Search

Heuristics are commonly used to tackle diverse search and optimization problems. Design heuristics usually require tedious manual crafting with domain knowledge. Recent works have incorporated large language models (LLMs) into automatic heuristic search leveraging their powerful language and coding capacity. However, existing research focuses on the optimal performance on the target problem as the sole objective, neglecting other criteria such as efficiency and scalability, which are vital in practice. To tackle this challenge, we propose to model heuristic search as a multi-objective optimization problem and consider introducing other practical criteria beyond optimal performance. Due to the complexity of the search space, conventional multi-objective optimization methods struggle to effectively handle multi-objective heuristic search. We propose the first LLM-based multi-objective heuristic search framework, Multi-objective Evolution of Heuristic (MEoH), which integrates LLMs in a zero-shot manner to generate a non-dominated set of heuristics to meet multiple design criteria. We design a new dominance-dissimilarity mechanism for effective population management and selection, which incorporates both code dissimilarity in the search space and dominance in the objective space. MEoH is demonstrated in two well-known combinatorial optimization problems: the online Bin Packing Problem (BPP) and the Traveling Salesman Problem (TSP). Results indicate that a variety of elite heuristics are automatically generated in a single run, offering more trade-off options than existing methods. It successfully achieves competitive or superior performance while improving efficiency up to 10 times. Moreover, we also observe that the multi-objective search introduces novel insights into heuristic design and leads to the discovery of diverse heuristics.

Effective retinal vessel segmentation requires a sophisticated integration of global contextual awareness and local vessel continuity. To address this challenge, we propose the Graph Capsule Convolution Network (GCC-UNet), which merges capsule convolutions with CNNs to capture both local and global features. The Graph Capsule Convolution operator is specifically designed to enhance the representation of global context, while the Selective Graph Attention Fusion module ensures seamless integration of local and global information. To further improve vessel continuity, we introduce the Bottleneck Graph Attention module, which incorporates Channel-wise and Spatial Graph Attention mechanisms. The Multi-Scale Graph Fusion module adeptly combines features from various scales. Our approach has been rigorously validated through experiments on widely used public datasets, with ablation studies confirming the efficacy of each component. Comparative results highlight GCC-UNet's superior performance over existing methods, setting a new benchmark in retinal vessel segmentation. Notably, this work represents the first integration of vanilla, graph, and capsule convolutional techniques in the domain of medical image segmentation.

Multiobjective optimization problems (MOPs) are prevalent in machine learning, with applications in multi-task learning, learning under fairness or robustness constraints, etc. Instead of reducing multiple objective functions into a scalar objective, MOPs aim to optimize for the so-called Pareto optimality or Pareto set learning, which involves optimizing more than one objective function simultaneously, over models with millions of parameters. Existing benchmark libraries for MOPs mainly focus on evolutionary algorithms, most of which are zeroth-order methods that do not effectively utilize higher-order information from objectives and cannot scale to large-scale models with millions of parameters. In light of the above gap, this paper introduces LibMOON, the first multiobjective optimization library that supports state-of-the-art gradient-based methods, provides a fair benchmark, and is open-sourced for the community.

Effective activation functions introduce non-linear transformations, providing neural networks with stronger fitting capa-bilities, which help them better adapt to real data distributions. Huawei Noah's Lab believes that dynamic activation functions are more suitable than static activation functions for enhancing the non-linear capabilities of neural networks. Tsinghua University's related research also suggests using dynamically adjusted activation functions. Building on the ideas of using fine-tuned activation functions from Tsinghua University and Huawei Noah's Lab, we propose a series-based learnable ac-tivation function called LSLU (Learnable Series Linear Units). This method simplifies deep learning networks while im-proving accuracy. This method introduces learnable parameters {\theta} and {\omega} to control the activation function, adapting it to the current layer's training stage and improving the model's generalization. The principle is to increase non-linearity in each activation layer, boosting the network's overall non-linearity. We evaluate LSLU's performance on CIFAR10, CIFAR100, and specific task datasets (e.g., Silkworm), validating its effectiveness. The convergence behavior of the learnable parameters {\theta} and {\omega}, as well as their effects on generalization, are analyzed. Our empirical results show that LSLU enhances the general-ization ability of the original model in various tasks while speeding up training. In VanillaNet training, parameter {\theta} initially decreases, then increases before stabilizing, while {\omega} shows an opposite trend. Ultimately, LSLU achieves a 3.17% accuracy improvement on CIFAR100 for VanillaNet (Table 3). Codes are available at https://github.com/vontran2021/Learnable-series-linear-units-LSLU.

Video generation models hold substantial potential in areas such as filmmaking. However, current video diffusion models need high computational costs and produce suboptimal results due to high complexity of video generation task. In this paper, we propose \textbf{ConFiner}, an efficient high-quality video generation framework that decouples video generation into easier subtasks: structure \textbf{con}trol and spatial-temporal re\textbf{fine}ment. It can generate high-quality videos with chain of off-the-shelf diffusion model experts, each expert responsible for a decoupled subtask. During the refinement, we introduce coordinated denoising, which can merge multiple diffusion experts' capabilities into a single sampling. Furthermore, we design ConFiner-Long framework, which can generate long coherent video with three constraint strategies on ConFiner. Experimental results indicate that with only 10\% of the inference cost, our ConFiner surpasses representative models like Lavie and Modelscope across all objective and subjective metrics. And ConFiner-Long can generate high-quality and coherent videos with up to 600 frames.

