings or gradients, which we found are plagued by the curse of dimensionality. In this paper, we delve into the inefficiencies of the K-Means method in client grouping, attributing failures due to the high dimensionality as well as data sparsity occurring in FRS, and propose CoFedRec, a novel Co-clustering Federated Recommendation mechanism, to address clients heterogeneity and enhance the collaborative filtering within the federated framework. Specifically, the server initially formulates an item membership from the client-provided item networks. Subsequently, clients are grouped regarding a specific item category picked from the item membership during each communication round, resulting in an intelligently aggregated group model. Meanwhile, to comprehensively capture the global inter-relationships among items, we incorporate an additional supervised contrastive learning term based on the server-side generated item membership into the local training phase for each client. Extensive experiments on four datasets are provided, which verify the effectiveness of the proposed CoFedRec., Comment: WWW '24: Proceedings of the ACM Web Conference 2024

Spacetime supersymmetry (SUSY) that interchanges fermions and bosons is of great theoretical importance but has not yet been revealed experimentally in particle physics. It has also been desired to explore quantum-mechanical SUSY in microscopic lattice models. Inspired by the recent experiments of Floquet engineering of Rydberg atom arrays, we find that quantum mechanical SUSY can be realized in Floquet Rydberg atom arrays. Moreover, we utilize the supercharge dynamics to demonstrate the SUSY property of the model under investigation: the expectation value of supercharge freezes under time evolution for supersymmetric lattice models in contrast to the trivial oscillation for generic nonsupersymmetric lattice models. The proposal is validated on direct simulation of Rydberg atom arrays' dynamics and ready for experiments. This work sheds light on the future experimental exploration of SUSY with the help of Rydberg atom arrays., Comment: 4 pages, 3 figures

Cognitive diagnosis model (CDM) is a fundamental and upstream component in intelligent education. It aims to infer students' mastery levels based on historical response logs. However, existing CDMs usually follow the ID-based embedding paradigm, which could often diminish the effectiveness of CDMs in open student learning environments. This is mainly because they can hardly directly infer new students' mastery levels or utilize new exercises or knowledge without retraining. Textual semantic information, due to its unified feature space and easy accessibility, can help alleviate this issue. Unfortunately, directly incorporating semantic information may not benefit CDMs, since it does not capture response-relevant features and thus discards the individual characteristics of each student. To this end, this paper proposes a dual-fusion cognitive diagnosis framework (DFCD) to address the challenge of aligning two different modalities, i.e., textual semantic features and response-relevant features. Specifically, in DFCD, we first propose the exercise-refiner and concept-refiner to make the exercises and knowledge concepts more coherent and reasonable via large language models. Then, DFCD encodes the refined features using text embedding models to obtain the semantic information. For response-related features, we propose a novel response matrix to fully incorporate the information within the response logs. Finally, DFCD designs a dual-fusion module to merge the two modal features. The ultimate representations possess the capability of inference in open student learning environments and can be also plugged in existing CDMs. Extensive experiments across real-world datasets show that DFCD achieves superior performance by integrating different modalities and strong adaptability in open student learning environments.

Recommender systems predict personalized item rankings based on user preference distributions derived from historical behavior data. Recently, diffusion models (DMs) have gained attention in recommendation for their ability to model complex distributions, yet current DM-based recommenders often rely on traditional objectives like mean squared error (MSE) or recommendation objectives, which are not optimized for personalized ranking tasks or fail to fully leverage DM's generative potential. To address this, we propose PreferDiff, a tailored optimization objective for DM-based recommenders. PreferDiff transforms BPR into a log-likelihood ranking objective and integrates multiple negative samples to better capture user preferences. Specifically, we employ variational inference to handle the intractability through minimizing the variational upper bound and replaces MSE with cosine error to improve alignment with recommendation tasks. Finally, we balance learning generation and preference to enhance the training stability of DMs. PreferDiff offers three key benefits: it is the first personalized ranking loss designed specifically for DM-based recommenders and it improves ranking and faster convergence by addressing hard negatives. We also prove that it is theoretically connected to Direct Preference Optimization which indicates that it has the potential to align user preferences in DM-based recommenders via generative modeling. Extensive experiments across three benchmarks validate its superior recommendation performance and commendable general sequential recommendation capabilities. Our codes are available at \url{https://github.com/lswhim/PreferDiff}.

