Search

Advanced Air Mobility (AAM) operations are expected to transform air transportation while challenging current air traffic management practices. By introducing a novel market-based mechanism, we address the problem of on-demand allocation of capacity-constrained airspace to AAM vehicles with heterogeneous and private valuations. We model airspace and air infrastructure as a collection of contiguous regions with constraints on the number of vehicles that simultaneously enter, stay, or exit each region. Vehicles request access to the airspace with trajectories spanning multiple regions at different times. We use the graph structure of our airspace model to formulate the allocation problem as a path allocation problem on a time-extended graph. To ensure the cost information of AAM vehicles remains private, we introduce a novel mechanism that allocates each vehicle a budget of "air-credits" and anonymously charges prices for traversing the edges of the time-extended graph. We seek to compute a competitive equilibrium that ensures that: (i) capacity constraints are satisfied, (ii) a strictly positive resource price implies that the sector capacity is fully utilized, and (iii) the allocation is integral and optimal for each AAM vehicle given current prices, without requiring access to individual vehicle utilities. However, a competitive equilibrium with integral allocations may not always exist. We provide sufficient conditions for the existence and computation of a fractional-competitive equilibrium, where allocations can be fractional. Building on these theoretical insights, we propose a distributed, iterative, two-step algorithm that: 1) computes a fractional competitive equilibrium, and 2) derives an integral allocation from this equilibrium. We validate the effectiveness of our approach in allocating trajectories for two emerging urban air mobility services: drone delivery and air taxis., Comment: 31 pages, 7 figures, 3 tables

An amplitude analysis of the $D_{s1}(2460)^+\to D_{s}^{+}\pi^{+}\pi^{-}$ transition is performed simultaneously in $B^{0}\to D^{-}D_{s}^{+}\pi^{+}\pi^{-}$, $B^{+}\to{\bar{D}}^{0} D_{s}^{+}\pi^{+}\pi^{-}$, and $B^{0}\to D^{*-}D_{s}^{+}\pi^{+}\pi^{-}$ decays. The study is based on a data sample of proton-proton collisions recorded with the LHCb detector at centre-of-mass energies of $\sqrt{s}=7,8,$ and $13\,$TeV, corresponding to a total integrated luminosity of $9\,\rm{fb}^{-1}$. A clear double-peak structure is observed in the $m(\pi^{+}\pi^{-})$ spectrum of the $D_{s1}(2460)^{+}\to D_{s}^{+}\pi^{+}\pi^{-}$ decay. The data can be described either with a model including $f_0(500)$, $f_0(980)$ and $f_2(1270)$ resonances, in which the contributions of $f_0(980)$ and $f_2(1270)$ are unexpectedly large, or with a model including $f_0(500)$, a doubly charged open-charm tetraquark state $T_{c\bar{s}}^{++}$ and its isospin partner $T_{c\bar{s}}^{0}$. If the former is considered implausible, the $T_{c\bar{s}}$ states are observed with high significance, and the data are consistent with isospin symmetry. When imposing isospin constraints between the two $T_{c\bar{s}}$ states, their mass and width are determined to be $2327\pm13\pm13\,$MeV and $96\pm16\,^{+170}_{-23}\,$MeV, respectively, where the first uncertainty is statistical and the second is systematic. The mass is slightly below the $DK$ threshold, and a spin-parity of $0^+$ is favoured with high significance., Comment: All figures and tables, along with machine-readable versions and any supplementary material and additional information, are available at https://lbfence.cern.ch/alcm/public/analysis/full-details/3280/ (LHCb public pages)

Cluster-weighted factor analyzers (CWFA) are a versatile class of mixture models designed to estimate the joint distribution of a random vector that includes a response variable along with a set of explanatory variables. They are particularly valuable in situations involving high dimensionality. This paper enhances CWFA models in two notable ways. First, it enables the prediction of multiple response variables while considering their potential interactions. Second, it identifies factors associated with disjoint groups of explanatory variables, thereby improving interpretability. This development leads to the introduction of the multivariate cluster-weighted disjoint factor analyzers (MCWDFA) model. An alternating expectation-conditional maximization algorithm is employed for parameter estimation. The effectiveness of the proposed model is assessed through an extensive simulation study that examines various scenarios. The proposal is applied to crime data from the United States, sourced from the UCI Machine Learning Repository, with the aim of capturing potential latent heterogeneity within communities and identifying groups of socio-economic features that are similarly associated with factors predicting crime rates. Results provide valuable insights into the underlying structures influencing crime rates which may potentially be helpful for effective cluster-specific policymaking and social interventions., Comment: 6 Tables, 7 Figures, 49 pages

Semi-supervised video object segmentation (VOS) has been largely driven by space-time memory (STM) networks, which store past frame features in a spatiotemporal memory to segment the current frame via softmax attention. However, STM networks face memory limitations due to the quadratic complexity of softmax matching, restricting their applicability as video length and resolution increase. To address this, we propose LiVOS, a lightweight memory network that employs linear matching via linear attention, reformulating memory matching into a recurrent process that reduces the quadratic attention matrix to a constant-size, spatiotemporal-agnostic 2D state. To enhance selectivity, we introduce gated linear matching, where a data-dependent gate matrix is multiplied with the state matrix to control what information to retain or discard. Experiments on diverse benchmarks demonstrated the effectiveness of our method. It achieved 64.8 J&F on MOSE and 85.1 J&F on DAVIS, surpassing all non-STM methods and narrowing the gap with STM-based approaches. For longer and higher-resolution videos, it matched STM-based methods with 53% less GPU memory and supports 4096p inference on a 32G consumer-grade GPU--a previously cost-prohibitive capability--opening the door for long and high-resolution video foundation models., Comment: Code&models: https://github.com/uncbiag/LiVOS

Noise-enhanced applications in open quantum walk (QW) have recently seen a surge due to their ability to improve performance. However, verifying the success of open QW is challenging, as mixed-state tomography is a resource-intensive process, and implementing all required measurements is almost impossible due to various physical constraints. To address this challenge, we present a neural-network-based method for reconstructing mixed states with a high fidelity (~97.5%) while costing only 50% of the number of measurements typically required for open discrete-time QW in one dimension. Our method uses a neural density operator that models the system and environment, followed by a generalized natural gradient descent procedure that significantly speeds up the training process. Moreover, we introduce a compact interferometric measurement device, improving the scalability of our photonic QW setup that enables experimental learning of mixed states. Our results demonstrate that highly expressive neural networks can serve as powerful alternatives to traditional state tomography.