We introduce a novel framework to financial time series forecasting that leverages causality-inspired models to balance the trade-off between invariance to distributional changes and minimization of prediction errors. To the best of our knowledge, this is the first study to conduct a comprehensive comparative analysis among state-of-the-art causal discovery algorithms, benchmarked against non-causal feature selection techniques, in the application of forecasting asset returns. Empirical evaluations demonstrate the efficacy of our approach in yielding stable and accurate predictions, outperforming baseline models, particularly in tumultuous market conditions.

We introduce MoMa, a novel modality-aware mixture-of-experts (MoE) architecture designed for pre-training mixed-modal, early-fusion language models. MoMa processes images and text in arbitrary sequences by dividing expert modules into modality-specific groups. These groups exclusively process designated tokens while employing learned routing within each group to maintain semantically informed adaptivity. Our empirical results reveal substantial pre-training efficiency gains through this modality-specific parameter allocation. Under a 1-trillion-token training budget, the MoMa 1.4B model, featuring 4 text experts and 4 image experts, achieves impressive FLOPs savings: 3.7x overall, with 2.6x for text and 5.2x for image processing compared to a compute-equivalent dense baseline, measured by pre-training loss. This outperforms the standard expert-choice MoE with 8 mixed-modal experts, which achieves 3x overall FLOPs savings (3x for text, 2.8x for image). Combining MoMa with mixture-of-depths (MoD) further improves pre-training FLOPs savings to 4.2x overall (text: 3.4x, image: 5.3x), although this combination hurts performance in causal inference due to increased sensitivity to router accuracy. These results demonstrate MoMa's potential to significantly advance the efficiency of mixed-modal, early-fusion language model pre-training, paving the way for more resource-efficient and capable multimodal AI systems., Comment: v2 -> update related work section v3 -> fix spelling

Automated heuristic design (AHD) has gained considerable attention for its potential to automate the development of effective heuristics. The recent advent of large language models (LLMs) has paved a new avenue for AHD, with initial efforts focusing on framing AHD as an evolutionary program search (EPS) problem. However, inconsistent benchmark settings, inadequate baselines, and a lack of detailed component analysis have left the necessity of integrating LLMs with search strategies and the true progress achieved by existing LLM-based EPS methods to be inadequately justified. This work seeks to fulfill these research queries by conducting a large-scale benchmark comprising four LLM-based EPS methods and four AHD problems across nine LLMs and five independent runs. Our extensive experiments yield meaningful insights, providing empirical grounding for the importance of evolutionary search in LLM-based AHD approaches, while also contributing to the advancement of future EPS algorithmic development. To foster accessibility and reproducibility, we have fully open-sourced our benchmark and corresponding results., Comment: Accepted by the 18th International Conference on Parallel Problem Solving From Nature (PPSN 2024)

The integration of real-world data (RWD) and randomized controlled trials (RCT) is increasingly important for advancing causal inference in scientific research. This combination holds great promise for enhancing the efficiency of causal effect estimation, offering benefits such as reduced trial participant numbers and expedited drug access for patients. Despite the availability of numerous data fusion methods, selecting the most appropriate one for a specific research question remains challenging. This paper systematically reviews and compares these methods regarding their assumptions, limitations, and implementation complexities. Through simulations reflecting real-world scenarios, we identify a prevalent risk-reward trade-off across different methods. We investigate and interpret this trade-off, providing key insights into the strengths and weaknesses of various methods; thereby helping researchers navigate through the application of data fusion for improved causal inference.

In the era of 5G and beyond, the increasing complexity of wireless networks necessitates innovative frameworks for efficient management and deployment. Digital twins (DTs), embodying real-time monitoring, predictive configurations, and enhanced decision-making capabilities, stand out as a promising solution in this context. Within a time-series data-driven framework that effectively maps wireless networks into digital counterparts, encapsulated by integrated vertical and horizontal twinning phases, this study investigates the security challenges in distributed network DT systems, which potentially undermine the reliability of subsequent network applications such as wireless traffic forecasting. Specifically, we consider a minimal-knowledge scenario for all attackers, in that they do not have access to network data and other specialized knowledge, yet can interact with previous iterations of server-level models. In this context, we spotlight a novel fake traffic injection attack designed to compromise a distributed network DT system for wireless traffic prediction. In response, we then propose a defense mechanism, termed global-local inconsistency detection (GLID), to counteract various model poisoning threats. GLID strategically removes abnormal model parameters that deviate beyond a particular percentile range, thereby fortifying the security of network twinning process. Through extensive experiments on real-world wireless traffic datasets, our experimental evaluations show that both our attack and defense strategies significantly outperform existing baselines, highlighting the importance of security measures in the design and implementation of DTs for 5G and beyond network systems., Comment: Accepted by Internet of Things Journal (IoT-J). arXiv admin note: substantial text overlap with arXiv:2404.14389

