Search

Models based on recursive adaptive partitioning such as decision trees and their ensembles are popular for high-dimensional regression as they can potentially avoid the curse of dimensionality. Because empirical risk minimization (ERM) is computationally infeasible, these models are typically trained using greedy algorithms. Although effective in many cases, these algorithms have been empirically observed to get stuck at local optima. We explore this phenomenon in the context of learning sparse regression functions over $d$ binary features, showing that when the true regression function $f^*$ does not satisfy Abbe et al. (2022)'s Merged Staircase Property (MSP), greedy training requires $\exp(\Omega(d))$ to achieve low estimation error. Conversely, when $f^*$ does satisfy MSP, greedy training can attain small estimation error with only $O(\log d)$ samples. This dichotomy mirrors that of two-layer neural networks trained with stochastic gradient descent (SGD) in the mean-field regime, thereby establishing a head-to-head comparison between SGD-trained neural networks and greedy recursive partitioning estimators. Furthermore, ERM-trained recursive partitioning estimators achieve low estimation error with $O(\log d)$ samples irrespective of whether $f^*$ satisfies MSP, thereby demonstrating a statistical-computational trade-off for greedy training. Our proofs are based on a novel interpretation of greedy recursive partitioning using stochastic process theory and a coupling technique that may be of independent interest.

Word embeddings and language models have transformed natural language processing (NLP) by facilitating the representation of linguistic elements in continuous vector spaces. This review visits foundational concepts such as the distributional hypothesis and contextual similarity, tracing the evolution from sparse representations like one-hot encoding to dense embeddings including Word2Vec, GloVe, and fastText. We examine both static and contextualized embeddings, underscoring advancements in models such as ELMo, BERT, and GPT and their adaptations for cross-lingual and personalized applications. The discussion extends to sentence and document embeddings, covering aggregation methods and generative topic models, along with the application of embeddings in multimodal domains, including vision, robotics, and cognitive science. Advanced topics such as model compression, interpretability, numerical encoding, and bias mitigation are analyzed, addressing both technical challenges and ethical implications. Additionally, we identify future research directions, emphasizing the need for scalable training techniques, enhanced interpretability, and robust grounding in non-textual modalities. By synthesizing current methodologies and emerging trends, this survey offers researchers and practitioners an in-depth resource to push the boundaries of embedding-based language models., Comment: 21 pages

In the ultra-low inter-core crosstalk working zone of terrestrial multi-band and multi-core fiber (MCF) elastic optical networks (EONs), the ICXT in all channels of all cores remains below the ICXT threshold of the highest modulation format level (64QAM) for long-haul distances (10000 km). This paper analyzes the performance of this type of MCF in multi-band EONs (MB-EONs). We investigate two band and space division multiplexing (BSDM) scenarios: MCF and a bundle of multi-fiber pairs (BuMFP). Furthermore, the UL-ICXT performance of two MCFs, one with the standard cladding diameter (CD = 125 micrometers) with 4 cores and another with a nonstandard larger CD with 7 cores, is evaluated in the US backbone network. Our findings show that, with careful design of the MCFs physical structure, even with a standard CD, it is possible to achieve UL-ICXT in C, L, and S-band long-haul BSDM EONs. Additionally, the simulation results show that network throughput for BSDM EONs with MCFs in the UL-ICXT regime is up to 12 percent higher than the BuMFP scenario, with capacity increasing linearly with the number of cores.

We derive a modified master equation for the quantum Rabi model in the parameter regime where quantum criticality can occur. The modified master equation can avoid some unphysical predictions, such as excitations in the system at zero temperature and emission of ground-state photons. Due to spectrum collapse, we find that there is mostly no energy relaxation in the system at the critical point. For the same reason, phase coherence rapidly reduces and vanishes at the critical point. We analyze the quantum metrological limits of the system in the presence of dephasing. These results show a strong limitation on the precision of phase-shift estimation., Comment: 7 pages, two figures, comments are welcome

We consider a distributed detection problem within a wireless sensor network (WSN), where a substantial number of sensors cooperate to detect the existence of sparse stochastic signals. To achieve a trade-off between detection performance and system constraints, multi-bit quantizers are employed at local sensors. Then, two quantization strategies, namely raw quantization (RQ) and likelihood ratio quantization (LQ), are examined. The multi-bit quantized signals undergo encoding into binary codewords and are subsequently transmitted to the fusion center via error-prone reporting channels. Upon exploiting the locally most powerful test (LMPT) strategy, we devise two multi-bit LMPT detectors in which quantized raw observations and local likelihood ratios are fused respectively. Moreover, the asymptotic detection performance of the proposed quantized detectors is analyzed, and closed-form expressions for the detection and false alarm probabilities are derived. Furthermore, the multi-bit quantizer design criterion, considering both RQ and LQ, is then proposed to achieve near-optimal asymptotic performance for our proposed detectors. The normalized Fisher information and asymptotic relative efficiency are derived, serving as tools to analyze and compensate for the loss of information introduced by the quantization. Simulation results validate the effectiveness of the proposed detectors, especially in scenarios with low signal-to-noise ratios and poor channel conditions., Comment: Accepted by IEEE Transactions on Signal and Information Processing over Networks

The pyrochlore lattice magnet has been one of the most fruitful platforms for the experimental and theoretical search for spin liquids. Besides the canonical case of spin ice, works in recent years have identified a variety of new quantum and classical spin liquids from the generic nearest-neighbor anisotropic spin Hamiltonian on the pyrochlore lattice. However, a general framework for the thorough classification and characterization of these exotic states of matter has been lacking, and so is an exhaustive list of all possible spin liquids that this model can support and what is the corresponding structure of their emergent field theory. In this work, we develop such a theoretical framework to allocate interaction parameters stabilizing different classical spin liquids and derive their corresponding effective generalized emerging Gauss's laws at low temperatures. Combining this with Monte Carlo simulations, we systematically identify all classical spin liquids for the general nearest-neighbor anisotropic spin Hamiltonian on the pyrochlore lattice. We uncover new spin liquid models with exotic forms of generalized Gauss's law and multipole conservation laws. Furthermore, we present an atlas of all spin liquid regimes in the phase diagram, which illuminates the global picture of how different classical spin liquids are connected in parameter space and transition into each other. Our work serves as a treasure map for the theoretical study of classical and quantum spin liquids, as well as for the experimental search and rationalization of exotic pyrochlore lattice magnets., Comment: 25 pages, 10 figures, 5 tables