Depth estimation under adverse conditions remains a significant challenge. Recently, multi-spectral depth estimation, which integrates both visible light and thermal images, has shown promise in addressing this issue. However, existing algorithms struggle with precise pixel-level feature matching, limiting their ability to fully exploit geometric constraints across different spectra. To address this, we propose a novel framework incorporating stereo depth estimation to enforce accurate geometric constraints. In particular, we treat the visible light and thermal images as a stereo pair and utilize a Cross-modal Feature Matching (CFM) Module to construct a cost volume for pixel-level matching. To mitigate the effects of poor lighting on stereo matching, we introduce Degradation Masking, which leverages robust monocular thermal depth estimation in degraded regions. Our method achieves state-of-the-art (SOTA) performance on the Multi-Spectral Stereo (MS2) dataset, with qualitative evaluations demonstrating high-quality depth maps under varying lighting conditions.

Helical Kelvin waves were conjectured to exist for the 3D Euler equations in Lucas and Dritschel \cite{LucDri} (as well as in \cite{Chu}) by studying dispersion relation for infinitesimal linear perturbations of a circular helically symmetric vortex patch. This paper aims to rigorously establish the existence of these $m$-fold symmetric helical Kelvin waves, in both simply and doubly connected cases, for the 3D Euler equations. The construction is based on linearization of contour dynamics equations and bifurcation theory. Our results rigorously verify the prediction in aforementioned papers and extend $m$-waves of Kelvin from the 2D Euler equations to the 3D helically symmetric Euler equations.

The attached-eddy model (AEM) predicts mean velocity and streamwise velocity variance profiles that follow a logarithmic shape in the overlap region of high Reynolds number wall-bounded turbulent flows. Moreover, the AEM coefficients are presumed to attain asymptotically constant values at very high Reynolds numbers. Here, the logarithmic behaviour of the AEM predictions in the near-neutral atmospheric surface layer is examined using sonic anemometer measurements from a 62-m meteorological tower located in the Eastern Snake River Plain, Idaho, US. Utilizing an extensive 210-day dataset, the inertial sublayer (ISL) is first identified by analyzing the measured momentum flux and mean velocity profile. The logarithmic behaviour of the streamwise velocity variance and the associated `-1' scaling of the streamwise velocity energy spectra are then investigated. The findings indicate that the Townsend-Perry coefficient ($A_1$) is influenced by mild non-stationarity that manifests itself as a Reynolds number dependence. After excluding non-stationary runs and requiring a Reynolds number higher than $4 \times 10^7$, the inferred $A_1$ converges to values ranging between 1 and 1.25, consistent with laboratory experiments. Moreover, the independence of the normalized vertical velocity variance from the wall-normal distance in the ISL is further checked and the constant coefficient value agrees with reported laboratory experiments at very high Reynolds numbers as well as many surface layer experiments. Furthermore, nine benchmark cases selected through a restrictive quality control reveal a closer relationship between the `-1' scaling in the streamwise velocity energy spectrum and the logarithmic behaviour of streamwise velocity variance at higher Reynolds numbers, though no direct equivalence between them is observed.

Learning-task oriented semantic communication is pivotal in optimizing transmission efficiency by extracting and conveying essential semantics tailored to specific tasks, such as image reconstruction and classification. Nevertheless, the challenge of eavesdropping poses a formidable threat to semantic privacy due to the open nature of wireless communications. In this paper, intelligent reflective surface (IRS)-enhanced secure semantic communication (IRS-SSC) is proposed to guarantee the physical layer security from a task-oriented semantic perspective. Specifically, a multi-layer codebook is exploited to discretize continuous semantic features and describe semantics with different numbers of bits, thereby meeting the need for hierarchical semantic representation and further enhancing the transmission efficiency. Novel semantic security metrics, i.e., secure semantic rate (S-SR) and secure semantic spectrum efficiency (S-SSE), are defined to map the task-oriented security requirements at the application layer into the physical layer. To achieve artificial intelligence (AI)-native secure communication, we propose a noise disturbance enhanced hybrid deep reinforcement learning (NdeHDRL)-based resource allocation scheme. This scheme dynamically maximizes the S-SSE by jointly optimizing the bits for semantic representations, reflective coefficients of the IRS, and the subchannel assignment. Moreover, we propose a novel semantic context awared state space (SCA-SS) to fusion the high-dimensional semantic space and the observable system state space, which enables the agent to perceive semantic context and solves the dimensional catastrophe problem. Simulation results demonstrate the efficiency of our proposed schemes in both enhancing the security performance and the S-SSE compared to several benchmark schemes.

Vision-language pre-training (VLP) models excel at interpreting both images and text but remain vulnerable to multimodal adversarial examples (AEs). Advancing the generation of transferable AEs, which succeed across unseen models, is key to developing more robust and practical VLP models. Previous approaches augment image-text pairs to enhance diversity within the adversarial example generation process, aiming to improve transferability by expanding the contrast space of image-text features. However, these methods focus solely on diversity around the current AEs, yielding limited gains in transferability. To address this issue, we propose to increase the diversity of AEs by leveraging the intersection regions along the adversarial trajectory during optimization. Specifically, we propose sampling from adversarial evolution triangles composed of clean, historical, and current adversarial examples to enhance adversarial diversity. We provide a theoretical analysis to demonstrate the effectiveness of the proposed adversarial evolution triangle. Moreover, we find that redundant inactive dimensions can dominate similarity calculations, distorting feature matching and making AEs model-dependent with reduced transferability. Hence, we propose to generate AEs in the semantic image-text feature contrast space, which can project the original feature space into a semantic corpus subspace. The proposed semantic-aligned subspace can reduce the image feature redundancy, thereby improving adversarial transferability. Extensive experiments across different datasets and models demonstrate that the proposed method can effectively improve adversarial transferability and outperform state-of-the-art adversarial attack methods. The code is released at https://github.com/jiaxiaojunQAQ/SA-AET.