Honeycomb cobalt oxides containing 3$\it{d}$ Co$^{2+}$ ions might realize frustrated magnetism and novel quantum phases. Among candidate materials, Na$_{3}$Co$_{2}$SbO$_{6}$ stands out for its distorted honeycomb lattice and significant in-plane anisotropy, motivating vector-field tuning inside the honeycomb plane. Here we use thermal transport down to the mK regime to study twin-free crystals of Na$_{3}$Co$_{2}$SbO$_{6}$ subject to in-plane vector fields. We find that the thermal conductivity $\kappa$ never exceeds the heat-transport capability of phonons, rendering its suppression primarily due to phonon scattering off magnetic excitations and/or domain boundaries. The system's field-driven quantum criticality manifests itself as an abundance of magnetic fluctuations hindering the heat transport, which further depends on the field direction in an intriguing manner., Comment: 6 pages with 4 figures and 5 pages with 5 figures

Deep Reinforcement Learning (DRL) is regarded as a promising tool for optical network optimization. However, the flexibility and efficiency of current DRL-based solutions for optical network optimization require further improvement. Currently, generative models have showcased their significant performance advantages across various domains. In this paper, we introduce OpticGAI, the AI-generated policy design paradigm for optical networks. In detail, it is implemented as a novel DRL framework that utilizes generative models to learn the optimal policy network. Furthermore, we assess the performance of OpticGAI on two NP-hard optical network problems, Routing and Wavelength Assignment (RWA) and dynamic Routing, Modulation, and Spectrum Allocation (RMSA), to show the feasibility of the AI-generated policy paradigm. Simulation results have shown that OpticGAI achieves the highest reward and the lowest blocking rate of both RWA and RMSA problems. OpticGAI poses a promising direction for future research on generative AI-enhanced flexible optical network optimization., Comment: Accepted by ACM SIGCOMM 2024 Workshop on Hot Topics in Optical Technologies and Applications in Networking

Large language models (LLMs) often hallucinate and lack the ability to provide attribution for their generations. Semi-parametric LMs, such as kNN-LM, approach these limitations by refining the output of an LM for a given prompt using its nearest neighbor matches in a non-parametric data store. However, these models often exhibit slow inference speeds and produce non-fluent texts. In this paper, we introduce Nearest Neighbor Speculative Decoding (NEST), a novel semi-parametric language modeling approach that is capable of incorporating real-world text spans of arbitrary length into the LM generations and providing attribution to their sources. NEST performs token-level retrieval at each inference step to compute a semi-parametric mixture distribution and identify promising span continuations in a corpus. It then uses an approximate speculative decoding procedure that accepts a prefix of the retrieved span or generates a new token. NEST significantly enhances the generation quality and attribution rate of the base LM across a variety of knowledge-intensive tasks, surpassing the conventional kNN-LM method and performing competitively with in-context retrieval augmentation. In addition, NEST substantially improves the generation speed, achieving a 1.8x speedup in inference time when applied to Llama-2-Chat 70B.

Multi-objective optimization can be found in many real-world applications where some conflicting objectives can not be optimized by a single solution. Existing optimization methods often focus on finding a set of Pareto solutions with different optimal trade-offs among the objectives. However, the required number of solutions to well approximate the whole Pareto optimal set could be exponentially large with respect to the number of objectives, which makes these methods unsuitable for handling many optimization objectives. In this work, instead of finding a dense set of Pareto solutions, we propose a novel Tchebycheff set scalarization method to find a few representative solutions (e.g., 5) to cover a large number of objectives (e.g., $>100$) in a collaborative and complementary manner. In this way, each objective can be well addressed by at least one solution in the small solution set. In addition, we further develop a smooth Tchebycheff set scalarization approach for efficient optimization with good theoretical guarantees. Experimental studies on different problems with many optimization objectives demonstrate the effectiveness of our proposed method.

Confocal microscopy, a critical advancement in optical imaging, is widely applied because of its excellent anti-noise ability. However, it has low imaging efficiency and can cause phototoxicity. Optical-sectioning structured illumination microscopy (OS-SIM) can overcome the limitations of confocal microscopy but still face challenges in imaging depth and signal-to-noise ratio (SNR). We introduce the concept of confocal imaging into OS-SIM and propose confocal structured illumination microscopy (CSIM) to enhance the imaging performance of OS-SIM. CSIM exploits the principle of dual photography to reconstruct a dual image from each pixel of the camera. The reconstructed dual image is equivalent to the image obtained by using the spatial light modulator (SLM) as a virtual camera, enabling the separation of the conjugate and non-conjugate signals recorded by the camera pixel. We can reject the non-conjugate signals by extracting the conjugate signal from each dual image to reconstruct a confocal image when establishing the conjugate relationship between the camera and the SLM. We have constructed the theoretical framework of CSIM. Optical-sectioning experimental results demonstrate that CSIM can reconstruct images with superior SNR and greater imaging depth compared with existing OS-SIM. CSIM is expected to expand the application scope of OS-SIM.