In this paper, we introduce tensor involved peridynamics, a unified framework for simulating both isotropic and anisotropic materials. While traditional peridynamics models effectively simulate isotropic materials, they face challenges with anisotropic materials and are prone to instability caused by zero energy modes. Our novel model extend the linear bond based peridynamics framework by incorporating the elastic tensor into the micrmodulus function, thereby ensuring stability for anisotropic materials without the need for additional corrections. For isotropic materials. the model mantains compatibility with conventional bond based peridynamics, assuming Possion's rations of 1/4 in 3D and 1/3 in 2D.Numerical experiments confirm the model's stability and accuracy across various scenarios. Additionally, we introduce a damage model for isotropic materials. validating its performance in predicting crack propagation paths in a 2D plate. The results show superior alignment with experimental date compared to traditional model., Comment: Peridynamics; Anisotropic materials; Elastic tensor; Zero-energy mode

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

Safety is one of the fundamental challenges in control theory. Recently, multi-step optimal control problems for discrete-time dynamical systems were developed to ensure stability, while adhering to input constraints and safety-critical requirements. This was achieved by incorporating discrete-time Control Barrier Functions (CBFs) within a Model Predictive Control (MPC) framework. Existing work usually centers on the feasibility or safety of optimization problems when the boundaries of safe sets are clearly defined. Most of this research limits discussions to CBFs with relative degree one with respect to the system dynamics. Furthermore, real-time computation becomes challenging in MPC problems with large horizons. In this paper, we introduce a framework that addresses the safety-critical MPC problem through iterative optimization, applicable across CBFs of any relative degree. Our approach involves linearizing the nonlinear system dynamics and safety constraints, modeled as Discrete-time High-Order CBFs (DHOCBFs), at each time step. Additionally, when the boundaries of the safe sets are complex, we present a learning-based method to develop linear boundary equations for these safe sets. These equations are then converted into linearized DHOCBFs. The benefits of computational performance and safe avoidance of obstacles with diverse shapes are examined and confirmed through numerical results., Comment: 16 pages, 12 figures. arXiv admin note: text overlap with arXiv:2210.04361

Response times contain information about economically relevant but unobserved variables like willingness to pay, preference intensity, quality, or happiness. Here, we provide a general characterization of the properties of latent variables that can be detected using response time data. Our characterization generalizes various results in the literature, helps to solve identification problems of binary response models, and paves the way for many new applications. We apply the result to test the hypothesis that marginal happiness is decreasing in income, a principle that is commonly accepted but so far not established empirically.

The nonequilibrium dynamics of quantum many-body systems have attracted growing attention due to various intriguing phenomena absent in equilibrium physics. One famous example is the quantum Mpemba effect, where the subsystem symmetry is restored faster under a symmetric quench from a more asymmetric initial state. The quantum Mpemba effect has been extensively studied in integrable and chaotic systems. In this Letter, we investigate symmetry restoration and quantum Mpemba effect in many-body localized systems with various initial states. We reveal that the symmetry can still be fully restored in many-body localization phases without approaching thermal equilibrium. Furthermore, we demonstrate that the presence of the quantum Mpemba effect is universal for any initial tilted product state, contrasting to the cases in the chaotic systems where the presence of the quantum Mpemba effect relies on the choice of initial states. We also provide a theoretical analysis of symmetry restoration and quantum Mpemba effects with the help of the effective model for many-body localization. This Letter not only sheds light on extending the quantum Mpemba effect to more non-equilibrium settings but also contributes to a deeper understanding of the many-body localization., Comment: 23 pages (including supplemental materials), 11 figures