The topological properties observed in iron-based superconductors extend our understanding of vortex Majorana quasiparticle excitations in unexpected ways. Vortex Majorana physics has been extensively studied within the context of the topologically protected surface Dirac state. By employing an in-situ strain device, we demonstrate that uniaxial strain can generate Majorana zero modes out of the topological Dirac semimetal bulk state in LiFeAs. Uniaxial strain along [100] direction is found to enhance the band renormalization of LiFeAs, effectively reducing the energy separation between the Fermi level and the topological Dirac semimetal state, and breaking C4 symmetry. Using scanning tunneling microscopy, we observe the evolution of vortex bound states in the topological Dirac semimetal state region, accompanied by the emergence of Majorana zero modes and vortex bound states contributed by the bulk band. Our work provides a controllable method for experimentally engineering Majorana physics in iron-based superconductors, and offers valuable insights into the topological Dirac semimetal state with intrinsic s-wave superconductivity., Comment: 17 pages, 4 figures

In-context learning (ICL) and Retrieval-Augmented Generation (RAG) have gained attention for their ability to enhance LLMs' reasoning by incorporating external knowledge but suffer from limited contextual window size, leading to insufficient information injection. To this end, we propose a novel framework, RuAG, to automatically distill large volumes of offline data into interpretable first-order logic rules, which are injected into LLMs to boost their reasoning capabilities. Our method begins by formulating the search process relying on LLMs' commonsense, where LLMs automatically define head and body predicates. Then, RuAG applies Monte Carlo Tree Search (MCTS) to address the combinational searching space and efficiently discover logic rules from data. The resulting logic rules are translated into natural language, allowing targeted knowledge injection and seamless integration into LLM prompts for LLM's downstream task reasoning. We evaluate our framework on public and private industrial tasks, including natural language processing, time-series, decision-making, and industrial tasks, demonstrating its effectiveness in enhancing LLM's capability over diverse tasks.

Gottesman-Kitaev-Preskill (GKP) encoding holds promise for continuous-variable fault-tolerant quantum computing. While an ideal GKP encoding is abstract and impractical due to its nonphysical nature, approximate versions provide viable alternatives. Conventional approximate GKP codewords are superpositions of multiple {large-amplitude} squeezed coherent states. This feature ensures correctability against single-photon loss and dephasing {at short times}, but also increases the difficulty of preparing the codewords. To minimize this trade-off, we utilize a neural network to generate optimal approximate GKP states, allowing effective error correction with just a few squeezed coherent states. We find that such optimized GKP codes outperform the best conventional ones, requiring fewer squeezed coherent states, while maintaining simple and generalized stabilizer operators. Specifically, the former outperform the latter with just \textit{one third} of the number of squeezed coherent states at a squeezing level of 9.55 dB. This optimization drastically decreases the complexity of codewords while improving error correctability.

The pervasive use of the Internet and social media introduces significant challenges to automated sentiment analysis, particularly for sarcastic expressions in user-generated content. Sarcasm conveys negative emotions through ostensibly positive or exaggerated language, complicating its detection within natural language processing tasks. To address this, we propose an innovative sarcasm detection model integrating Convolutional Neural Networks (CNN), Gated Recurrent Units (GRU), Long Short-Term Memory (LSTM), and Multi-Head Attention mechanisms. The CNN component captures local n-gram features, while GRU and LSTM layers model sequential dependencies and contextual information. Multi-Head Attention enhances the model's focus on relevant parts of the input, improving interpretability. Experiments on two sarcasm detection datasets, Headlines and Riloff, demonstrate that the model achieves an accuracy of 81.20% and an F1 score of 80.77% on Headlines, and an accuracy of 79.72% with an F1 score of 61.39% on Riloff, outperforming traditional models. These results validate the effectiveness of our hybrid approach for sarcasm detection in social media texts.

The Water Cherenkov Detector Array (WCDA) is one of the components of Large High Altitude Air Shower Observatory (LHAASO) and can monitor any sources over two-thirds of the sky for up to 7 hours per day with >98\% duty cycle. In this work, we report the detection of two outbursts of the Fanaroff-Riley I radio galaxy NGC 1275 that were detected by LHAASO-WCDA between November 2022 and January 2023 with statistical significance of 5.2~$\sigma$ and 8.3~$\sigma$. The observed spectral energy distribution in the range from 500 GeV to 3 TeV is fitted by a power-law with a best-fit spectral index of $\alpha=-3.37\pm0.52$ and $-3.35\pm0.29$, respectively. The outburst flux above 0.5~TeV was ($4.55\pm 4.21)\times~10^{-11}~\rm cm^{-2}~s^{-1}$ and ($3.45\pm 1.78)\times~10^{-11}~\rm cm^{-2}~s^{-1}$, corresponding to 60\%, 45\% of Crab Nebula flux. Variation analysis reveals the variability time-scale of days at the TeV energy band. A simple test by one-zone synchrotron self-Compton model reproduces the data in the gamma-ray band well., Comment: 11 pages, 8 figures, 3 tables

Miniaturized spectrometers for Raman spectroscopy have the potential to open up a new chapter in sensing. Raman spectroscopy is essential for material characterization and biomedical diagnostics, however, its weak signal and the need for sub-nanometer resolution pose challenges. Conventional spectrometers, with footprints proportional to optical throughput and resolution, are difficult to integrate into compact devices such as wearables. Waveguide-based Fourier Transform Spectrometers (FTS) enable compact spectrometers, and multi-aperture designs can achieve high throughput for applications such as Raman spectroscopy, however, experimental research in this domain remains limited. In this work, we present a multi-aperture SiN waveguide-based FTS overcoming these limitations and enabling Raman spectroscopy of isopropyl alcohol, glucose, Paracetamol, and Ibuprofen with enhanced throughput. Our spectrometer chip, fabricated on a 200 mm SiN wafer, with 160 edge-coupled waveguide apertures connected to an array of ultra-compact interferometers and a small footprint of just 1.6 mm x 4.8 mm, achieves a spectral range of 40 nm and a resolution of 0.5 nm. Experimental results demonstrate that least absolute shrinkage and selection operator (LASSO) regression significantly enhances Raman spectrum reconstruction. Our work on waveguide-based spectrometry paves the way for integrating accurate and compact Raman sensors into consumer electronics and space exploration instruments., Comment: 13 pages, 5 figures, Corresponding Authors: Sarp Kerman (sarp.kerman@photonicview.com), Chang Chen (changchen@sjtu.edu.cn)

