Search

Content-based Recommender Systems (CRSs) play a crucial role in shaping user experiences in e-commerce, online advertising, and personalized recommendations. However, due to the vast amount of categorical features, the embedding tables used in CRS models pose a significant storage bottleneck for real-world deployment, especially on resource-constrained devices. To address this problem, various embedding pruning methods have been proposed, but most existing ones require expensive retraining steps for each target parameter budget, leading to enormous computation costs. In reality, this computation cost is a major hurdle in real-world applications with diverse storage requirements, such as federated learning and streaming settings. In this paper, we propose Shapley Value-guided Embedding Reduction (Shaver) as our response. With Shaver, we view the problem from a cooperative game perspective, and quantify each embedding parameter's contribution with Shapley values to facilitate contribution-based parameter pruning. To address the inherently high computation costs of Shapley values, we propose an efficient and unbiased method to estimate Shapley values of a CRS's embedding parameters. Moreover, in the pruning stage, we put forward a field-aware codebook to mitigate the information loss in the traditional zero-out treatment. Through extensive experiments on three real-world datasets, Shaver has demonstrated competitive performance with lightweight recommendation models across various parameter budgets. The source code is available at https://anonymous.4open.science/r/shaver-E808

The diffusion model, a new generative modeling paradigm, has achieved significant success in generating images, audio, video, and text. It has been adapted for sequence-to-sequence text generation (Seq2Seq) through DiffuSeq, termed S2S Diffusion. Existing S2S-Diffusion models predominantly rely on fixed or hand-crafted rules to schedule noise during the diffusion and denoising processes. However, these models are limited by non-contextualized noise, which fails to fully consider the characteristics of Seq2Seq tasks. In this paper, we propose the Meta-DiffuB framework - a novel scheduler-exploiter S2S-Diffusion paradigm designed to overcome the limitations of existing S2S-Diffusion models. We employ Meta-Exploration to train an additional scheduler model dedicated to scheduling contextualized noise for each sentence. Our exploiter model, an S2S-Diffusion model, leverages the noise scheduled by our scheduler model for updating and generation. Meta-DiffuB achieves state-of-the-art performance compared to previous S2S-Diffusion models and fine-tuned pre-trained language models (PLMs) across four Seq2Seq benchmark datasets. We further investigate and visualize the impact of Meta-DiffuB's noise scheduling on the generation of sentences with varying difficulties. Additionally, our scheduler model can function as a "plug-and-play" model to enhance DiffuSeq without the need for fine-tuning during the inference stage.

One of the most challenging problems in the computational study of localization in quantum manybody systems is to capture the effects of rare events, which requires sampling over exponentially many disorder realizations. We implement an efficient procedure on a quantum processor, leveraging quantum parallelism, to efficiently sample over all disorder realizations. We observe localization without disorder in quantum many-body dynamics in one and two dimensions: perturbations do not diffuse even though both the generator of evolution and the initial states are fully translationally invariant. The disorder strength as well as its density can be readily tuned using the initial state. Furthermore, we demonstrate the versatility of our platform by measuring Renyi entropies. Our method could also be extended to higher moments of the physical observables and disorder learning.

Lattice gauge theories (LGTs) can be employed to understand a wide range of phenomena, from elementary particle scattering in high-energy physics to effective descriptions of many-body interactions in materials. Studying dynamical properties of emergent phases can be challenging as it requires solving many-body problems that are generally beyond perturbative limits. We investigate the dynamics of local excitations in a $\mathbb{Z}_2$ LGT using a two-dimensional lattice of superconducting qubits. We first construct a simple variational circuit which prepares low-energy states that have a large overlap with the ground state; then we create particles with local gates and simulate their quantum dynamics via a discretized time evolution. As the effective magnetic field is increased, our measurements show signatures of transitioning from deconfined to confined dynamics. For confined excitations, the magnetic field induces a tension in the string connecting them. Our method allows us to experimentally image string dynamics in a (2+1)D LGT from which we uncover two distinct regimes inside the confining phase: for weak confinement the string fluctuates strongly in the transverse direction, while for strong confinement transverse fluctuations are effectively frozen. In addition, we demonstrate a resonance condition at which dynamical string breaking is facilitated. Our LGT implementation on a quantum processor presents a novel set of techniques for investigating emergent particle and string dynamics.

This paper presents a Multimodal Ambient Context-enriched Intelligence Platform (MACeIP) for Smart Cities, a comprehensive system designed to enhance urban management and citizen engagement. Our platform integrates advanced technologies, including Internet of Things (IoT) sensors, edge and cloud computing, and Multimodal AI, to create a responsive and intelligent urban ecosystem. Key components include Interactive Hubs for citizen interaction, an extensive IoT sensor network, intelligent public asset management, a pedestrian monitoring system, a City Planning Portal, and a Cloud Computing System. We demonstrate the prototype of MACeIP in several cities, focusing on Fredericton, New Brunswick. This work contributes to innovative city development by offering a scalable, efficient, and user-centric approach to urban intelligence and management., Comment: 4 pages, 6 figures, IEEE/IEIE ICCE-Asia 2024