This research explores the enhancement of lunar landing precision through an advanced structured light system, integrating machine learning, Iterative Learning Control (ILC) and Structured Illumination Microscopy (SIM) techniques. By employing Moire fringe patterns for high-precision scanning maneuvers, the study addresses the limitations of conventional structured light systems. A nonlinear mathematical optimization model is developed to refine the world model, optimizing oscillation frequency and amplitude to improve resolution. The findings suggest that this approach can double the conventional resolution, promising significant advancements in the accuracy of lunar landings, with potential real-time application., Comment: 5 pages, 1 figure

Neural network models for audio tasks, such as automatic speech recognition (ASR) and acoustic scene classification (ASC), are susceptible to noise contamination for real-life applications. To improve audio quality, an enhancement module, which can be developed independently, is explicitly used at the front-end of the target audio applications. In this paper, we present an end-to-end learning solution to jointly optimise the models for audio enhancement (AE) and the subsequent applications. To guide the optimisation of the AE module towards a target application, and especially to overcome difficult samples, we make use of the sample-wise performance measure as an indication of sample importance. In experiments, we consider four representative applications to evaluate our training paradigm, i.e., ASR, speech command recognition (SCR), speech emotion recognition (SER), and ASC. These applications are associated with speech and non-speech tasks concerning semantic and non-semantic features, transient and global information, and the experimental results indicate that our proposed approach can considerably boost the noise robustness of the models, especially at low signal-to-noise ratios (SNRs), for a wide range of computer audition tasks in everyday-life noisy environments.

Cognitive diagnosis models (CDMs) are designed to learn students' mastery levels using their response logs. CDMs play a fundamental role in online education systems since they significantly influence downstream applications such as teachers' guidance and computerized adaptive testing. Despite the success achieved by existing CDMs, we find that they suffer from a thorny issue that the learned students' mastery levels are too similar. This issue, which we refer to as oversmoothing, could diminish the CDMs' effectiveness in downstream tasks. CDMs comprise two core parts: learning students' mastery levels and assessing mastery levels by fitting the response logs. This paper contends that the oversmoothing issue arises from that existing CDMs seldom utilize response signals on exercises in the learning part but only use them as labels in the assessing part. To this end, this paper proposes an oversmoothing-resistant cognitive diagnosis framework (ORCDF) to enhance existing CDMs by utilizing response signals in the learning part. Specifically, ORCDF introduces a novel response graph to inherently incorporate response signals as types of edges. Then, ORCDF designs a tailored response-aware graph convolution network (RGC) that effectively captures the crucial response signals within the response graph. Via ORCDF, existing CDMs are enhanced by replacing the input embeddings with the outcome of RGC, allowing for the consideration of response signals on exercises in the learning part. Extensive experiments on real-world datasets show that ORCDF not only helps existing CDMs alleviate the oversmoothing issue but also significantly enhances the models' prediction and interpretability performance. Moreover, the effectiveness of ORCDF is validated in the downstream task of computerized adaptive testing.

Traditional robotic motion planning methods often struggle with fixed resolutions in dynamically changing environments. To address these challenges, we introduce the A-OctoMap, an adaptive Octo-Tree structure that enhances spatial representation and facilitates real-time, efficient motion planning. This novel framework allows for dynamic space partitioning and multi-resolution queries, significantly improving computational efficiency and precision. Key innovations include a tree-based data structure for enhanced geometric processing, real-time map updating for accurate trajectory planning, and efficient collision detection. Our extensive testing shows superior navigation safety and efficiency in complex settings compared to conventional methods. A-OctoMap sets a new standard for adaptive spatial mapping in autonomous systems, promising significant advancements in navigating unpredictable environments., Comment: 8 pages, 6 figures