This article presents the design of an open-API-based explainable AI (XAI) service to provide feature contribution explanations for cloud AI services. Cloud AI services are widely used to develop domain-specific applications with precise learning metrics. However, the underlying cloud AI services remain opaque on how the model produces the prediction. We argue that XAI operations are accessible as open APIs to enable the consolidation of the XAI operations into the cloud AI services assessment. We propose a design using a microservice architecture that offers feature contribution explanations for cloud AI services without unfolding the network structure of the cloud models. We can also utilize this architecture to evaluate the model performance and XAI consistency metrics showing cloud AI services trustworthiness. We collect provenance data from operational pipelines to enable reproducibility within the XAI service. Furthermore, we present the discovery scenarios for the experimental tests regarding model performance and XAI consistency metrics for the leading cloud vision AI services. The results confirm that the architecture, based on open APIs, is cloud-agnostic. Additionally, data augmentations result in measurable improvements in XAI consistency metrics for cloud AI services., Comment: Published in: IEEE Transactions on Cloud Computing ( Volume: 12, Issue: 2, April-June 2024)

We introduce Dynamic Dropout, a novel regularization technique designed to enhance the training efficiency of Transformer models by dynamically adjusting the dropout rate based on training epochs or validation loss improvements. This approach addresses the challenge of balancing regularization and model capacity, which is crucial for achieving fast convergence and high performance. Our method involves modifying the GPT model to accept a variable dropout rate and updating dropout layers during training using schedules such as linear decay, exponential decay, and validation loss-based adjustments. Extensive experiments on the Shakespeare\_char dataset demonstrate that Dynamic Dropout significantly accelerates training and improves inference efficiency compared to a baseline model with a fixed dropout rate. The validation loss-based adjustment schedule provided the best overall performance, highlighting the potential of Dynamic Dropout as a valuable technique for training large-scale Transformer models.

Extreme mass-ratio hyperbolic encounters (EMRHEs) around the supermassive black holes will be observable at the future gravitational-wave (GW) detectors in space, such as LISA and Taiji. Here we consider such EMRHEs in the presence of surrounding matter distribution including baryonic accretion disk and dark matter (DM) spike, and estimate their effects on the orbital evolution and GW waveforms. We find that large possible impacts come from the gravitational potential of accretion disk, while the influence of DM spike is small. We also illustrate that environments can leave distinctive imprints on the GW waveforms, but resolving such modifications is found to be challenging for LISA-like detectors in the near future., Comment: 20 pages, 10 figures

Semi-supervised learning (SSL) is a popular solution to alleviate the high annotation cost in medical image classification. As a main branch of SSL, consistency regularization engages in imposing consensus between the predictions of a single sample from different views, termed as Absolute Location consistency (AL-c). However, only AL-c may be insufficient. Just like when diagnosing a case in practice, besides the case itself, the doctor usually refers to certain related trustworthy cases to make more reliable decisions.Therefore, we argue that solely relying on AL-c may ignore the relative differences across samples, which we interpret as relative locations, and only exploit limited information from one perspective. To address this issue, we propose a Sample Consistency Mean Teacher (SCMT) which not only incorporates AL c but also additionally enforces consistency between the samples' relative similarities to its related samples, called Relative Location consistency (RL c). AL c and RL c conduct consistency regularization from two different perspectives, jointly extracting more diverse semantic information for classification. On the other hand, due to the highly similar structures in medical images, the sample distribution could be overly dense in feature space, making their relative locations susceptible to noise. To tackle this problem, we further develop a Sample Scatter Mean Teacher (SSMT) by utilizing contrastive learning to sparsify the sample distribution and obtain robust and effective relative locations. Extensive experiments on different datasets demonstrate the superiority of our method., Comment: Accepted by IEEE Transactions on Emerging Topics in Computational Intelligence

We explore the entanglement dynamics of two detectors undergoing uniform acceleration and circular motion within a massive scalar field, while also investigating the influence of the anti-Unruh effect on entanglement harvesting. Contrary to the conventional understanding of the weak anti-Unruh effect, where entanglement typically increases, we observe that the maximum entanglement between detectors does not exhibit a strict monotonic dependence on detector acceleration. Particularly at low accelerations, fluctuations in the entanglement maxima show a strong correlation with fluctuations in detector transition rates.We also find that the maximum entanglement of detectors tends to increase with smaller field mass. Novelly, our findings indicate the absence of a strong anti-Unruh effect in (3+1)-dimensional massive scalar fields. Instead, thermal effects arising from acceleration contribute to a decrease in the detector entanglement maximum.

Diffusion model, as a powerful generative model, has found a wide range of applications including MRI reconstruction. However, most existing diffusion model-based MRI reconstruction methods operate directly in pixel space, which makes their optimization and inference computationally expensive. Latent diffusion models were introduced to address this problem in natural image processing, but directly applying them to MRI reconstruction still faces many challenges, including the lack of control over the generated results, the adaptability of Variational AutoEncoder (VAE) to MRI, and the exploration of applicable data consistency in latent space. To address these challenges, a Latent Diffusion Prior based undersampled MRI reconstruction (LDPM) method is proposed. A sketcher module is utilized to provide appropriate control and balance the quality and fidelity of the reconstructed MR images. A VAE adapted for MRI tasks (MR-VAE) is explored, which can serve as the backbone for future MR-related tasks. Furthermore, a variation of the DDIM sampler, called the Dual-Stage Sampler, is proposed to achieve high-fidelity reconstruction in the latent space. The proposed method achieves competitive results on fastMRI datasets, and the effectiveness of each module is demonstrated in ablation experiments.

Scaling large language models (LLMs) demands extensive data and computing resources, which are traditionally constrained to data centers by the high-bandwidth requirements of distributed training. Low-bandwidth methods like federated learning (FL) could enable collaborative training of larger models across weakly-connected GPUs if they can effectively be used for pre-training. To achieve this, we introduce Photon, the first complete system for federated end-to-end LLM training, leveraging cross-silo FL for global-scale training with minimal communication overheads. Using Photon, we train the first federated family of decoder-only LLMs from scratch. We show that: (1) Photon can train model sizes up to 7B in a federated fashion while reaching an even better perplexity than centralized pre-training; (2) Photon model training time decreases with available compute, achieving a similar compute-time trade-off to centralized; and (3) Photon outperforms the wall-time of baseline distributed training methods by 35% via communicating 64x-512xless. Our proposal is robust to data heterogeneity and converges twice as fast as previous methods like DiLoCo. This surprising data efficiency stems from a unique approach combining small client batch sizes with extremely high learning rates, enabled by federated averaging's robustness to hyperparameters. Photon thus represents the first economical system for global internet-wide LLM pre-training., Comment: 13 pages, 9 appendix pages, 10 figures, 3 algorithms, 8 tables

Large language models (LLMs) pre-trained on massive corpora have demonstrated impressive few-shot learning capability on many NLP tasks. Recasting an NLP task into a text-to-text generation task is a common practice so that generative LLMs can be prompted to resolve it. However, performing document-level relation extraction (DocRE) tasks with generative LLM models is still challenging due to the structured output format of DocRE, which complicates the conversion to plain text. Limited information available in few-shot samples and prompt instructions induce further difficulties and challenges in relation extraction for mentioned entities in a document. In this paper, we represent the structured output as a graph-style triplet rather than natural language expressions and leverage generative LLMs for the DocRE task. Our approach, the Graph-DPEP framework is grounded in the reasoning behind triplet explanation thoughts presented in natural language. In this framework, we first introduce a ``decomposed-plug" method for performing the generation from LLMs over prompts with type-space decomposition to alleviate the burden of distinguishing all relation types. Second, we employ a verifier for calibrating the generation and identifying overlooked query entity pairs. Third, we develop "ensemble-play", reapplying generation on the entire type list by leveraging the reasoning thoughts embedded in a sub-graph associated with the missing query pair to address the missingness issue. Through extensive comparisons with existing prompt techniques and alternative Language Models (LLMs), our framework demonstrates superior performance on publicly available benchmarks in experiments.