Binary code search plays a crucial role in applications like software reuse detection. Currently, existing models are typically based on either internal code semantics or a combination of function call graphs (CG) and internal code semantics. However, these models have limitations. Internal code semantic models only consider the semantics within the function, ignoring the inter-function semantics, making it difficult to handle situations such as function inlining. The combination of CG and internal code semantics is insufficient for addressing complex real-world scenarios. To address these limitations, we propose BinEnhance, a novel framework designed to leverage the inter-function semantics to enhance the expression of internal code semantics for binary code search. Specifically, BinEnhance constructs an External Environment Semantic Graph (EESG), which establishes a stable and analogous external environment for homologous functions by using different inter-function semantic relations (e.g., call, location, data-co-use). After the construction of EESG, we utilize the embeddings generated by existing internal code semantic models to initialize nodes of EESG. Finally, we design a Semantic Enhancement Model (SEM) that uses Relational Graph Convolutional Networks (RGCNs) and a residual block to learn valuable external semantics on the EESG for generating the enhanced semantics embedding. In addition, BinEnhance utilizes data feature similarity to refine the cosine similarity of semantic embeddings. We conduct experiments under six different tasks (e.g., under function inlining scenario) and the results illustrate the performance and robustness of BinEnhance. The application of BinEnhance to HermesSim, Asm2vec, TREX, Gemini, and Asteria on two public datasets results in an improvement of Mean Average Precision (MAP) from 53.6% to 69.7%. Moreover, the efficiency increases fourfold., Comment: Accepted by Network and Distributed System Security (NDSS) Symposium 2025 fall cycle

We study the optimal allocation of prizes in rank-order tournaments with loss averse agents. Prize sharing becomes increasingly optimal with loss aversion because more equitable prizes reduce the marginal psychological cost of anticipated losses. Furthermore, loss aversion can boost effort if prizes are sufficiently equitable, but otherwise effort declines with loss aversion. Overall, these results give credence to more equitable allocations of competitive rewards. A win-win scenario is where optimal prizes are equitable even under loss neutrality, in which case the principal benefits from agents' loss aversion.

Quasi-phase matching (QPM) is a technique extensively utilized in nonlinear optics for enhancing the efficiency and stability of frequency conversion processes. However, the conventional QPM relies on periodically poled ferroelectric crystals, which are limited in availability. The 3R phase of molybdenum disulfide (3R-MoS2), a transition metal dichalcogenide (TMDc) with the broken inversion symmetry, stands out as a promising candidate for QPM, enabling efficient nonlinear process. Here, we experimentally demonstrate the QPM at nanoscale, utilizing van der Waals stacking of 3R-MoS2 layers with specific orientation to realize second harmonic generation (SHG) enhancement beyond the non QPM limit. We have also demonstrated enhanced spontaneous parametric down-conversion (SPDC) via QPM of 3R-MoS2 homo-structure, enabling more efficient generation of entangled photon pairs. The tunable capacity of 3R-MoS2 van der Waals stacking provides a platform for tuning phase-matching condition. This technique opens interesting possibilities for potential applications in nonlinear process and quantum technology.

The rise of large language models (LLMs) has revolutionized user interactions with knowledge-based systems, enabling chatbots to synthesize vast amounts of information and assist with complex, exploratory tasks. However, LLM-based chatbots often struggle to provide personalized support, particularly when users start with vague queries or lack sufficient contextual information. This paper introduces the Collaborative Assistant for Personalized Exploration (CARE), a system designed to enhance personalization in exploratory tasks by combining a multi-agent LLM framework with a structured user interface. CARE's interface consists of a Chat Panel, Solution Panel, and Needs Panel, enabling iterative query refinement and dynamic solution generation. The multi-agent framework collaborates to identify both explicit and implicit user needs, delivering tailored, actionable solutions. In a within-subject user study with 22 participants, CARE was consistently preferred over a baseline LLM chatbot, with users praising its ability to reduce cognitive load, inspire creativity, and provide more tailored solutions. Our findings highlight CARE's potential to transform LLM-based systems from passive information retrievers to proactive partners in personalized problem-solving and exploration.

Proteins, essential to biological systems, perform functions intricately linked to their three-dimensional structures. Understanding the relationship between protein structures and their amino acid sequences remains a core challenge in protein modeling. While traditional protein foundation models benefit from pre-training on vast unlabeled datasets, they often struggle to capture critical co-evolutionary information, which evolutionary-based methods excel at. In this study, we introduce a novel pre-training strategy for protein foundation models that emphasizes the interactions among amino acid residues to enhance the extraction of both short-range and long-range co-evolutionary features from sequence data. Trained on a large-scale protein sequence dataset, our model demonstrates superior generalization ability, outperforming established baselines of similar size, including the ESM model, across diverse downstream tasks. Experimental results confirm the model's effectiveness in integrating co-evolutionary information, marking a significant step forward in protein sequence-based modeling.

Despite significant progress in visual decoding with fMRI data, its high cost and low temporal resolution limit widespread applicability. To address these challenges, we introduce RealMind, a novel EEG-based visual decoding framework that leverages multi-modal models to efficiently interpret semantic information. By integrating semantic and geometric consistency learning, RealMind enhances feature alignment, leading to improved decoding performance. Our framework achieves a 56.73\% Top-5 accuracy in a 200-way retrieval task and a 26.59\% BLEU-1 score in a 200-way visual captioning task, representing the first successful attempt at zero-shot visual captioning using EEG data. RealMind provides a robust, adaptable, and cost-effective alternative to fMRI-based methods, offering scalable solutions for EEG-based visual decoding in practical applications.

Large language models (LLMs) show impressive performance in solving complex languagetasks. However, its large number of parameterspresent significant challenges for the deployment and application of the model on edge devices. Compressing large language models to low bits can enable them to run on resource-constrained devices, often leading to performance degradation. To address this problem, we propose gradient-aware weight quantization (GWQ), the first quantization approach for low-bit weight quantization that leverages gradients to localize outliers, requiring only a minimal amount of calibration data for outlier detection. GWQ retains the weights corresponding to the top 1% outliers preferentially at FP16 precision, while the remaining non-outlier weights are stored in a low-bit format. GWQ found experimentally that utilizing the sensitive weights in the gradient localization model is more scientific compared to utilizing the sensitive weights in the Hessian matrix localization model. Compared to current quantization methods, GWQ can be applied to multiple language models and achieves lower PPL on the WikiText2 and C4 dataset. In the zero-shot task, GWQ quantized models have higher accuracy compared to other quantization methods.GWQ is also suitable for multimodal model quantization, and the quantized Qwen-VL family model is more accurate than other methods. zero-shot target detection task dataset RefCOCO outperforms the current stat-of-the-arts method SPQR. GWQ achieves 1.2x inference speedup in comparison to the original model, and effectively reduces the inference memory.