The significance of intelligent sensing systems is growing in the realm of smart services. These systems extract relevant signal features and generate informative representations for particular tasks. However, building the feature extraction component for such systems requires extensive domain-specific expertise or data. The exceptionally rapid development of foundation models is likely to usher in newfound abilities in such intelligent sensing. We propose a new scheme for sensing model, which we refer to as semi-generalist sensing model (SGSM). SGSM is able to semiautomatically solve various tasks using relatively less task-specific labeled data compared to traditional systems. Built through the analysis of the common theoretical model, SGSM can depict different modalities, such as the acoustic and Wi-Fi signal. Experimental results on such two heterogeneous sensors illustrate that SGSM functions across a wide range of scenarios, thereby establishing its broad applicability. In some cases, SGSM even achieves better performance than sensor-specific specialized solutions. Wi-Fi evaluations indicate a 20\% accuracy improvement when applying SGSM to an existing sensing model.

Theorem 1 in Bikhchandani & Segal (2011; Theoretical Economics) suggests that a complete, transitive, monotonic, and continuous preference is regret based if and only if it is expected utility. Their Proposition 1 suggests that transitivity and continuity of a regret-based preference implies an equivalence condition: if random variables $X$ and $Y$ have the same distribution, then $X\sim Y$. We give counterexamples to Proposition 1.

With the rapid advancement of multimodal large language models (MLLMs), their evaluation has become increasingly comprehensive. However, understanding long multimodal content, as a foundational ability for real-world applications, remains underexplored. In this work, we present Needle In A Multimodal Haystack (MM-NIAH), the first benchmark specifically designed to systematically evaluate the capability of existing MLLMs to comprehend long multimodal documents. Our benchmark includes three types of evaluation tasks: multimodal retrieval, counting, and reasoning. In each task, the model is required to answer the questions according to different key information scattered throughout the given multimodal document. Evaluating the leading MLLMs on MM-NIAH, we observe that existing models still have significant room for improvement on these tasks, especially on vision-centric evaluation. We hope this work can provide a platform for further research on long multimodal document comprehension and contribute to the advancement of MLLMs. Code and benchmark are released at https://github.com/OpenGVLab/MM-NIAH., Comment: Accepted to NeurIPS 2024 Track Datasets and Benchmarks

Large vision-language models (LVLMs) are ignorant of the up-to-date knowledge, such as LLaVA series, because they cannot be updated frequently due to the large amount of resources required, and therefore fail in many cases. For example, if a LVLM was released on January 2024, and it wouldn't know the singer of the theme song for the new Detective Conan movie, which wasn't released until April 2024. To solve the problem, a promising solution motivated by retrieval-augmented generation (RAG) is to provide LVLMs with up-to-date knowledge via internet search during inference, i.e., internet-augmented generation (IAG), which is already integrated in some closed-source commercial LVLMs such as GPT-4V. However, the specific mechanics underpinning them remain a mystery. In this paper, we propose a plug-and-play framework, for augmenting existing LVLMs in handling visual question answering (VQA) about up-to-date knowledge, dubbed SearchLVLMs. A hierarchical filtering model is trained to effectively and efficiently find the most helpful content from the websites returned by a search engine to prompt LVLMs with up-to-date knowledge. To train the model and evaluate our framework's performance, we propose a pipeline to automatically generate news-related VQA samples to construct a dataset, dubbed UDK-VQA. A multi-model voting mechanism is introduced to label the usefulness of website/content for VQA samples to construct the training set. Experimental results demonstrate the effectiveness of our framework, outperforming GPT-4V by about 25% in accuracy., Comment: 13 pages, 6 figures, a plug-and-play framework to augment large vision-language models with up-to-date internet knowledge