Analyzing programs with loops is a challenging task, suffering from potential issues such as indeterminate number of iterations and exponential growth of control flow complexity. Loop summarization, as a static analysis method for concrete semantic interpretation, receives increasing focuses. It produces symbolic expressions semantically equivalent to the loop program. However, current loop summarization methods are only suitable for single-branch loops or multi-branch loops with simple cycles, without supporting complex loops with irregular branch-to-branch transitions. In this paper, we proposed LoopSCC, a novel loop summarization technique, to achieve concrete semantic interpretation on complex loop. LoopSCC analyzes the control flow at the granularity of single-loop-path and applies the strongly connected components (SCC for short) for contraction and simplification, resulting in the contracted single-loop-path graph (CSG for short). Based on the control flow information provided by the CSG, we can convert the loop summary into a combination of SCC summaries. When an SCC contains irregular branch-to-branch transitions, we propose to explore a convergent range to identify the determinate cycles of different execution paths, referred as oscillatory interval. The loop summarization composed of both iteration conditions and execution operations can eventually be derived recursively. Extensive experiments compared to six state-of-the-art loop interpretation methods are conducted to evaluate the effectiveness of LoopSCC. From the results, LoopSCC outperforms comparative methods in both interpretation accuracy and application effectiveness. Especially, LoopSCC achieves a 100% interpretation accuracy on public common-used benchmark. A systematical study for loop properties on three large-scale programs illustrates that LoopSCC presents outstanding scalability for real-world loop programs.

Assertion-based verification (ABV) is a critical method to ensure logic designs comply with their architectural specifications. ABV requires assertions, which are generally converted from specifications through human interpretation by verification engineers. Existing methods for generating assertions from specification documents are limited to sentences extracted by engineers, discouraging their practical applications. In this work, we present AssertLLM, an automatic assertion generation framework that processes complete specification documents. AssertLLM can generate assertions from both natural language and waveform diagrams in specification files. It first converts unstructured specification sentences and waveforms into structured descriptions using natural language templates. Then, a customized Large Language Model (LLM) generates the final assertions based on these descriptions. Our evaluation demonstrates that AssertLLM can generate more accurate and higher-quality assertions compared to GPT-4o and GPT-3.5., Comment: Accepted by ASPDAC'25. arXiv admin note: substantial text overlap with arXiv:2402.00386

Time series anomaly detection (TSAD) is becoming increasingly vital due to the rapid growth of time series data across various sectors. Anomalies in web service data, for example, can signal critical incidents such as system failures or server malfunctions, necessitating timely detection and response. However, most existing TSAD methodologies rely heavily on manual feature engineering or require extensive labeled training data, while also offering limited interpretability. To address these challenges, we introduce a pioneering framework called the Time Series Anomaly Multimodal Analyzer (TAMA), which leverages the power of Large Multimodal Models (LMMs) to enhance both the detection and interpretation of anomalies in time series data. By converting time series into visual formats that LMMs can efficiently process, TAMA leverages few-shot in-context learning capabilities to reduce dependence on extensive labeled datasets. Our methodology is validated through rigorous experimentation on multiple real-world datasets, where TAMA consistently outperforms state-of-the-art methods in TSAD tasks. Additionally, TAMA provides rich, natural language-based semantic analysis, offering deeper insights into the nature of detected anomalies. Furthermore, we contribute one of the first open-source datasets that includes anomaly detection labels, anomaly type labels, and contextual description, facilitating broader exploration and advancement within this critical field. Ultimately, TAMA not only excels in anomaly detection but also provides a comprehensive approach for understanding the underlying causes of anomalies, pushing TSAD forward through innovative methodologies and insights., Comment: Under review

Designing causal bandit algorithms depends on two central categories of assumptions: (i) the extent of information about the underlying causal graphs and (ii) the extent of information about interventional statistical models. There have been extensive recent advances in dispensing with assumptions on either category. These include assuming known graphs but unknown interventional distributions, and the converse setting of assuming unknown graphs but access to restrictive hard/$\operatorname{do}$ interventions, which removes the stochasticity and ancestral dependencies. Nevertheless, the problem in its general form, i.e., unknown graph and unknown stochastic intervention models, remains open. This paper addresses this problem and establishes that in a graph with $N$ nodes, maximum in-degree $d$ and maximum causal path length $L$, after $T$ interaction rounds the regret upper bound scales as $\tilde{\mathcal{O}}((cd)^{L-\frac{1}{2}}\sqrt{T} + d + RN)$ where $c>1$ is a constant and $R$ is a measure of intervention power. A universal minimax lower bound is also established, which scales as $\Omega(d^{L-\frac{3}{2}}\sqrt{T})$. Importantly, the graph size $N$ has a diminishing effect on the regret as $T$ grows. These bounds have matching behavior in $T$, exponential dependence on $L$, and polynomial dependence on $d$ (with the gap $d\ $). On the algorithmic aspect, the paper presents a novel way of designing a computationally efficient CB algorithm, addressing a challenge that the existing CB algorithms using soft interventions face., Comment: 42 pages, 8 figures

Recent developments in 2D visual generation have been remarkably successful. However, 3D and 4D generation remain challenging in real-world applications due to the lack of large-scale 4D data and effective model design. In this paper, we propose to jointly investigate general 3D and 4D generation by leveraging camera and object movements commonly observed in daily life. Due to the lack of real-world 4D data in the community, we first propose a data curation pipeline to obtain camera poses and object motion strength from videos. Based on this pipeline, we introduce a large-scale real-world 4D scene dataset: CamVid-30K. By leveraging all the 3D and 4D data, we develop our framework, GenXD, which allows us to produce any 3D or 4D scene. We propose multiview-temporal modules, which disentangle camera and object movements, to seamlessly learn from both 3D and 4D data. Additionally, GenXD employs masked latent conditions to support a variety of conditioning views. GenXD can generate videos that follow the camera trajectory as well as consistent 3D views that can be lifted into 3D representations. We perform extensive evaluations across various real-world and synthetic datasets, demonstrating GenXD's effectiveness and versatility compared to previous methods in 3D and 4D generation.