Quantum architecture search (QAS) represents a fundamental challenge in quantum machine learning. Unlike previous methods that treat it as a static search process, from a perspective on QAS as an item retrieval task in vast search space, we decompose the search process into dynamic alternating phases of coarse and fine-grained knowledge learning. We propose quantum untrained-explored synergistic trained architecture (QUEST-A),a framework through coarse-grained untrained filtering for rapid search space reduction and fine-grained trained focusing for precise space refinement in progressive QAS. QUEST-A develops an evolutionary mechanism with knowledge accumulation and reuse to enhance multi-level knowledge transfer in architecture searching. Experiments demonstrate QUEST-A's superiority over existing methods: enhancing model expressivity in signal representation, maintaining high performance across varying complexities in image classification, and achieving order-of-magnitude precision improvements in variational quantum eigensolver tasks, providing a transferable methodology for QAS.

Virtual Network Embedding (VNE) is a challenging combinatorial optimization problem that refers to resource allocation associated with hard and multifaceted constraints in network function virtualization (NFV). Existing works for VNE struggle to handle such complex constraints, leading to compromised system performance and stability. In this paper, we propose a \textbf{CON}straint-\textbf{A}ware \textbf{L}earning framework for VNE, named \textbf{CONAL}, to achieve efficient constraint management. Concretely, we formulate the VNE problem as a constrained Markov decision process with violation tolerance. This modeling approach aims to improve both resource utilization and solution feasibility by precisely evaluating solution quality and the degree of constraint violation. We also propose a reachability-guided optimization with an adaptive reachability budget method that dynamically assigns budget values. This method achieves persistent zero violation to guarantee the feasibility of VNE solutions and more stable policy optimization by handling instances without any feasible solution. Furthermore, we propose a constraint-aware graph representation method to efficiently learn cross-graph relations and constrained path connectivity in VNE. Finally, extensive experimental results demonstrate the superiority of our proposed method over state-of-the-art baselines. Our code is available at https://github.com/GeminiLight/conal-vne.

Identifying mutations of SARS-CoV-2 strains associated with their phenotypic changes is critical for pandemic prediction and prevention. We compared an explainable convolutional neural network (CNN) and the traditional genome-wide association study (GWAS) on the mutations associated with WHO labels of SARS-CoV-2, a proxy for virulence phenotypes. We trained a CNN classification model that can predict genomic sequences into Variants of Concern (VOCs), and then applied Shapley Additive explanations (SHAP) model to identify mutations that are important for the correct predictions. For comparison, we performed traditional GWAS to identify mutations associated with VOCs. Comparison of the two approaches shows that the explainable neural network approach can more effectively reveal known nucleotide substitutions associated with VOCs, such as those in the spike gene regions. Our results suggest that explainable neural networks for genomic sequences offer a promising alternative to the traditional genome wide analysis approaches.

We present an novel framework for efficiently and effectively extending the powerful continuous diffusion processes to discrete modeling. Previous approaches have suffered from the discrepancy between discrete data and continuous modeling. Our study reveals that the absence of guidance from discrete boundaries in learning probability contours is one of the main reasons. To address this issue, we propose a two-step forward process that first estimates the boundary as a prior distribution and then rescales the forward trajectory to construct a boundary conditional diffusion model. The reverse process is proportionally adjusted to guarantee that the learned contours yield more precise discrete data. Experimental results indicate that our approach achieves strong performance in both language modeling and discrete image generation tasks. In language modeling, our approach surpasses previous state-of-the-art continuous diffusion language models in three translation tasks and a summarization task, while also demonstrating competitive performance compared to auto-regressive transformers. Moreover, our method achieves comparable results to continuous diffusion models when using discrete ordinal pixels and establishes a new state-of-the-art for categorical image generation on the Cifar-10 dataset., Comment: NeuraIPS 2024 poster

We present AutoGLM, a new series in the ChatGLM family, designed to serve as foundation agents for autonomous control of digital devices through Graphical User Interfaces (GUIs). While foundation models excel at acquiring human knowledge, they often struggle with decision-making in dynamic real-world environments, limiting their progress toward artificial general intelligence. This limitation underscores the importance of developing foundation agents capable of learning through autonomous environmental interactions by reinforcing existing models. Focusing on Web Browser and Phone as representative GUI scenarios, we have developed AutoGLM as a practical foundation agent system for real-world GUI interactions. Our approach integrates a comprehensive suite of techniques and infrastructures to create deployable agent systems suitable for user delivery. Through this development, we have derived two key insights: First, the design of an appropriate "intermediate interface" for GUI control is crucial, enabling the separation of planning and grounding behaviors, which require distinct optimization for flexibility and accuracy respectively. Second, we have developed a novel progressive training framework that enables self-evolving online curriculum reinforcement learning for AutoGLM. Our evaluations demonstrate AutoGLM's effectiveness across multiple domains. For web browsing, AutoGLM achieves a 55.2% success rate on VAB-WebArena-Lite (improving to 59.1% with a second attempt) and 96.2% on OpenTable evaluation tasks. In Android device control, AutoGLM attains a 36.2% success rate on AndroidLab (VAB-Mobile) and 89.7% on common tasks in popular Chinese APPs.

In the context of widespread global information sharing, information security and privacy protection have become focal points. Steganographic systems enhance information security by embedding confidential information into public carriers; however, existing generative text steganography methods face challenges in handling the long-tail distribution of candidate word pools, which impacts the imperceptibility of steganographic information. This paper proposes a quality control theory for steganographic text generation based on information entropy constraints, exploring the relationship between the imperceptibility of steganographic texts and information entropy. By controlling the information entropy of the candidate word pool within a specific range, we optimize the imperceptibility of the steganographic text. We establish upper and lower bounds for information entropy and introduce an adaptive truncation method to balance semantic coherence and lexical diversity. Experimental results demonstrate that reasonably controlling the candidate pool size and information entropy thresholds significantly enhances the quality and detection resistance of steganographic texts, showcasing broad application potential in the field of natural language processing.