Detecting anomaly edges for dynamic graphs aims to identify edges significantly deviating from the normal pattern and can be applied in various domains, such as cybersecurity, financial transactions and AIOps. With the evolving of time, the types of anomaly edges are emerging and the labeled anomaly samples are few for each type. Current methods are either designed to detect randomly inserted edges or require sufficient labeled data for model training, which harms their applicability for real-world applications. In this paper, we study this problem by cooperating with the rich knowledge encoded in large language models(LLMs) and propose a method, namely AnomalyLLM. To align the dynamic graph with LLMs, AnomalyLLM pre-trains a dynamic-aware encoder to generate the representations of edges and reprograms the edges using the prototypes of word embeddings. Along with the encoder, we design an in-context learning framework that integrates the information of a few labeled samples to achieve few-shot anomaly detection. Experiments on four datasets reveal that AnomalyLLM can not only significantly improve the performance of few-shot anomaly detection, but also achieve superior results on new anomalies without any update of model parameters., Comment: 13pages

In this study, we explore the information capacity of open quantum systems, focusing on the effective channels formed by the subsystem of random quantum circuits and quantum Hamiltonian evolution. By analyzing the subsystem information capacity, which is closely linked to quantum coherent information of these effective quantum channels, we uncover a diverse range of dynamical and steady behaviors depending on the types of evolution. Therefore, the subsystem information capacity serves as a valuable tool for studying the intrinsic nature of various dynamical phases, such as integrable, localized, thermalized, and topological systems. We also reveal the impact of different initial information encoding schemes on information dynamics including one-to-one, one-to-many, and many-to-many. To support our findings, we provide representative examples for numerical simulations, including random quantum circuits with or without mid-circuit measurements, random Clifford Floquet circuits, free and interacting Aubry-Andr\'e models, and Su-Schrieffer-Heeger models. Those numerical results are further quantitatively explained using the effective statistical model mapping and the quasiparticle picture in the cases of random circuits and non-interacting Hamiltonian dynamics, respectively., Comment: 32 pages, 31 figures

Large Vision-Language Models (LVLMs) show significant strides in general-purpose multimodal applications such as visual dialogue and embodied navigation. However, existing multimodal evaluation benchmarks cover a limited number of multimodal tasks testing rudimentary capabilities, falling short in tracking LVLM development. In this study, we present MMT-Bench, a comprehensive benchmark designed to assess LVLMs across massive multimodal tasks requiring expert knowledge and deliberate visual recognition, localization, reasoning, and planning. MMT-Bench comprises $31,325$ meticulously curated multi-choice visual questions from various multimodal scenarios such as vehicle driving and embodied navigation, covering $32$ core meta-tasks and $162$ subtasks in multimodal understanding. Due to its extensive task coverage, MMT-Bench enables the evaluation of LVLMs using a task map, facilitating the discovery of in- and out-of-domain tasks. Evaluation results involving $30$ LVLMs such as the proprietary GPT-4V, GeminiProVision, and open-sourced InternVL-Chat, underscore the significant challenges posed by MMT-Bench. We anticipate that MMT-Bench will inspire the community to develop next-generation multimodal foundation models aimed at achieving general-purpose multimodal intelligence., Comment: 77 pages, 41 figures

Code translation tools (transpilers) are developed for automatic source-to-source translation. Although learning-based transpilers have shown impressive enhancement against rule-based counterparts, owing to their task-specific pre-training on extensive monolingual corpora. Their current performance still remains unsatisfactory for practical deployment, and the associated training resources are also prohibitively expensive. LLMs pre-trained on huge amounts of human-written code/text have shown remarkable performance in many code intelligence tasks due to their powerful generality, even without task-specific training. Thus, LLMs can potentially circumvent the above limitations, but they have not been exhaustively explored yet. This paper investigates diverse LLMs and learning-based transpilers for automated code translation tasks, finding that: although certain LLMs have outperformed current transpilers, they still have some accuracy issues, where most of the failures are induced by a lack of comprehension of source programs, missing clear instructions on I/O types in translation, and ignoring discrepancies between source and target programs. Enlightened by the above findings, we further propose UniTrans, a Unified code Translation framework, applicable to various LLMs, for unleashing their power in this field. Specifically, UniTrans first crafts a series of test cases for target programs with the assistance of source programs. Next, it harnesses the above auto-generated test cases to augment the code translation and then evaluate their correctness via execution. Afterward, UniTrans further (iteratively) repairs incorrectly translated programs prompted by test case execution results. Extensive experiments are conducted on six settings of translation datasets between Python, Java, and C++. Three recent LLMs of diverse sizes are tested with UniTrans, and all achieve substantial improvements., Comment: 23 pages, 7 figures, accepted by FSE'24 (2024 ACM International Conference on the Foundations of Software Engineering)