Data sharing is a prerequisite for collaborative innovation, enabling organizations to leverage diverse datasets for deeper insights. In real-world applications like FinTech and Smart Manufacturing, transactional data, often in tabular form, are generated and analyzed for insight generation. However, such datasets typically contain sensitive personal/business information, raising privacy concerns and regulatory risks. Data synthesis tackles this by generating artificial datasets that preserve the statistical characteristics of real data, removing direct links to individuals. However, attackers can still infer sensitive information using background knowledge. Differential privacy offers a solution by providing provable and quantifiable privacy protection. Consequently, differentially private data synthesis has emerged as a promising approach to privacy-aware data sharing. This paper provides a comprehensive overview of existing differentially private tabular data synthesis methods, highlighting the unique challenges of each generation model for generating tabular data under differential privacy constraints. We classify the methods into statistical and deep learning-based approaches based on their generation models, discussing them in both centralized and distributed environments. We evaluate and compare those methods within each category, highlighting their strengths and weaknesses in terms of utility, privacy, and computational complexity. Additionally, we present and discuss various evaluation methods for assessing the quality of the synthesized data, identify research gaps in the field and directions for future research.

WebAssembly is a low-level bytecode language designed for client-side execution in web browsers. The need for decompilation techniques that recover high-level source code from WASM binaries has grown as WASM continues to gain widespread adoption and its security concerns. However little research has been done to assess the quality of decompiled code from WASM. This paper aims to fill this gap by conducting a comprehensive comparative analysis between decompiled C code from WASM binaries and state-of-the-art native binary decompilers. We presented a novel framework for empirically evaluating C-based decompilers from various aspects including correctness/ readability/ and structural similarity. The proposed metrics are validated practicality in decompiler assessment and provided insightful observations regarding the characteristics and constraints of existing decompiled code. This in turn contributes to bolstering the security and reliability of software systems that rely on WASM and native binaries., Comment: SecureComm'24: Proceedings of the 20th EAI International Conference on Security and Privacy in Communication Networks

We study a generalization of the Schramm-Loewner evolution loop measure to pairs of non-intersecting Jordan curves on the Riemann sphere. We also introduce four equivalent definitions for a two-loop Loewner potential: respectively expressing it in terms of normalized Brownian loop measure, zeta-regularized determinants of the Laplacian, an integral formula generalizing universal Liouville action, and Loewner-Kufarev energy of a foliation. Moreover, we prove that the potential is finite if and only if both loops are Weil-Petersson quasicircles, that it is an Onsager-Machlup functional for the two-loop SLE, and a variational formula involving Schwarzian derivatives. Addressing the question of minimization of the two-loop Loewner potential, we find that any such minimizers must be pairs of circles. However, the potential is not bounded, diverging to negative infinity as the circles move away from each other and to positive infinity as the circles merge, thus preventing a definition of two-loop Loewner energy for the prospective large deviations theory for the two-loop SLE. To remedy the divergence, we study a way of generalizing the two-loop Loewner potential by taking into account how conformal field theory (CFT) partition functions depend on the modulus of the annulus between the loops. This generalization is motivated by the correspondence between SLE and CFT, and it also emerges from the geometry of the real determinant line bundle as introduced by Kontsevich and Suhov., Comment: 36 pages, 5 figures

Continual learning aims to incrementally acquire new concepts in data streams while resisting forgetting previous knowledge. With the rise of powerful pre-trained models (PTMs), there is a growing interest in training incremental learning systems using these foundation models, rather than learning from scratch. Existing works often view PTMs as a strong initial point and directly apply parameter-efficient tuning (PET) in the first session for adapting to downstream tasks. In the following sessions, most methods freeze model parameters for tackling forgetting issues. However, applying PET directly to downstream data cannot fully explore the inherent knowledge in PTMs. Additionally, freezing the parameters in incremental sessions hinders models' plasticity to novel concepts not covered in the first session. To solve the above issues, we propose a Slow And Fast parameter-Efficient tuning (SAFE) framework. In particular, to inherit general knowledge from foundation models, we include a transfer loss function by measuring the correlation between the PTM and the PET-applied model. After calibrating in the first session, the slow efficient tuning parameters can capture more informative features, improving generalization to incoming classes. Moreover, to further incorporate novel concepts, we strike a balance between stability and plasticity by fixing slow efficient tuning parameters and continuously updating the fast ones. Specifically, a cross-classification loss with feature alignment is proposed to circumvent catastrophic forgetting. During inference, we introduce an entropy-based aggregation strategy to dynamically utilize the complementarity in the slow and fast learners. Extensive experiments on seven benchmark datasets verify the effectiveness of our method by significantly surpassing the state-of-the-art., Comment: Accepted by NeurIPS 2024

Inverse protein folding is a fundamental task in computational protein design, which aims to design protein sequences that fold into the desired backbone structures. While the development of machine learning algorithms for this task has seen significant success, the prevailing approaches, which predominantly employ a discriminative formulation, frequently encounter the error accumulation issue and often fail to capture the extensive variety of plausible sequences. To fill these gaps, we propose Bridge-IF, a generative diffusion bridge model for inverse folding, which is designed to learn the probabilistic dependency between the distributions of backbone structures and protein sequences. Specifically, we harness an expressive structure encoder to propose a discrete, informative prior derived from structures, and establish a Markov bridge to connect this prior with native sequences. During the inference stage, Bridge-IF progressively refines the prior sequence, culminating in a more plausible design. Moreover, we introduce a reparameterization perspective on Markov bridge models, from which we derive a simplified loss function that facilitates more effective training. We also modulate protein language models (PLMs) with structural conditions to precisely approximate the Markov bridge process, thereby significantly enhancing generation performance while maintaining parameter-efficient training. Extensive experiments on well-established benchmarks demonstrate that Bridge-IF predominantly surpasses existing baselines in sequence recovery and excels in the design of plausible proteins with high foldability. The code is available at https://github.com/violet-sto/Bridge-IF., Comment: NeurIPS 2024

In this manuscript, we aim to establish global existence of weak solutions with higher regularity to the compressible Navier-Stokes equations under no-slip boundary conditions. Though Lions\cite{L1} and Feireisl\cite{F1} have established global weak solutions with finite energy under Dirichelet boundary conditions by making use of so called effective viscous flux and oscillation defect measure,Hoff has investigated global weak solutions with higher regularity in \cite{H1,Hof2} when the domain is either whole space or half space with Navier-slip boundary conditions, yet the existence theory of global weak solution with higher regularity under Dirichlet boundary conditions remains unknown. In this paper we prove that the system will admit at least one global weak solutions with higher regularity as long as the initial energy is suitably small when the domain is a 2D solid disc. This is achieved by exploiting the structure of the exact Green function of the disc to decompose the effective viscous flux into three parts, which corresponds to the pressure term, boundary term and the remaining term respectively. In order to control the boundary term, one of the key observations is to use the geometry of the domain which sucessfully to bound the integral of the effective viscous flux where $L^1$ norm is always unbounded., Comment: 30 pages