Neural combinatorial optimization (NCO) is a promising learning-based approach to solving various vehicle routing problems without much manual algorithm design. However, the current NCO methods mainly focus on the in-distribution performance, while the real-world problem instances usually come from different distributions. A costly fine-tuning approach or generalized model retraining from scratch could be needed to tackle the out-of-distribution instances. Unlike the existing methods, this work investigates an efficient prompt learning approach in NCO for cross-distribution adaptation. To be concrete, we propose a novel prompt learning method to facilitate fast zero-shot adaptation of a pre-trained model to solve routing problem instances from different distributions. The proposed model learns a set of prompts among various distributions and then selects the best-matched one to prompt a pre-trained attention model for each problem instance. Extensive experiments show that the proposed prompt learning approach facilitates the fast adaptation of pre-trained routing models. It also outperforms existing generalized models on both in-distribution prediction and zero-shot generalization to a diverse set of new tasks. Our code implementation is available online https://github.com/FeiLiu36/PromptVRP.

As an emerging paradigm of content creation, AI-Generated Content (AIGC) has been widely adopted by a large number of edge end users. However, the requests for generated content from AIGC users have obvious diversity, and there remains a notable lack of research addressing the variance in user demands for AIGC services. This gap underscores a critical need for suitable AIGC service selection mechanisms satisfying various AIGC user requirements under resource-constrained edge environments. To address this challenge, this paper proposes a novel Attention-based Diffusion Soft Actor-Critic (ADSAC) algorithm to select the appropriate AIGC model in response to heterogeneous AIGC user requests. Specifically, the ADSAC algorithm integrates a diffusion model as the policy network in the off-policy reinforcement learning (RL) framework, to capture the intricate relationships between the characteristics of AIGC tasks and the integrated edge network states. Furthermore, an attention mechanism is utilized to harness the contextual long-range dependencies present in state feature vectors, enhancing the decision-making process. Extensive experiments validate the effectiveness of our algorithm in enhancing the overall user utility and reducing the crash rate of servers. Compared to the existing methods, the proposed ADSAC algorithm outperforms existing methods, reducing the overall user utility loss and the server crash rate by at least 58.3% and 58.4%, respectively. These results demonstrate our ADSAC algorithm is a robust solution to the challenges of diverse and dynamic user requirements in edge-based AIGC application environments.

AI-generated content (AIGC) models, represented by large language models (LLM), have brought revolutionary changes to the content generation fields. The high-speed and extensive 6G technology is an ideal platform for providing powerful AIGC mobile service applications, while future 6G mobile networks also need to support intelligent and personalized mobile generation services. However, the significant ethical and security issues of current AIGC models, such as adversarial attacks, privacy, and fairness, greatly affect the credibility of 6G intelligent networks, especially in ensuring secure, private, and fair AIGC applications. In this paper, we propose TrustGAIN, a novel paradigm for trustworthy AIGC in 6G networks, to ensure trustworthy large-scale AIGC services in future 6G networks. We first discuss the adversarial attacks and privacy threats faced by AIGC systems in 6G networks, as well as the corresponding protection issues. Subsequently, we emphasize the importance of ensuring the unbiasedness and fairness of the mobile generative service in future intelligent networks. In particular, we conduct a use case to demonstrate that TrustGAIN can effectively guide the resistance against malicious or generated false information. We believe that TrustGAIN is a necessary paradigm for intelligent and trustworthy 6G networks to support AIGC services, ensuring the security, privacy, and fairness of AIGC network services.

Currently, the generative model has garnered considerable attention due to its application in addressing the challenge of scarcity of abnormal samples in the industrial Internet of Things (IoT). However, challenges persist regarding the edge deployment of generative models and the optimization of joint edge AI-generated content (AIGC) tasks. In this paper, we focus on the edge optimization of AIGC task execution and propose GMEL, a generative model-driven industrial AIGC collaborative edge learning framework. This framework aims to facilitate efficient few-shot learning by leveraging realistic sample synthesis and edge-based optimization capabilities. First, a multi-task AIGC computational offloading model is presented to ensure the efficient execution of heterogeneous AIGC tasks on edge servers. Then, we propose an attention-enhanced multi-agent reinforcement learning (AMARL) algorithm aimed at refining offloading policies within the IoT system, thereby supporting generative model-driven edge learning. Finally, our experimental results demonstrate the effectiveness of the proposed algorithm in optimizing the total system latency of the edge-based AIGC task completion.

The neural combinatorial optimization (NCO) approach has shown great potential for solving routing problems without the requirement of expert knowledge. However, existing constructive NCO methods cannot directly solve large-scale instances, which significantly limits their application prospects. To address these crucial shortcomings, this work proposes a novel Instance-Conditioned Adaptation Model (ICAM) for better large-scale generalization of neural combinatorial optimization. In particular, we design a powerful yet lightweight instance-conditioned adaptation module for the NCO model to generate better solutions for instances across different scales. In addition, we develop an efficient three-stage reinforcement learning-based training scheme that enables the model to learn cross-scale features without any labeled optimal solution. Experimental results show that our proposed method is capable of obtaining excellent results with a very fast inference time in solving Traveling Salesman Problems (TSPs) and Capacitated Vehicle Routing Problems (CVRPs) across different scales. To the best of our knowledge, our model achieves state-of-the-art performance among all RL-based constructive methods for TSP and CVRP with up to 1,000 nodes., Comment: 17 pages, 6 figures