Social media platforms have evolved rapidly in modernity without strong regulation. One clear obstacle faced by current users is that of toxicity. Toxicity on social media manifests through a number of forms, including harassment, negativity, misinformation or other means of divisiveness. In this paper, we characterize literature surrounding toxicity, formalize a definition of toxicity, propose a novel cycle of internet extremism, list current approaches to toxicity detection, outline future directions to minimize toxicity in future social media endeavors, and identify current gaps in research space. We present a novel perspective of the negative impacts of social media platforms and fill a gap in literature to help improve the future of social media platforms., Comment: 12 pages, 2 figures, 2 tables, Cycle of Internet Extremism

Although large language models (LLMs) have demonstrated their strong intelligence ability, the high demand for computation and storage hinders their practical application. To this end, many model compression techniques are proposed to increase the efficiency of LLMs. However, current researches only validate their methods on limited models, datasets, metrics, etc, and still lack a comprehensive evaluation under more general scenarios. So it is still a question of which model compression approach we should use under a specific case. To mitigate this gap, we present the Large Language Model Compression Benchmark (LLMCBench), a rigorously designed benchmark with an in-depth analysis for LLM compression algorithms. We first analyze the actual model production requirements and carefully design evaluation tracks and metrics. Then, we conduct extensive experiments and comparison using multiple mainstream LLM compression approaches. Finally, we perform an in-depth analysis based on the evaluation and provide useful insight for LLM compression design. We hope our LLMCBench can contribute insightful suggestions for LLM compression algorithm design and serve as a foundation for future research. Our code is available at https://github.com/AboveParadise/LLMCBench., Comment: Accepted by NeurIPS 2024 Datasets and Benchmarks Track

Measurements of $CP$ observables and the CKM angle $\gamma$ are performed in $B^{\pm} \to D K^*(892)^{\pm}$ decays, where $D$ represents a superposition of $D^0$ and $\overline{D}{}^0$ states, using the LHCb dataset collected during Run 1 (2011-2012) and Run 2 (2015-2018). A comprehensive study of this channel is presented with the $D$ meson reconstructed in two-body final states $K^{\pm}\pi^{\mp}$, $K^+K^-$ and $\pi^+\pi^-$; four-body final states $K^{\pm}\pi^{\mp}\pi^{\pm}\pi^{\mp}$ and $\pi^+\pi^-\pi^+\pi^-$; and three-body final states $K^0_{S} \pi^+\pi^-$ and $K^0_{S} K^+ K^-$. This analysis includes the first observation of the suppressed $B^{\pm} \to [\pi^+K^-]_D K^{*\pm}$ and $B^{\pm} \to [\pi^+K^-\pi^+\pi^-]_D K^{*\pm}$ decays. The combined result gives $\gamma=(63\pm 13)^\circ$., Comment: All figures and tables, along with machine-readable versions and any supplementary material and additional information, are available at https://lbfence.cern.ch/alcm/public/analysis/full-details/3180/ (LHCb public pages)

Large language model (LLM) safety is a critical issue, with numerous studies employing red team testing to enhance model security. Among these, jailbreak methods explore potential vulnerabilities by crafting malicious prompts that induce model outputs contrary to safety alignments. Existing black-box jailbreak methods often rely on model feedback, repeatedly submitting queries with detectable malicious instructions during the attack search process. Although these approaches are effective, the attacks may be intercepted by content moderators during the search process. We propose an improved transfer attack method that guides malicious prompt construction by locally training a mirror model of the target black-box model through benign data distillation. This method offers enhanced stealth, as it does not involve submitting identifiable malicious instructions to the target model during the search phase. Our approach achieved a maximum attack success rate of 92%, or a balanced value of 80% with an average of 1.5 detectable jailbreak queries per sample against GPT-3.5 Turbo on a subset of AdvBench. These results underscore the need for more robust defense mechanisms.

We first study $f$-biharmonicity of totally umbilical hypersurfaces in a generic Riemannian manifold and then prove that any totally umbilical proper $f$-biharmonic hypersurface in a nonpositively curved manifold has to be noncompact. We also explore $f$-biharmonicity of totally umbilical hyperplanes in a conformally flat space. Secondly, we construct $f$-biharmonic surfaces and biharmonic conformal immersions of the associated surfaces into a conformall flat 3-space and also give a complete classification of $f$-biharmonic surfaces of nonzero constant mean curvature in 3-space forms. Finally, we especially investigate $f$-biharmonicity of hypersurfaces into a conformally flat space of negative sectional curvature. We show that any totally umbilical $f$-biharmonic surface of a 3-manifold with nonpositve sectional curvature is minimal whilst there are proper $f$-biharmonic $m$-dimensional submanifolds with $m\geq3$ and $m\neq4$ into nonpositvely curved manifolds., Comment: 20

Recently, rapid advancements in Multi-Modal In-Context Learning (MM-ICL) have achieved notable success, which is capable of achieving superior performance across various tasks without requiring additional parameter tuning. However, the underlying rules for the effectiveness of MM-ICL remain under-explored. To fill this gap, this work aims to investigate the research question: "What factors affect the performance of MM-ICL?'' To this end, we investigate extensive experiments on the three core steps of MM-ICL including demonstration retrieval, demonstration ordering, and prompt construction using 6 vision large language models and 20 strategies. Our findings highlight (1) the necessity of a multi-modal retriever for demonstration retrieval, (2) the importance of intra-demonstration ordering over inter-demonstration ordering, and (3) the enhancement of task comprehension through introductory instructions in prompts. We hope this study can serve as a foundational guide for optimizing MM-ICL strategies in future research., Comment: Accepted at NeurIPS 2024

Neural Control Barrier Functions (NCBFs) have shown significant promise in enforcing safety constraints on nonlinear autonomous systems. State-of-the-art exact approaches to verifying safety of NCBF-based controllers exploit the piecewise-linear structure of ReLU neural networks, however, such approaches still rely on enumerating all of the activation regions of the network near the safety boundary, thus incurring high computation cost. In this paper, we propose a framework for Synthesis with Efficient Exact Verification (SEEV). Our framework consists of two components, namely (i) an NCBF synthesis algorithm that introduces a novel regularizer to reduce the number of activation regions at the safety boundary, and (ii) a verification algorithm that exploits tight over-approximations of the safety conditions to reduce the cost of verifying each piecewise-linear segment. Our simulations show that SEEV significantly improves verification efficiency while maintaining the CBF quality across various benchmark systems and neural network structures. Our code is available at https://github.com/HongchaoZhang-HZ/SEEV.