Lead-halide perovskites are semiconductor materials with attractive properties for photovoltaic and other optoelectronic applications. However, determining crucial electronic material parameters, such as charge-carrier mobility and lifetime, is plagued by a wide range of reported values and inconsistencies caused by interpreting and reporting data originating from different measurement techniques. In this paper, we propose a method for the simultaneous determination of mobility and lifetime using only one technique: transient photoluminescence spectroscopy. By measuring and simulating the decay of the photoluminescence intensity and the redshift of the photoluminescence peak as a function of time after the laser pulse, we extract the mobility, lifetime, and diffusion length of halide perovskite films. With a voltage-dependent steady-state photoluminescence measurement on a cell, we relate the diffusion length to the external voltage and quantify its value at the maximum power point., Comment: 24 pages, 5 figures

Bright dipolar excitons, which contain electrical dipoles and have high oscillator strength, are an ideal platform for studying correlated quantum phenomena. They usually rely on carrier tunneling between two quantum wells or two layers to hybridize with nondipolar excitons to gain oscillator strength. In this work, we uncovered a new type of bright infrared dipolar exciton by stacking 90{\deg}-twisted black phosphorus (BP) structures. These excitons, inherent to the reconstructed band structure, exhibit high oscillator strength. Most importantly, they inherit the linear polarization from BP, which allows light polarization to be used to select the dipole direction. Moreover, the dipole moment and resonance energy can be widely tuned by the thickness of the BP. Our results demonstrate a useful platform for exploring tunable correlated dipolar excitons.

Advanced Persistent Threats (APTs) are continuously evolving, leveraging their stealthiness and persistence to put increasing pressure on current provenance-based Intrusion Detection Systems (IDS). This evolution exposes several critical issues: (1) The dense interaction between malicious and benign nodes within provenance graphs introduces neighbor noise, hindering effective detection; (2) The complex prediction mechanisms of existing APTs detection models lead to the insufficient utilization of prior knowledge embedded in the data; (3) The high computational cost makes detection impractical. To address these challenges, we propose Winemaking, a lightweight threat detection system built on a knowledge distillation framework, capable of node-level detection within audit log provenance graphs. Specifically, Winemaking applies graph Laplacian regularization to reduce neighbor noise, obtaining smoothed and denoised graph signals. Subsequently, Winemaking employs a teacher model based on GNNs to extract knowledge, which is then distilled into a lightweight student model. The student model is designed as a trainable combination of a feature transformation module and a personalized PageRank random walk label propagation module, with the former capturing feature knowledge and the latter learning label and structural knowledge. After distillation, the student model benefits from the knowledge of the teacher model to perform precise threat detection. We evaluate Winemaking through extensive experiments on three public datasets and compare its performance against several state-of-the-art IDS solutions. The results demonstrate that Winemaking achieves outstanding detection accuracy across all scenarios and the detection time is 1.4 to 5.2 times faster than the current state-of-the-art methods., Comment: 8 pages body, 11 pages total(without authors)

Ensuring that Multimodal Large Language Models (MLLMs) maintain consistency in their responses is essential for developing trustworthy multimodal intelligence. However, existing benchmarks include many samples where all MLLMs \textit{exhibit high response uncertainty when encountering misleading information}, requiring even 5-15 response attempts per sample to effectively assess uncertainty. Therefore, we propose a two-stage pipeline: first, we collect MLLMs' responses without misleading information, and then gather misleading ones via specific misleading instructions. By calculating the misleading rate, and capturing both correct-to-incorrect and incorrect-to-correct shifts between the two sets of responses, we can effectively metric the model's response uncertainty. Eventually, we establish a \textbf{\underline{M}}ultimodal \textbf{\underline{U}}ncertainty \textbf{\underline{B}}enchmark (\textbf{MUB}) that employs both explicit and implicit misleading instructions to comprehensively assess the vulnerability of MLLMs across diverse domains. Our experiments reveal that all open-source and close-source MLLMs are highly susceptible to misleading instructions, with an average misleading rate exceeding 86\%. To enhance the robustness of MLLMs, we further fine-tune all open-source MLLMs by incorporating explicit and implicit misleading data, which demonstrates a significant reduction in misleading rates. Our code is available at: \href{https://github.com/Yunkai696/MUB}{https://github.com/Yunkai696/MUB}

Discovery of clusters with high symmetrical geometry, such as C60 fullerene, always attract lots of interest because of their diverse nature. However, most of such interesting cluster were sporadically discovered, is there any systematic method to explore all possible high symmetrical clusters? Herein, we propose an idea to systematically construct high symmetrical structures based on novel conjugate-dual (co-dual) concept. A co-dual structure would be constructed by conjugately combining one high symmetrical polyhedron and its corresponding dual. In such co-dual structures, the symmetry of the original polyhedron could be kept or even promoted in some special cases. This provides a way to explore high symmetrical polyhedra and leads to a new cluster family, co-dual clusters. In this paper, we have systematically studied the spherical co-dual clusters with one- or two-element shells, and found a series of stable cage-like and core-shell clusters. The co-dual structures would be a new treasure box for hunting novel clusters.

A critical aspect of safe and efficient motion planning for autonomous vehicles (AVs) is to handle the complex and uncertain behavior of surrounding human-driven vehicles (HDVs). Despite intensive research on driver behavior prediction, existing approaches typically overlook the interactions between AVs and HDVs assuming that HDV trajectories are not affected by AV actions. To address this gap, we present a transformer-transfer learning-based interaction-aware trajectory predictor for safe motion planning of autonomous driving, focusing on a vehicle-to-vehicle (V2V) interaction scenario consisting of an AV and an HDV. Specifically, we construct a transformer-based interaction-aware trajectory predictor using widely available datasets of HDV trajectory data and further transfer the learned predictor using a small set of AV-HDV interaction data. Then, to better incorporate the proposed trajectory predictor into the motion planning module of AVs, we introduce an uncertainty quantification method to characterize the errors of the predictor, which are integrated into the path-planning process. Our experimental results demonstrate the value of explicitly considering interactions and handling uncertainties.