In the contemporary logistics industry, automation plays a pivotal role in enhancing production efficiency and expanding industrial scale. Autonomous mobile robots, in particular, have become integral to the modernization efforts in warehouses. One noteworthy application in robotic warehousing is the robotic sorting system (RSS), distinguished by its characteristics such as cost-effectiveness, simplicity, scalability, and adaptable throughput control. While previous research has focused on analyzing the efficiency of RSS, it often assumed an ideal robot management system ignoring potential queuing delays by assuming constant travel times. This study relaxes this assumption and explores the quantitative relationship between RSS configuration parameters and system throughput. We introduce a novel robot traffic management method, named the rhythmic control for sorting scenario (RC-S), for RSS operations, equipped with an estimation formula establishing the relationship between system performance and configurations. Simulations validate that RC-S reduces average service time by 10.3\% compared to the classical cooperative A* algorithm, while also improving throughput and runtime. Based on the performance analysis of RC-S, we further develop a layout optimization model for RSS, considering RSS configuration, desired throughput, and costs, to minimize expenses and determine the best layout. Numerical studies show that at lower throughput levels, facility costs dominate, while at higher throughput levels, labor costs prevail. Additionally, due to traffic efficiency limitations, RSS is well-suited for small-scale operations like end-of-supply-chain distribution centers.

We address a dynamic pricing problem for airlines aiming to maximize expected revenue from selling cargo space on a single-leg flight. The cargo shipments' weight and volume are uncertain and their precise values remain unavailable at the booking time. We model this problem as a Markov decision process, and further derive a necessary condition for its optimal pricing strategy. To break the curse of dimensionality, we develop two categories of approximation methods and pricing strategies. One category is based on the quantity of accepted bookings, while the other is founded on the expected weight and volume of accepted bookings. We prove that the pricing strategy of the quantity-based method possesses several inherent structural properties, which are crucial for analytically validating the model and accelerating the computational process. For the weight-volume-based approximation method, we derive a theoretical upper bound for the optimality gap of total expected revenue. For both methods, we further develop augmented strategies to address the extreme pricing issues in scenarios with high product heterogeneity and incorporate the second moment to enhance performance in the scenarios of high uncertainty, respectively. We utilize realistic dataset to conduct extensive numerical tests, and the results show that the average performance gap between the optimal expected revenue and that of each proposed pricing strategy is less than 10%. The quantity-based method requires the least computation, and performs quite well in the scenarios with low product heterogeneity. The augmented quantity-based method and the weight-volume-based method further enhance the resilience to product heterogeneity. The augmented weight-volume-based method significantly improves the revenue when there are high penalties for overbooking and high uncertainty.

In many real-world applications, the Pareto Set (PS) of a continuous multiobjective optimization problem can be a piecewise continuous manifold. A decision maker may want to find a solution set that approximates a small part of the PS and requires the solutions in this set share some similarities. This paper makes a first attempt to address this issue. We first develop a performance metric that considers both optimality and variable sharing. Then we design an algorithm for finding the model that minimizes the metric to meet the user's requirements. Experimental results illustrate that we can obtain a linear model that approximates the mapping from the preference vectors to solutions in a local area well., Comment: Preprint of EMO 2023 conference paper

The end-to-end neural combinatorial optimization (NCO) method shows promising performance in solving complex combinatorial optimization problems without the need for expert design. However, existing methods struggle with large-scale problems, hindering their practical applicability. To overcome this limitation, this work proposes a novel Self-Improved Learning (SIL) method for better scalability of neural combinatorial optimization. Specifically, we develop an efficient self-improved mechanism that enables direct model training on large-scale problem instances without any labeled data. Powered by an innovative local reconstruction approach, this method can iteratively generate better solutions by itself as pseudo-labels to guide efficient model training. In addition, we design a linear complexity attention mechanism for the model to efficiently handle large-scale combinatorial problem instances with low computation overhead. Comprehensive experiments on the Travelling Salesman Problem (TSP) and the Capacitated Vehicle Routing Problem (CVRP) with up to 100K nodes in both uniform and real-world distributions demonstrate the superior scalability of our method.

Federated neuromorphic learning (FedNL) leverages event-driven spiking neural networks and federated learning frameworks to effectively execute intelligent analysis tasks over amounts of distributed low-power devices but also perform vulnerability to poisoning attacks. The threat of backdoor attacks on traditional deep neural networks typically comes from time-invariant data. However, in FedNL, unknown threats may be hidden in time-varying spike signals. In this paper, we start to explore a novel vulnerability of FedNL-based systems with the concept of time division multiplexing, termed Spikewhisper, which allows attackers to evade detection as much as possible, as multiple malicious clients can imperceptibly poison with different triggers at different timeslices. In particular, the stealthiness of Spikewhisper is derived from the time-domain divisibility of global triggers, in which each malicious client pastes only one local trigger to a certain timeslice in the neuromorphic sample, and also the polarity and motion of each local trigger can be configured by attackers. Extensive experiments based on two different neuromorphic datasets demonstrate that the attack success rate of Spikewispher is higher than the temporally centralized attacks. Besides, it is validated that the effect of Spikewispher is sensitive to the trigger duration.