In the social media, users frequently express personal emotions, a subset of which may indicate potential suicidal tendencies. The implicit and varied forms of expression in internet language complicate accurate and rapid identification of suicidal intent on social media, thus creating challenges for timely intervention efforts. The development of deep learning models for suicide risk detection is a promising solution, but there is a notable lack of relevant datasets, especially in the Chinese context. To address this gap, this study presents a Chinese social media dataset designed for fine-grained suicide risk classification, focusing on indicators such as expressions of suicide intent, methods of suicide, and urgency of timing. Seven pre-trained models were evaluated in two tasks: high and low suicide risk, and fine-grained suicide risk classification on a level of 0 to 10. In our experiments, deep learning models show good performance in distinguishing between high and low suicide risk, with the best model achieving an F1 score of 88.39%. However, the results for fine-grained suicide risk classification were still unsatisfactory, with an weighted F1 score of 50.89%. To address the issues of data imbalance and limited dataset size, we investigated both traditional and advanced, large language model based data augmentation techniques, demonstrating that data augmentation can enhance model performance by up to 4.65% points in F1-score. Notably, the Chinese MentalBERT model, which was pre-trained on psychological domain data, shows superior performance in both tasks. This study provides valuable insights for automatic identification of suicidal individuals, facilitating timely psychological intervention on social media platforms. The source code and data are publicly available.

Cognitive diagnosis aims to gauge students' mastery levels based on their response logs. Serving as a pivotal module in web-based online intelligent education systems (WOIESs), it plays an upstream and fundamental role in downstream tasks like learning item recommendation and computerized adaptive testing. WOIESs are open learning environment where numerous new students constantly register and complete exercises. In WOIESs, efficient cognitive diagnosis is crucial to fast feedback and accelerating student learning. However, the existing cognitive diagnosis methods always employ intrinsically transductive student-specific embeddings, which become slow and costly due to retraining when dealing with new students who are unseen during training. To this end, this paper proposes an inductive cognitive diagnosis model (ICDM) for fast new students' mastery levels inference in WOIESs. Specifically, in ICDM, we propose a novel student-centered graph (SCG). Rather than inferring mastery levels through updating student-specific embedding, we derive the inductive mastery levels as the aggregated outcomes of students' neighbors in SCG. Namely, SCG enables to shift the task from finding the most suitable student-specific embedding that fits the response logs to finding the most suitable representations for different node types in SCG, and the latter is more efficient since it no longer requires retraining. To obtain this representation, ICDM consists of a construction-aggregation-generation-transformation process to learn the final representation of students, exercises and concepts. Extensive experiments across real-world datasets show that, compared with the existing cognitive diagnosis methods that are always transductive, ICDM is much more faster while maintains the competitive inference performance for new students., Comment: WWW 2024