Precise alignment of multi-modal images with inherent feature discrepancies poses a pivotal challenge in deformable image registration. Traditional learning-based approaches often consider registration networks as black boxes without interpretability. One core insight is that disentangling alignment features and non-alignment features across modalities bring benefits. Meanwhile, it is challenging for the prominent methods for image registration tasks, such as convolutional neural networks, to capture long-range dependencies by their local receptive fields. The methods often fail when the given image pair has a large misalignment due to the lack of effectively learning long-range dependencies and correspondence. In this paper, we propose MambaReg, a novel Mamba-based architecture that integrates Mamba's strong capability in capturing long sequences to address these challenges. With our proposed several sub-modules, MambaReg can effectively disentangle modality-independent features responsible for registration from modality-dependent, non-aligning features. By selectively attending to the relevant features, our network adeptly captures the correlation between multi-modal images, enabling focused deformation field prediction and precise image alignment. The Mamba-based architecture seamlessly integrates the local feature extraction power of convolutional layers with the long-range dependency modeling capabilities of Mamba. Experiments on public non-rigid RGB-IR image datasets demonstrate the superiority of our method, outperforming existing approaches in terms of registration accuracy and deformation field smoothness.

Combining the efficiency of semi-empirical potentials with the accuracy of quantum mechanical methods, machine-learning interatomic potentials (MLIPs) have significantly advanced atomistic modeling in computational materials science and chemistry. This necessitates the continual development of MLIP models with improved accuracy and efficiency, which enable long-time scale molecular dynamics simulations to unveil the intricate underlying mechanisms that would otherwise remain elusive. Among various existing MLIP models, the moment tensor potential (MTP) model employs a highly descriptive rotationally-covariant moment tensor to describe the local atomic environment, enabling the use of even linear regression for model fitting. Although the current MTP model has achieved state-of-the-art efficiency for similar accuracy, there is still room for optimizing the contraction process of moment tensors. In this work, we propose an effective genetic algorithm based optimization scheme that can significantly reduce the number of independent moment tensor components and intermediate tensor components. This leads to a speedup of nearly one order of magnitude in efficiency and also improved accuracy compared to the traditional MTP model for intricate basis sets. We have applied our improved MTP model to predicting the energetic and dynamical properties of various point and planar defects in Ni-Al alloys, showing overall good performances and in general outperforming the semi-empirical potentials. This work paves the way for fast and accurate atomistic modeling of complex systems and provides a useful tool for modeling defects in Ni-Al alloys., Comment: 44 pages, 12 figures

The escalating sophistication of cyber-attacks and the widespread utilization of stealth tactics have led to significant security threats globally. Nevertheless, the existing static detection methods exhibit limited coverage, and traditional dynamic monitoring approaches encounter challenges in bypassing evasion techniques. Thus, it has become imperative to implement nuanced and dynamic analysis to achieve precise behavior detection in real time. There are two pressing concerns associated with current dynamic malware behavior detection solutions. Firstly, the collection and processing of data entail a significant amount of overhead, making it challenging to be employed for real-time detection on the end host. Secondly, these approaches tend to treat malware as a singular entity, thereby overlooking varied behaviors within one instance. To fill these gaps, we propose PARIS, an adaptive trace fetching, lightweight, real-time malicious behavior detection system. Specifically, we monitor malicious behavior with Event Tracing for Windows (ETW) and learn to selectively collect maliciousness-related APIs or call stacks, significantly reducing the data collection overhead. As a result, we can monitor a wider range of APIs and detect more intricate attack behavior. We implemented a prototype of PARIS and evaluated the system overhead, the accuracy of comparative behavior recognition, and the impact of different models and parameters. The result demonstrates that PARIS can reduce over 98.8% of data compared to the raw ETW trace and hence decreases the overhead on the host in terms of memory, bandwidth, and CPU usage with a similar detection accuracy to the baselines that suffer from the high overhead. Furthermore, a breakdown evaluation shows that 80% of the memory and bandwidth savings and a complete reduction in CPU usage can be attributed to our adaptive trace-fetching collector.

This paper makes a step towards modeling the modality discrepancy in the cross-spectral re-identification task. Based on the Lambertain model, we observe that the non-linear modality discrepancy mainly comes from diverse linear transformations acting on the surface of different materials. From this view, we unify all data augmentation strategies for cross-spectral re-identification by mimicking such local linear transformations and categorizing them into moderate transformation and radical transformation. By extending the observation, we propose a Random Linear Enhancement (RLE) strategy which includes Moderate Random Linear Enhancement (MRLE) and Radical Random Linear Enhancement (RRLE) to push the boundaries of both types of transformation. Moderate Random Linear Enhancement is designed to provide diverse image transformations that satisfy the original linear correlations under constrained conditions, whereas Radical Random Linear Enhancement seeks to generate local linear transformations directly without relying on external information. The experimental results not only demonstrate the superiority and effectiveness of RLE but also confirm its great potential as a general-purpose data augmentation for cross-spectral re-identification. The code is available at \textcolor{magenta}{\url{https://github.com/stone96123/RLE}}., Comment: Accepted to NeurIPS 2024

Manipulating garments and fabrics has long been a critical endeavor in the development of home-assistant robots. However, due to complex dynamics and topological structures, garment manipulations pose significant challenges. Recent successes in reinforcement learning and vision-based methods offer promising avenues for learning garment manipulation. Nevertheless, these approaches are severely constrained by current benchmarks, which offer limited diversity of tasks and unrealistic simulation behavior. Therefore, we present GarmentLab, a content-rich benchmark and realistic simulation designed for deformable object and garment manipulation. Our benchmark encompasses a diverse range of garment types, robotic systems and manipulators. The abundant tasks in the benchmark further explores of the interactions between garments, deformable objects, rigid bodies, fluids, and human body. Moreover, by incorporating multiple simulation methods such as FEM and PBD, along with our proposed sim-to-real algorithms and real-world benchmark, we aim to significantly narrow the sim-to-real gap. We evaluate state-of-the-art vision methods, reinforcement learning, and imitation learning approaches on these tasks, highlighting the challenges faced by current algorithms, notably their limited generalization capabilities. Our proposed open-source environments and comprehensive analysis show promising boost to future research in garment manipulation by unlocking the full potential of these methods. We guarantee that we will open-source our code as soon as possible. You can watch the videos in supplementary files to learn more about the details of our work. Our project page is available at: https://garmentlab.github.io/, Comment: NeurIPS 2024

Alongside the rapid development of Large Language Models (LLMs), there has been a notable increase in efforts to integrate LLM techniques in information retrieval (IR) and search engines (SE). Recently, an additional post-ranking stage is suggested in SE to enhance user satisfaction in practical applications. Nevertheless, research dedicated to enhancing the post-ranking stage through LLMs remains largely unexplored. In this study, we introduce a novel paradigm named Large Language Models for Post-Ranking in search engine (LLM4PR), which leverages the capabilities of LLMs to accomplish the post-ranking task in SE. Concretely, a Query-Instructed Adapter (QIA) module is designed to derive the user/item representation vectors by incorporating their heterogeneous features. A feature adaptation step is further introduced to align the semantics of user/item representations with the LLM. Finally, the LLM4PR integrates a learning to post-rank step, leveraging both a main task and an auxiliary task to fine-tune the model to adapt the post-ranking task. Experiment studies demonstrate that the proposed framework leads to significant improvements and exhibits state-of-the-art performance compared with other alternatives.