Frequency information (e.g., Discrete Wavelet Transform and Fast Fourier Transform) has been widely applied to solve the issue of Low-Light Image Enhancement (LLIE). However, existing frequency-based models primarily operate in the simple wavelet or Fourier space of images, which lacks utilization of valid global and local information in each space. We found that wavelet frequency information is more sensitive to global brightness due to its low-frequency component while Fourier frequency information is more sensitive to local details due to its phase component. In order to achieve superior preliminary brightness enhancement by optimally integrating spatial channel information with low-frequency components in the wavelet transform, we introduce channel-wise Mamba, which compensates for the long-range dependencies of CNNs and has lower complexity compared to Diffusion and Transformer models. So in this work, we propose a novel Wavelet-based Mamba with Fourier Adjustment model called WalMaFa, consisting of a Wavelet-based Mamba Block (WMB) and a Fast Fourier Adjustment Block (FFAB). We employ an Encoder-Latent-Decoder structure to accomplish the end-to-end transformation. Specifically, WMB is adopted in the Encoder and Decoder to enhance global brightness while FFAB is adopted in the Latent to fine-tune local texture details and alleviate ambiguity. Extensive experiments demonstrate that our proposed WalMaFa achieves state-of-the-art performance with fewer computational resources and faster speed. Code is now available at: https://github.com/mcpaulgeorge/WalMaFa., Comment: 18 pages, 8 figures, ACCV2024

Coronary artery disease poses a significant global health challenge, often necessitating percutaneous coronary intervention (PCI) with stent implantation. Assessing stent apposition holds pivotal importance in averting and identifying PCI complications that lead to in-stent restenosis. Here we proposed a novel three-dimensional (3D) distance-color-coded assessment (DccA)for PCI stent apposition via deep-learning-based 3D multi-object segmentation in intravascular optical coherence tomography (IV-OCT). Our proposed 3D DccA accurately segments 3D vessel lumens and stents in IV-OCT images, using a spatial matching network and dual-layer training with style transfer. It quantifies and maps stent-lumen distances into a 3D color space, facilitating 3D visual assessment of PCI stent apposition. Achieving over 95% segmentation precision, our proposed DccA enhances clinical evaluation of PCI stent deployment and supports personalized treatment planning.

Understanding the binding dynamics of liquid molecules is of fundamental importance in physical and life sciences. However, nanoscale fast dynamics pose great challenges for experimental characterization. Conventionally, the binding dynamics have been assumed to be memoryless. Here, we integrate large scale computer simulation, scaling theory, and real-time single particle tracking microscopy with high spatiotemporal precision to unveil a universal memory effect in the binding dynamics of liquid molecules. This binding memory can be quantified by a binding time autocorrelation function, whose power-law decay depends not only on the binding affinity, but also on the topological and materials properties of the surrounding environment. Context-dependent biomolecular binding memory is likely exploited by biological systems to regulate biochemical reactions and biophysical processes. Deciphering this binding memory offers a novel strategy to probe complex biological systems and advanced soft materials.

In this paper, we present an event-triggered distributed optimization approach including a distributed controller to solve a class of distributed time-varying optimization problems (DTOP). The proposed approach is developed within a distributed neurodynamic (DND) framework that not only optimizes the global objective function in real-time, but also ensures that the states of the agents converge to consensus. This work stands out from existing methods in two key aspects. First, the distributed controller enables the agents to communicate only at designed instants rather than continuously by an event-triggered scheme, which reduces the energy required for agent communication. Second, by incorporating an integral mode technique, the event-triggered distributed controller avoids computing the inverse of the Hessian of each local objective function, thereby reducing computational costs. Finally, an example of battery charging problem is provided to demonstrate the effectiveness of the proposed event-triggered distributed optimization approach.

The spontaneous conversion of muonium to antimuonium is one of the interesting charged lepton flavor violation phenomena, offering a sensitive probe of potential new physics and serving as a tool to constrain the parameter space beyond the Standard Model. Utilizing a high-intensity muon beam, a Michel electron magnetic spectrometer and a positron transport solenoid together with a positron detection system, MACE aims to discover or constrain this rare process at the conversion probability beyond the level of $10^{-13}$. This report provides an overview of the theoretical framework and detailed experimental design in the search for the muonium-to-antimuonium conversion., Comment: 115 pages, 59 figures

In this paper, we propose a novel framework that leverages large language models (LLMs) for predicting missing values in time-varying graph signals by exploiting spatial and temporal smoothness. We leverage the power of LLM to achieve a message-passing scheme. For each missing node, its neighbors and previous estimates are fed into and processed by LLM to infer the missing observations. Tested on the task of the online prediction of wind-speed graph signals, our model outperforms online graph filtering algorithms in terms of accuracy, demonstrating the potential of LLMs in effectively addressing partially observed signals in graphs.

Despite significant advances in deepfake detection, handling varying image quality, especially due to different compressions on online social networks (OSNs), remains challenging. Current methods succeed by leveraging correlations between paired images, whether raw or compressed. However, in open-world scenarios, paired data is scarce, with compressed images readily available but corresponding raw versions difficult to obtain. This imbalance, where unpaired data vastly outnumbers paired data, often leads to reduced detection performance, as existing methods struggle without corresponding raw images. To overcome this issue, we propose a novel approach named the open-world deepfake detection network (ODDN), which comprises two core modules: open-world data aggregation (ODA) and compression-discard gradient correction (CGC). ODA effectively aggregates correlations between compressed and raw samples through both fine-grained and coarse-grained analyses for paired and unpaired data, respectively. CGC incorporates a compression-discard gradient correction to further enhance performance across diverse compression methods in OSN. This technique optimizes the training gradient to ensure the model remains insensitive to compression variations. Extensive experiments conducted on 17 popular deepfake datasets demonstrate the superiority of the ODDN over SOTA baselines., Comment: 9 pages, 4 figures

The development of large language models (LLMs) has significantly expanded model sizes, resulting in substantial GPU memory requirements during inference. The key and value storage of the attention map in the KV (key-value) cache accounts for more than 80\% of this memory consumption. Nowadays, most existing KV cache compression methods focus on intra-layer compression within a single Transformer layer but few works consider layer-wise compression. In this paper, we propose a plug-and-play method called \textit{KVSharer}, which shares the KV cache between layers to achieve layer-wise compression. Rather than intuitively sharing based on higher similarity, we discover a counterintuitive phenomenon: sharing dissimilar KV caches better preserves the model performance. Experiments show that \textit{KVSharer} can reduce KV cache computation by 30\%, thereby lowering memory consumption without significantly impacting model performance and it can also achieve at least 1.3 times generation acceleration. Additionally, we verify that \textit{KVSharer} is compatible with existing intra-layer KV cache compression methods, and combining both can further save memory., Comment: Under Review by ICLR2025

Current multimodal recommendation models have extensively explored the effective utilization of multimodal information; however, their reliance on ID embeddings remains a performance bottleneck. Even with the assistance of multimodal information, optimizing ID embeddings remains challenging for ID-based Multimodal Recommender when interaction data is sparse. Furthermore, the unique nature of item-specific ID embeddings hinders the information exchange among related items and the spatial requirement of ID embeddings increases with the scale of item. Based on these limitations, we propose an ID-free MultimOdal TOken Representation scheme named MOTOR that represents each item using learnable multimodal tokens and connects them through shared tokens. Specifically, we first employ product quantization to discretize each item's multimodal features (e.g., images, text) into discrete token IDs. We then interpret the token embeddings corresponding to these token IDs as implicit item features, introducing a new Token Cross Network to capture the implicit interaction patterns among these tokens. The resulting representations can replace the original ID embeddings and transform the original ID-based multimodal recommender into ID-free system, without introducing any additional loss design. MOTOR reduces the overall space requirements of these models, facilitating information interaction among related items, while also significantly enhancing the model's recommendation capability. Extensive experiments on nine mainstream models demonstrate the significant performance improvement achieved by MOTOR, highlighting its effectiveness in enhancing multimodal recommendation systems., Comment: 11 pages,6 figures