The formation of jets in black hole accretion systems is a long-standing problem. It has been proposed that a jet can be formed by extracting the rotation energy of the black hole ("BZ-jet") or the accretion flow ("disk-jet"). While both models can produce collimated relativistic outflows, neither has successfully explained the observed jet morphology. By employing general relativistic magnetohydrodynamic simulations, and considering nonthermal electrons accelerated by magnetic reconnection that is likely driven by magnetic eruption in the underlying accretion flow, we obtain images by radiative transfer calculations and compared them to millimeter observations of the jet in M87. We find that the BZ-jet originating from a magnetically arrested disk around a high-spin black hole can well reproduce the jet morphology, including its width and limb-brightening feature., Comment: 46 pages, 20 figures, 3 tables, published in Science Advances on 22 Mar 2024. arXiv admin note: substantial text overlap with arXiv:2206.05661

Multi-agent perception (MAP) allows autonomous systems to understand complex environments by interpreting data from multiple sources. This paper investigates intermediate collaboration for MAP with a specific focus on exploring "good" properties of collaborative view (i.e., post-collaboration feature) and its underlying relationship to individual views (i.e., pre-collaboration features), which were treated as an opaque procedure by most existing works. We propose a novel framework named CMiMC (Contrastive Mutual Information Maximization for Collaborative Perception) for intermediate collaboration. The core philosophy of CMiMC is to preserve discriminative information of individual views in the collaborative view by maximizing mutual information between pre- and post-collaboration features while enhancing the efficacy of collaborative views by minimizing the loss function of downstream tasks. In particular, we define multi-view mutual information (MVMI) for intermediate collaboration that evaluates correlations between collaborative views and individual views on both global and local scales. We establish CMiMNet based on multi-view contrastive learning to realize estimation and maximization of MVMI, which assists the training of a collaboration encoder for voxel-level feature fusion. We evaluate CMiMC on V2X-Sim 1.0, and it improves the SOTA average precision by 3.08% and 4.44% at 0.5 and 0.7 IoU (Intersection-over-Union) thresholds, respectively. In addition, CMiMC can reduce communication volume to 1/32 while achieving performance comparable to SOTA. Code and Appendix are released at https://github.com/77SWF/CMiMC.

We investigate efficient methods for training Large Language Models (LLMs) to possess capabilities in multiple specialized domains, such as coding, math reasoning and world knowledge. Our method, named Branch-Train-MiX (BTX), starts from a seed model, which is branched to train experts in embarrassingly parallel fashion with high throughput and reduced communication cost. After individual experts are asynchronously trained, BTX brings together their feedforward parameters as experts in Mixture-of-Expert (MoE) layers and averages the remaining parameters, followed by an MoE-finetuning stage to learn token-level routing. BTX generalizes two special cases, the Branch-Train-Merge method, which does not have the MoE finetuning stage to learn routing, and sparse upcycling, which omits the stage of training experts asynchronously. Compared to alternative approaches, BTX achieves the best accuracy-efficiency tradeoff.

The escalating threat of adversarial attacks on deep learning models, particularly in security-critical fields, has underscored the need for robust deep learning systems. Conventional robustness evaluations have relied on adversarial accuracy, which measures a model's performance under a specific perturbation intensity. However, this singular metric does not fully encapsulate the overall resilience of a model against varying degrees of perturbation. To address this gap, we propose a new metric termed adversarial hypervolume, assessing the robustness of deep learning models comprehensively over a range of perturbation intensities from a multi-objective optimization standpoint. This metric allows for an in-depth comparison of defense mechanisms and recognizes the trivial improvements in robustness afforded by less potent defensive strategies. Additionally, we adopt a novel training algorithm that enhances adversarial robustness uniformly across various perturbation intensities, in contrast to methods narrowly focused on optimizing adversarial accuracy. Our extensive empirical studies validate the effectiveness of the adversarial hypervolume metric, demonstrating its ability to reveal subtle differences in robustness that adversarial accuracy overlooks. This research contributes a new measure of robustness and establishes a standard for assessing and benchmarking the resilience of current and future defensive models against adversarial threats.

A two dimensional system with extra degrees of freedom, such as spin and valley, is of great interest in the study of quantum phase transitions. The critical condition when a transition between different multicomponent fractional quantum Hall states appears is one of the very few junctions for many body problems between theoretical calculations and experiments. In this work, we present that uniaxial strain induces pseudospin transitions of composite fermions in a two-dimensional hole gas. Determined from transport behavior, strain along <111> effectively changes pseudospin energy levels. We deduce that diagonal strain dominates these variations. Our experiment provides a wedge for manipulating two dimensional interacting systems mechanically., Comment: 12 pages with 4 figures and 9 pages with 4 figures

We propose an autonomous exploration algorithm designed for decentralized multi-robot teams, which takes into account map and localization uncertainties of range-sensing mobile robots. Virtual landmarks are used to quantify the combined impact of process noise and sensor noise on map uncertainty. Additionally, we employ an iterative expectation-maximization inspired algorithm to assess the potential outcomes of both a local robot's and its neighbors' next-step actions. To evaluate the effectiveness of our framework, we conduct a comparative analysis with state-of-the-art algorithms. The results of our experiments show the proposed algorithm's capacity to strike a balance between curbing map uncertainty and achieving efficient task allocation among robots.