In the digital world, influencers are pivotal as opinion leaders, shaping the views and choices of their influencees. Modern advertising often follows this trend, where marketers choose appropriate influencers for product endorsements, based on thorough market analysis. Previous studies on influencer selection have typically relied on numerical representations of individual opinions and interactions, a method that simplifies the intricacies of social dynamics. In this work, we first introduce a Time-aware Influencer Simulator (TIS), helping promoters identify and select the right influencers to market their products, based on LLM simulation. To validate our approach, we conduct experiments on the public advertising campaign dataset SAGraph which encompasses social relationships, posts, and user interactions. The results show that our method outperforms traditional numerical feature-based approaches and methods using limited LLM agents. Our research shows that simulating user timelines and content lifecycles over time simplifies scaling, allowing for large-scale agent simulations in social networks. Additionally, LLM-based agents for social recommendations and advertising offer substantial benefits for decision-making in promotional campaigns., Comment: 10 pages, 5 figures

The electronic and optical properties of graphene nanoribbons under uniaxial periodic strain have been explored using various nearest-neighbor hopping patterns. It is found that by properly selecting hopping patterns, momentum-resolved gaps within minibands emerge, modifying the energy band structure to exhibit hollowed-out profiles, and enhancing peak intensity in local density of states but reducing peak count. The optical transitions are impacted by altered parity symmetry of wavefunctions, causing changes in optical selection rules. The parity of wavefunctions for strained GNRs has been established through rigorous mathematical proof, whereby the optical selection rule is determined for the strained GNRs. The absorption curves arise from a complex interplay between diminished velocity matrix elements and escalated joint density of states.

This paper introduces a new approach to enhance the robustness of humanoid walking under strong perturbations, such as substantial pushes. Effective recovery from external disturbances requires bipedal robots to dynamically adjust their stepping strategies, including footstep positions and timing. Unlike most advanced walking controllers that restrict footstep locations to a predefined convex region, substantially limiting recoverable disturbances, our method leverages reinforcement learning to dynamically adjust the permissible footstep region, expanding it to a larger, effectively non-convex area and allowing cross-over stepping, which is crucial for counteracting large lateral pushes. Additionally, our method adapts footstep timing in real time to further extend the range of recoverable disturbances. Based on these adjustments, feasible footstep positions and DCM trajectory are planned by solving a QP. Finally, we employ a DCM controller and an inverse dynamics whole-body control framework to ensure the robot effectively follows the trajectory.

Large pretrained transformer models have revolutionized modern AI applications with their state-of-the-art performance in natural language processing (NLP). However, their substantial parameter count poses challenges for real-world deployment. To address this, researchers often reduce model size by pruning parameters based on their magnitude or sensitivity. Previous research has demonstrated the limitations of magnitude pruning, especially in the context of transfer learning for modern NLP tasks. In this paper, we introduce a new magnitude-based pruning algorithm called mixture Gaussian prior pruning (MGPP), which employs a mixture Gaussian prior for regularization. MGPP prunes non-expressive weights under the guidance of the mixture Gaussian prior, aiming to retain the model's expressive capability. Extensive evaluations across various NLP tasks, including natural language understanding, question answering, and natural language generation, demonstrate the superiority of MGPP over existing pruning methods, particularly in high sparsity settings. Additionally, we provide a theoretical justification for the consistency of the sparse transformer, shedding light on the effectiveness of the proposed pruning method.

Recent neural networks (NNs) with self-attention exhibit competitiveness across different AI domains, but the essential attention mechanism brings massive computation and memory demands. To this end, various sparsity patterns are introduced to reduce the quadratic computation complexity, among which the structured butterfly sparsity has been proven efficient in computation reduction while maintaining model accuracy. However, its complicated data accessing pattern brings utilization degradation and makes parallelism hard to exploit in general block-oriented architecture like GPU. Since the reconfigurable dataflow architecture is known to have better data reusability and architectural flexibility in general NN-based acceleration, we want to apply it to the butterfly sparsity for acquiring better computational efficiency for attention workloads. We first propose a hybrid butterfly-sparsity network to obtain better trade-offs between attention accuracy and performance. Next, we propose a scalable multilayer dataflow method supported by coarse-grained streaming parallelism designs, to orchestrate the butterfly sparsity computation on the dataflow array. The experiments show that compared with Jetson Xavier NX, our design has a speedup of up to $14.34\times$ ($9.29\times$ on average) as well as $11.14\times$ energy efficiency advancement in attention workloads. In comparison with SOTA attention accelerators of the same peak performance, our dataflow architecture acquires $2.38\times$-$4.7\times$ efficiency improvement as well as $6.60\times$-$15.37\times$ energy reduction with butterfly sparsity optimization., Comment: 9 pages, 17 figures, ICCAD 2024, 2024/07/05, Butterfly Sparsity Optimization Using Dataflow

The Mixture of Experts (MoE) is an advanced model architecture in the industry that combines multiple specialized expert models from various domains into a single supermodel. This approach enables the model to scale without significantly increasing the computational costs of training and inference, while maximizing model performance. However, current distributed training frameworks do not consider the ultimate optimization of communication, especially for large base models. This paper proposes a network-traffic-aware parallel optimization method that selects the optimal parallel strategy based on the communication volume, and the training cluster's inter-node and intra-node network topologies. Compared to the DeepSpeed, MoNTA achieves an 8x increase in AllToAll communication performance under 8-card tensor parallelism. Compared to the baseline, training a 2x70B model using 16 A800 cards, with an 8K sequence, results in a 13% overall latency performance improvement. Project Page: https://github.com/EnflameTechnology/DeepSpeed.

Transformer-based models have achieved state-of-the-art performance in various computer vision tasks, including image and video analysis. However, Transformer's complex architecture and black-box nature pose challenges for explainability, a crucial aspect for real-world applications and scientific inquiry. Current Explainable AI (XAI) methods can only provide one-dimensional feature importance, either spatial or temporal explanation, with significant computational complexity. This paper introduces STAA (Spatio-Temporal Attention Attribution), an XAI method for interpreting video Transformer models. Differ from traditional methods that separately apply image XAI techniques for spatial features or segment contribution analysis for temporal aspects, STAA offers both spatial and temporal information simultaneously from attention values in Transformers. The study utilizes the Kinetics-400 dataset, a benchmark collection of 400 human action classes used for action recognition research. We introduce metrics to quantify explanations. We also apply optimization to enhance STAA's raw output. By implementing dynamic thresholding and attention focusing mechanisms, we improve the signal-to-noise ratio in our explanations, resulting in more precise visualizations and better evaluation results. In terms of computational overhead, our method requires less than 3\% of the computational resources of traditional XAI methods, making it suitable for real-time video XAI analysis applications. STAA contributes to the growing field of XAI by offering a method for researchers and practitioners to analyze Transformer models.