High-level synthesis (HLS) is a widely used tool in designing Field Programmable Gate Array (FPGA). HLS enables FPGA design with software programming languages by compiling the source code into an FPGA circuit. The source code includes a program (called ``kernel'') and several pragmas that instruct hardware synthesis, such as parallelization, pipeline, etc. While it is relatively easy for software developers to design the program, it heavily relies on hardware knowledge to design the pragmas, posing a big challenge for software developers. Recently, different machine learning algorithms, such as GNNs, have been proposed to automate the pragma design via performance prediction. However, when applying the trained model on new kernels, the significant domain shift often leads to unsatisfactory performance. We propose a more domain-generalizable model structure: a two-level hierarchical Mixture of Experts (MoE), that can be flexibly adapted to any GNN model. Different expert networks can learn to deal with different regions in the representation space, and they can utilize similar patterns between the old kernels and new kernels. In the low-level MoE, we apply MoE on three natural granularities of a program: node, basic block, and graph. The high-level MoE learns to aggregate the three granularities for the final decision. To stably train the hierarchical MoE, we further propose a two-stage training method. Extensive experiments verify the effectiveness of the hierarchical MoE.

This paper presents the first measurement of $\psi{(2S)}$ and $\chi_{c1}(3872)$ meson production within fully reconstructed jets. Each quarkonium state (tag) is reconstructed via its decay to the $J/\psi$($\rightarrow\mu^+\mu^-$)$\pi^+\pi^-$ final state in the forward region using proton-proton collision data collected by the LHCb experiment at the center-of-mass-energy of $13 \text{TeV}$ in 2016, corresponding to an integrated luminosity of $1.64 \text{fb}^{-1}$. The fragmentation function, presented as the ratio of the quarkonium-tag transverse momentum to the full jet transverse momentum ($p_{\mathrm{T}}(\text{tag})/p_{\mathrm{T}}(\text{jet})$), is measured differentially in $p_{\mathrm{T}}(\text{jet})$ and $p_{\mathrm{T}}(\text{tag})$ bins. The distributions are separated into promptly produced quarkonia from proton-proton collisions and quarkonia produced from displaced $b$-hadron decays. While the displaced quarkonia fragmentation functions are in general well described by parton-shower predictions, the prompt quarkonium distributions differ significantly from fixed-order non-relativistic QCD (NRQCD) predictions followed by a QCD parton shower., Comment: All figures and tables, along with machine-readable versions and any supplementary material and additional information, are available at https://lbfence.cern.ch/alcm/public/analysis/full-details/1618/ (LHCb public pages)

Recent advancements in predictive models have demonstrated exceptional capabilities in predicting the future state of objects and scenes. However, the lack of categorization based on inherent characteristics continues to hinder the progress of predictive model development. Additionally, existing benchmarks are unable to effectively evaluate higher-capability, highly embodied predictive models from an embodied perspective. In this work, we classify the functionalities of predictive models into a hierarchy and take the first step in evaluating World Simulators by proposing a dual evaluation framework called WorldSimBench. WorldSimBench includes Explicit Perceptual Evaluation and Implicit Manipulative Evaluation, encompassing human preference assessments from the visual perspective and action-level evaluations in embodied tasks, covering three representative embodied scenarios: Open-Ended Embodied Environment, Autonomous, Driving, and Robot Manipulation. In the Explicit Perceptual Evaluation, we introduce the HF-Embodied Dataset, a video assessment dataset based on fine-grained human feedback, which we use to train a Human Preference Evaluator that aligns with human perception and explicitly assesses the visual fidelity of World Simulators. In the Implicit Manipulative Evaluation, we assess the video-action consistency of World Simulators by evaluating whether the generated situation-aware video can be accurately translated into the correct control signals in dynamic environments. Our comprehensive evaluation offers key insights that can drive further innovation in video generation models, positioning World Simulators as a pivotal advancement toward embodied artificial intelligence.

Integrating multi-modal clinical data, such as electronic health records (EHR) and chest X-ray images (CXR), is particularly beneficial for clinical prediction tasks. However, in a temporal setting, multi-modal data are often inherently asynchronous. EHR can be continuously collected but CXR is generally taken with a much longer interval due to its high cost and radiation dose. When clinical prediction is needed, the last available CXR image might have been outdated, leading to suboptimal predictions. To address this challenge, we propose DDL-CXR, a method that dynamically generates an up-to-date latent representation of the individualized CXR images. Our approach leverages latent diffusion models for patient-specific generation strategically conditioned on a previous CXR image and EHR time series, providing information regarding anatomical structures and disease progressions, respectively. In this way, the interaction across modalities could be better captured by the latent CXR generation process, ultimately improving the prediction performance. Experiments using MIMIC datasets show that the proposed model could effectively address asynchronicity in multimodal fusion and consistently outperform existing methods., Comment: Accepted by NeurIPS-24

The presence of unhealthy nodes in cloud infrastructure signals the potential failure of machines, which can significantly impact the availability and reliability of cloud services, resulting in negative customer experiences. Effectively addressing unhealthy node mitigation is therefore vital for sustaining cloud system performance. This paper introduces Deoxys, a causal inference engine tailored to recommending mitigation actions for unhealthy node in cloud systems to minimize virtual machine downtime and interruptions during unhealthy events. It employs double machine learning combined with causal forest to produce precise and reliable mitigation recommendations based solely on limited observational data collected from the historical unhealthy events. To enhance the causal inference model, Deoxys further incorporates a policy fallback mechanism based on model uncertainty and action overriding mechanisms to (i) improve the reliability of the system, and (ii) strike a good tradeoff between downtime reduction and resource utilization, thereby enhancing the overall system performance. After deploying Deoxys in a large-scale cloud infrastructure at Microsoft, our observations demonstrate that Deoxys significantly reduces average VM downtime by 53% compared to a legacy policy, while leading to 49.5% lower VM interruption rate. This substantial improvement enhances the reliability and stability of cloud platforms, resulting in a seamless customer experience.