Multi-objective optimization problems can be found in many real-world applications, where the objectives often conflict each other and cannot be optimized by a single solution. In the past few decades, numerous methods have been proposed to find Pareto solutions that represent optimal trade-offs among the objectives for a given problem. However, these existing methods could have high computational complexity or may not have good theoretical properties for solving a general differentiable multi-objective optimization problem. In this work, by leveraging the smooth optimization technique, we propose a lightweight and efficient smooth Tchebycheff scalarization approach for gradient-based multi-objective optimization. It has good theoretical properties for finding all Pareto solutions with valid trade-off preferences, while enjoying significantly lower computational complexity compared to other methods. Experimental results on various real-world application problems fully demonstrate the effectiveness of our proposed method., Comment: Accepted by the 41st International Conference on Machine Learning (ICML 2024)

Placement is crucial in the physical design, as it greatly affects power, performance, and area metrics. Recent advancements in analytical methods, such as DREAMPlace, have demonstrated impressive performance in global placement. However, DREAMPlace has some limitations, e.g., may not guarantee legalizable placements under the same settings, leading to fragile and unpredictable results. This paper highlights the main issue as being stuck in local optima, and proposes a hybrid optimization framework to efficiently escape the local optima, by perturbing the placement result iteratively. The proposed framework achieves significant improvements compared to state-of-the-art methods on two popular benchmarks., Comment: Work-in-Progress (WIP) poster of DAC 2024

We systematically study the acousto-current of two-dimensional electron systems in the integer and fractional quantum Hall regimes using surface acoustic waves. We are able to separate the co-existing acoustic scattering and drag, when phonons induce drag current and tune the electron conductivity, respectively. At large acoustic power, the drag current is finite when the system is compressible and exhibits minima when incompressible quantum Hall effects appear. Surprisingly, it exhibits anomalously large bipolar spikes within the quantum Hall plateaus while it vanishes linearly with reduced acoustic power at compressible phases. The current peaks reverse their polarity at the two flanks of exact integer or fractional fillings, consistent with the opposite electric charge of the quasiparticle/quasihole.

Vehicle routing problems (VRPs), which can be found in numerous real-world applications, have been an important research topic for several decades. Recently, the neural combinatorial optimization (NCO) approach that leverages a learning-based model to solve VRPs without manual algorithm design has gained substantial attention. However, current NCO methods typically require building one model for each routing problem, which significantly hinders their practical application for real-world industry problems with diverse attributes. In this work, we make the first attempt to tackle the crucial challenge of cross-problem generalization. In particular, we formulate VRPs as different combinations of a set of shared underlying attributes and solve them simultaneously via a single model through attribute composition. In this way, our proposed model can successfully solve VRPs with unseen attribute combinations in a zero-shot generalization manner. Extensive experiments are conducted on eleven VRP variants, benchmark datasets, and industry logistic scenarios. The results show that the unified model demonstrates superior performance in the eleven VRPs, reducing the average gap to around 5% from over 20% in the existing approach and achieving a significant performance boost on benchmark datasets as well as a real-world logistics application. The source code is included in https://github.com/FeiLiu36/MTNCO.

In order for large language model (LLM)-based assistants to effectively adapt to evolving information needs, it must be possible to update their factual knowledge through continued training on new data. The standard recipe for doing so involves continued pre-training on new documents followed by instruction-tuning on question-answer (QA) pairs. However, we find that LLMs trained with this recipe struggle to answer questions, even though the perplexity of documents is minimized. We found that QA pairs are generally straightforward, while documents are more complex, weaving many factual statements together in an intricate manner. Therefore, we hypothesize that it is beneficial to expose LLMs to QA pairs before continued pre-training on documents so that the process of encoding knowledge from complex documents takes into account how this knowledge is accessed through questions. Based on this, we propose pre-instruction-tuning (PIT), a method that instruction-tunes on questions prior to training on documents. This contrasts with standard instruction-tuning, which learns how to extract knowledge after training on documents. Extensive experiments and ablation studies demonstrate that pre-instruction-tuning significantly enhances the ability of LLMs to absorb knowledge from new documents, outperforming standard instruction-tuning by 17.8%., Comment: ACL 2024. The reproduced data for this paper is available at https://github.com/Edward-Sun/PIT

Collision avoidance algorithms for Autonomous Surface Vehicles (ASV) that follow the Convention on the International Regulations for Preventing Collisions at Sea (COLREGs) have been proposed in recent years. However, it may be difficult and unsafe to follow COLREGs in congested waters, where multiple ASVs are navigating in the presence of static obstacles and strong currents, due to the complex interactions. To address this problem, we propose a decentralized multi-ASV collision avoidance policy based on Distributional Reinforcement Learning, which considers the interactions among ASVs as well as with static obstacles and current flows. We evaluate the performance of the proposed Distributional RL based policy against a traditional RL-based policy and two classical methods, Artificial Potential Fields (APF) and Reciprocal Velocity Obstacles (RVO), in simulation experiments, which show that the proposed policy achieves superior performance in navigation safety, while requiring minimal travel time and energy. A variant of our framework that automatically adapts its risk sensitivity is also demonstrated to improve ASV safety in highly congested environments., Comment: The 2024 IEEE International Conference on Robotics and Automation (ICRA 2024)