An asymptotically flat hairy black hole (HBH) can exhibit distinct characteristics when compared to the Schwarzschild black hole, due to the evasion of no-hair theorem by minimally coupling the Einstein gravity with a scalar potential which possesses asymmetric vacua, i.e, a false vacuum $(\phi=0)$ and a true vacuum $(\phi=\phi_1)$. In this paper, we investigate the geodesic motion of both massive test particles and photons in the vicinity of HBH with $\phi_1=0.5$ and $\phi_1=1.0$ by analyzing their effective potentials derived from the geodesic equation. By fixing $\phi_1$, the effective potential of a massive test particle increases monotonically when its angular momentum $L$ is very small. When $L$ increases to a critical value, the effective potential possesses an inflection point which is known as the innermost stable of circular orbit (ISCO), where the test particle can still remain stable in a circular orbit with a minimal radius without being absorbed by the HBH or fleeing to infinity. Beyond the critical value of $L$, the effective potential possesses a local minimum and a local maximum, indicating the existence of unstable and stable circular orbits, respectively. Moreover, the HBH possesses an unstable photon sphere but its location slightly deviates from the Schwarzschild black hole. The trajectories of null geodesics in the vicinity of HBH can also be classified into three types, which are the direct, lensing and photon sphere, based on the deflection angle of light, but the values of impact parameters can vary significantly than the Schwarzschild black hole., Comment: 11 pages with total 11 figures

The development of large language models (LLM) has revolutionized various fields and is anticipated to drive the advancement of autonomous systems. In the context of autonomous optical networks, creating a high-level cognitive agent in the control layer remains a challenge. However, LLM is primarily developed for natural language processing tasks, rendering them less effective in predicting the physical dynamics of optical communications. Moreover, optical networks demand rigorous stability, where direct deployment of strategies generated from LLM poses safety concerns. In this paper, a digital twin (DT)-enhanced LLM scheme is proposed to facilitate autonomous optical networks. By leveraging monitoring data and advanced models, the DT of optical networks can accurately characterize their physical dynamics, furnishing LLMs with dynamic-updated information for reliable decision-making. Prior to deployment, the generated strategies from LLM can be pre-verified in the DT platform, which also provides feedback to the LLM for further refinement of strategies. The synergistic interplay between DT and LLM for autonomous optical networks is demonstrated through three scenarios: performance optimization under dynamic loadings in an experimental C+L-band long-haul transmission link, protection switching for device upgrading in a field-deployed six-node mesh network, and performance recovery after fiber cuts in a field-deployed C+L-band transmission link., Comment: 7 pages,6 figures; Accepted by IEEE Communications Magazine, Open call

Network optimization is a fundamental challenge in the Internet of Things (IoT) network, often characterized by complex features that make it difficult to solve these problems. Recently, generative diffusion models (GDMs) have emerged as a promising new approach to network optimization, with the potential to directly address these optimization problems. However, the application of GDMs in this field is still in its early stages, and there is a noticeable lack of theoretical research and empirical findings. In this study, we first explore the intrinsic characteristics of generative models. Next, we provide a concise theoretical proof and intuitive demonstration of the advantages of generative models over discriminative models in network optimization. Based on this exploration, we implement GDMs as optimizers aimed at learning high-quality solution distributions for given inputs, sampling from these distributions during inference to approximate or achieve optimal solutions. Specifically, we utilize denoising diffusion probabilistic models (DDPMs) and employ a classifier-free guidance mechanism to manage conditional guidance based on input parameters. We conduct extensive experiments across three challenging network optimization problems. By investigating various model configurations and the principles of GDMs as optimizers, we demonstrate the ability to overcome prediction errors and validate the convergence of generated solutions to optimal solutions.We provide code and data at https://github.com/qiyu3816/DiffSG.

Nontrivial spectral properties of non-Hermitian systems can give rise to intriguing effects that lack counterparts in Hermitian systems. For instance, when dynamically varying system parameters along a path enclosing an exceptional point (EP), chiral mode conversion occurs. A recent study [Phys. Rev. Lett. 133, 113802 (2024)] demonstrates the achievability of pure adiabatic state transfer by specifically selecting a trajectory in the system parameter space where the corresponding evolution operator exhibits a real spectrum while winding around an EP. However, the intended adiabatic state transfer becomes fragile when taking into account the effect of the nonadiabatic transition. In this work, we propose a scheme for achieving robust and rapid adiabatic state transfer in time-modulated two-level non-Hermitian systems by appropriately modulating system Hamiltonian and time-evolution trajectory. Numerical simulations confirm that complete adiabatic transfer can always be achieved even under nonadiabatic conditions after one period for different initialized adiabatic states, and the scheme remains insensitive to moderate fluctuations in control parameters. Therefore, this scheme offers alternative approaches for quantum-state engineering in non-Hermitian systems., Comment: 7 pages, 6 figures

We measure the time-integrated CP asymmetry in $D^{0} \rightarrow K^{0}_{S}K^{0}_{S}$ decays reconstructed in $e^{+}e^{-} \rightarrow c\overline{c}$ events collected by the Belle and Belle II experiments. The corresponding data samples have integrated luminosities of 980 fb$^{-1}$ and 428 fb$^{-1}$, respectively. The $D^{0}$ decays are required to originate from the $D^{*+} \rightarrow D^{0}\pi^{+}$ decay, which determines the charm flavor at production time. A control sample of $D^{0} \rightarrow K^{+}K^{-}$ decays is used to correct for production and detection asymmetries. The result, $(-1.4\pm1.3{\rm(stat)}\pm0.1{\rm (syst)})\%$, is consistent with previous determinations and with CP symmetry., Comment: 10 pages, 3 figures. arXiv admin note: text overlap with arXiv:2410.22961

The rapid integration of generative artificial intelligence (GenAI) technology into education necessitates precise measurement of GenAI literacy to ensure that learners and educators possess the skills to engage with and critically evaluate this transformative technology effectively. Existing instruments often rely on self-reports, which may be biased. In this study, we present the GenAI Literacy Assessment Test (GLAT), a 20-item multiple-choice instrument developed following established procedures in psychological and educational measurement. Structural validity and reliability were confirmed with responses from 355 higher education students using classical test theory and item response theory, resulting in a reliable 2-parameter logistic (2PL) model (Cronbach's alpha = 0.80; omega total = 0.81) with a robust factor structure (RMSEA = 0.03; CFI = 0.97). Critically, GLAT scores were found to be significant predictors of learners' performance in GenAI-supported tasks, outperforming self-reported measures such as perceived ChatGPT proficiency and demonstrating external validity. These results suggest that GLAT offers a reliable and valid method for assessing GenAI literacy, with the potential to inform educational practices and policy decisions that aim to enhance learners' and educators' GenAI literacy, ultimately equipping them to navigate an AI-enhanced future.