Recent work has shown that stabilizing an affine control system while optimizing a quadratic cost subject to state and control constraints can be mapped to a sequence of Quadratic Programs (QPs) using Control Barrier Functions (CBFs) and Control Lyapunov Functions (CLFs). One of the main challenges in this method is that the QPs could easily become infeasible under safety and spatio-temporal constraints with tight control bounds. In our own recent work, we defined Auxiliary-Variable Adaptive CBFs (AVCBFs) to improve the feasibility of the CBF-based QP, while avoiding extensive parameter tuning. In this paper, we consider spatio-temporal constraints as finite-time reachability requirements. In order to satisfy these requirements, we generalize AVCBFs to Auxiliary-Variable Adaptive Control Lyapunov Barrier Functions (AVCLBFs) that work for systems and constraints with arbitrary relative degrees. We show that our method has fewer conflicts with safety and input constraints, and outperforms the state of the art in term of adaptivity and feasibility in solving the QP. We illustrate our approach on an optimal control problem for a unicycle., Comment: 8 pages, 4 figures. arXiv admin note: text overlap with arXiv:2310.00238

This paper presents ConvBench, a novel multi-turn conversation evaluation benchmark tailored for Large Vision-Language Models (LVLMs). Unlike existing benchmarks that assess individual capabilities in single-turn dialogues, ConvBench adopts a three-level multimodal capability hierarchy, mimicking human cognitive processes by stacking up perception, reasoning, and creativity. Each level focuses on a distinct capability, mirroring the cognitive progression from basic perception to logical reasoning and ultimately to advanced creativity. ConvBench comprises 577 meticulously curated multi-turn conversations encompassing 215 tasks reflective of real-world demands. Automatic evaluations quantify response performance at each turn and overall conversation level. Leveraging the capability hierarchy, ConvBench enables precise attribution of conversation mistakes to specific levels. Experimental results reveal a performance gap between multi-modal models, including GPT4-V, and human performance in multi-turn conversations. Additionally, weak fine-grained perception in multi-modal models contributes to reasoning and creation failures. ConvBench serves as a catalyst for further research aimed at enhancing visual dialogues.

Dynamic obstacle avoidance is a challenging topic for optimal control and optimization-based trajectory planning problems. Many existing works use Control Barrier Functions (CBFs) to enforce safety constraints for control systems. CBFs are typically formulated based on the distance to obstacles, or integrated with path planning algorithms as a safety enhancement tool. However, these approaches usually require knowledge of the obstacle boundary equations or have very slow computational efficiency. In this paper, we propose a framework based on model predictive control (MPC) with discrete-time high-order CBFs (DHOCBFs) to generate a collision-free trajectory. The DHOCBFs are first obtained from convex polytopes generated through grid mapping, without the need to know the boundary equations of obstacles. Additionally, a path planning algorithm is incorporated into this framework to ensure the global optimality of the generated trajectory. We demonstrate through numerical examples that our framework allows a unicycle robot to safely and efficiently navigate tight, dynamically changing environments with both convex and nonconvex obstacles. By comparing our method to established CBF-based benchmarks, we demonstrate superior computing efficiency, length optimality, and feasibility in trajectory generation and obstacle avoidance., Comment: 8 pages, 6 figures. arXiv admin note: text overlap with arXiv:2210.04361

Entanglement asymmetry, which serves as a diagnostic tool for symmetry breaking and a proxy for thermalization, has recently been proposed and studied in the context of symmetry restoration for quantum many-body systems undergoing a quench. In this Letter, we investigate symmetry restoration in various symmetric random quantum circuits, particularly focusing on the U(1) symmetry case. In contrast to non-symmetric random circuits where the U(1) symmetry of a small subsystem can always be restored at late times, we reveal that symmetry restoration can fail in U(1)-symmetric circuits for certain weak symmetry-broken initial states in finite-size systems. In the early-time dynamics, we observe an intriguing quantum Mpemba effect implying that symmetry is restored faster when the initial state is more asymmetric. Furthermore, we also investigate the entanglement asymmetry dynamics for SU(2) and $Z_{2}$ symmetric circuits and identify the presence and absence of the quantum Mpemba effect for the corresponding symmetries, respectively. A unified understanding of these results is provided through the lens of quantum thermalization with conserved charges., Comment: Reference updated