It is desirable in many multi-objective machine learning applications, such as multi-task learning with conflicting objectives and multi-objective reinforcement learning, to find a Pareto solution that can match a given preference of a decision maker. These problems are often large-scale with available gradient information but cannot be handled very well by the existing algorithms. To tackle this critical issue, this paper proposes a novel predict-and-correct framework for locating a Pareto solution that fits the preference of a decision maker. In the proposed framework, a constraint function is introduced in the search progress to align the solution with a user-specific preference, which can be optimized simultaneously with multiple objective functions. Experimental results show that our proposed method can efficiently find a particular Pareto solution under the demand of a decision maker for standard multiobjective benchmark, multi-task learning, and multi-objective reinforcement learning problems with more than thousands of decision variables. Code is available at: https://github.com/xzhang2523/pmgda. Our code is current provided in the pgmda.rar attached file and will be open-sourced after publication.}

Multiobjective optimization (MOO) is prevalent in numerous applications, in which a Pareto front (PF) is constructed to display optima under various preferences. Previous methods commonly utilize the set of Pareto objectives (particles on the PF) to represent the entire PF. However, the empirical distribution of the Pareto objectives on the PF is rarely studied, which implicitly impedes the generation of diverse and representative Pareto objectives in previous methods. To bridge the gap, we suggest in this paper constructing \emph{uniformly distributed} Pareto objectives on the PF, so as to alleviate the limited diversity found in previous MOO approaches. We are the first to formally define the concept of ``uniformity" for an MOO problem. We optimize the maximal minimal distances on the Pareto front using a neural network, resulting in both asymptotically and non-asymptotically uniform Pareto objectives. Our proposed method is validated through experiments on real-world and synthetic problems, which demonstrates the efficacy in generating high-quality uniform Pareto objectives and the encouraging performance exceeding existing state-of-the-art methods. The detailed model implementation and the code are scheduled to be open-sourced upon publication.

Surface Acoustic Wave (SAW) is a powerful technique for investigating quantum phases appearing in two-dimensional electron systems. The electrons respond to the piezoelectric field of SAWthrough screening, attenuating its amplitude and shifting its velocity, which is described by the relaxation model. In this work, we systematically study this interaction using orders of magnitude lower SAW amplitude than that in previous studies. At high magnetic fields when electrons form highly correlated states such as the quantum Hall effect, we observe an anomalously large attenuation of SAW while the acoustic speed remains considerably high, inconsistent with the conventional relaxation model. This anomaly exists only when the SAW power is sufficiently low.

In the rapidly evolving field of machine learning, adversarial attacks present a significant challenge to model robustness and security. Decision-based attacks, which only require feedback on the decision of a model rather than detailed probabilities or scores, are particularly insidious and difficult to defend against. This work introduces L-AutoDA (Large Language Model-based Automated Decision-based Adversarial Attacks), a novel approach leveraging the generative capabilities of Large Language Models (LLMs) to automate the design of these attacks. By iteratively interacting with LLMs in an evolutionary framework, L-AutoDA automatically designs competitive attack algorithms efficiently without much human effort. We demonstrate the efficacy of L-AutoDA on CIFAR-10 dataset, showing significant improvements over baseline methods in both success rate and computational efficiency. Our findings underscore the potential of language models as tools for adversarial attack generation and highlight new avenues for the development of robust AI systems., Comment: Camera ready version for GECCO'24 workshop

Black-box query-based attacks constitute significant threats to Machine Learning as a Service (MLaaS) systems since they can generate adversarial examples without accessing the target model's architecture and parameters. Traditional defense mechanisms, such as adversarial training, gradient masking, and input transformations, either impose substantial computational costs or compromise the test accuracy of non-adversarial inputs. To address these challenges, we propose an efficient defense mechanism, PuriDefense, that employs random patch-wise purifications with an ensemble of lightweight purification models at a low level of inference cost. These models leverage the local implicit function and rebuild the natural image manifold. Our theoretical analysis suggests that this approach slows down the convergence of query-based attacks by incorporating randomness into purifications. Extensive experiments on CIFAR-10 and ImageNet validate the effectiveness of our proposed purifier-based defense mechanism, demonstrating significant improvements in robustness against query-based attacks.

Heuristics are widely used for dealing with complex search and optimization problems. However, manual design of heuristics can be often very labour extensive and requires rich working experience and knowledge. This paper proposes Evolution of Heuristic (EoH), a novel evolutionary paradigm that leverages both Large Language Models (LLMs) and Evolutionary Computation (EC) methods for Automatic Heuristic Design (AHD). EoH represents the ideas of heuristics in natural language, termed thoughts. They are then translated into executable codes by LLMs. The evolution of both thoughts and codes in an evolutionary search framework makes it very effective and efficient for generating high-performance heuristics. Experiments on three widely studied combinatorial optimization benchmark problems demonstrate that EoH outperforms commonly used handcrafted heuristics and other recent AHD methods including FunSearch. Particularly, the heuristic produced by EoH with a low computational budget (in terms of the number of queries to LLMs) significantly outperforms widely-used human hand-crafted baseline algorithms for the online bin packing problem.