Large language models (LLMs) equipped with chain-of-thoughts (CoT) prompting have shown significant multi-step reasoning capabilities in factual content like mathematics, commonsense, and logic. However, their performance in narrative reasoning, which demands greater abstraction capabilities, remains unexplored. This study utilizes tropes in movie synopses to assess the abstract reasoning abilities of state-of-the-art LLMs and uncovers their low performance. We introduce a trope-wise querying approach to address these challenges and boost the F1 score by 11.8 points. Moreover, while prior studies suggest that CoT enhances multi-step reasoning, this study shows CoT can cause hallucinations in narrative content, reducing GPT-4's performance. We also introduce an Adversarial Injection method to embed trope-related text tokens into movie synopses without explicit tropes, revealing CoT's heightened sensitivity to such injections. Our comprehensive analysis provides insights for future research directions., Comment: EMNLP 2024 Findings. The first two authors contributed equally. Code: https://github.com/Shelley1214/Trope

Hydro-generating units (HGUs) play a crucial role in integrating intermittent renewable energy sources into the power grid due to their flexible operational capabilities. This evolving role has led to an increase in transient events, such as startups, which impose significant stresses on turbines, leading to increased turbine fatigue and a reduced operational lifespan. Consequently, optimizing startup sequences to minimize stresses is vital for hydropower utilities. However, this task is challenging, as stress measurements on prototypes can be expensive and time-consuming. To tackle this challenge, we propose an innovative automated approach to optimize the startup parameters of HGUs with a limited budget of measured startup sequences. Our method combines active learning and black-box optimization techniques, utilizing virtual strain sensors and dynamic simulations of HGUs. This approach was tested in real-time during an on-site measurement campaign on an instrumented Francis turbine prototype. The results demonstrate that our algorithm successfully identified an optimal startup sequence using only seven measured sequences. It achieves a remarkable 42% reduction in the maximum strain cycle amplitude compared to the standard startup sequence. This study paves the way for more efficient HGU startup optimization, potentially extending their operational lifespans.

In this paper, we propose a new Bayesian Poisson network autoregression mixture model (PNARM). Our model combines ideas from the models of Dahl 2008, Ren et al. 2024 and Armillotta and Fokianos 2024, as it is motivated by the following aims. We consider the problem of modelling multivariate count time series since they arise in many real-world data sets, but has been studied less than its Gaussian-distributed counterpart (Fokianos 2024). Additionally, we assume that the time series occur on the nodes of a known underlying network where the edges dictate the form of the structural vector autoregression model, as a means of imposing sparsity. A further aim is to accommodate heterogeneous node dynamics, and to develop a probabilistic model for clustering nodes that exhibit similar behaviour. We develop an MCMC algorithm for sampling from the model's posterior distribution. The model is applied to a data set of COVID-19 cases in the counties of the Republic of Ireland.

An atomic array coupled to a photonic crystal waveguide forms a strongly coupled quantum interface, exhibiting various intriguing collective features of quantum dynamics. Here we consider a homogeneous atomic array and theoretically investigate its steady-state distribution when the incident fields drive the atoms from both sides at asymmetric angles. This effectively creates an interface shared by two zones of atoms under different driving angles. This setup introduces a competition between photon-mediated dipole-dipole interactions and the directionality of coupling, while differences of the travelling phases from the incident angles further influence the overall steady-state behavior. Under this asymmetric driving scheme, the presence of strongly confined localization can be identified, where localization can occur either at the interface or at one of edges. Additionally, we examine the size effect on the atomic localization, deriving an empirical formula to predict parameter regimes that favor interfaced localization. We also consider a defect-driving scheme, where a third zone is created by undriven atoms under symmetric travelling phases. This results in strongly confined single-site excitation localization, which can be explained through analytical solutions under the reciprocal coupling. Finally, we propose several methods for precise control of multiple single-site localizations under the defect-driving scheme. Our results provide insights into driven-dissipative quantum systems with nonreciprocal couplings and pave the way for quantum simulation of exotic many-body states relevant to quantum information applications., Comment: 8 figures

A natural open problem in Ramsey theory is to determine those $3$-graphs $H$ for which the off-diagonal Ramsey number $r(H, K_n^{(3)})$ grows polynomially with $n$. We make substantial progress on this question by showing that if $H$ is tightly connected or has at most two tight components, then $r(H, K_n^{(3)})$ grows polynomially if and only if $H$ is not contained in an iterated blowup of an edge., Comment: 12 pages

We propose Hymba, a family of small language models featuring a hybrid-head parallel architecture that integrates transformer attention mechanisms with state space models (SSMs) for enhanced efficiency. Attention heads provide high-resolution recall, while SSM heads enable efficient context summarization. Additionally, we introduce learnable meta tokens that are prepended to prompts, storing critical information and alleviating the "forced-to-attend" burden associated with attention mechanisms. This model is further optimized by incorporating cross-layer key-value (KV) sharing and partial sliding window attention, resulting in a compact cache size. During development, we conducted a controlled study comparing various architectures under identical settings and observed significant advantages of our proposed architecture. Notably, Hymba achieves state-of-the-art results for small LMs: Our Hymba-1.5B-Base model surpasses all sub-2B public models in performance and even outperforms Llama-3.2-3B with 1.32% higher average accuracy, an 11.67x cache size reduction, and 3.49x throughput., Comment: 20 pages, models are available on huggingface

Group Point-of-Interest (POI) recommendations aim to predict the next POI that satisfies the diverse preferences of a group of users. This task is more challenging than traditional individual POI recommendations due to complex group decision-making and extremely sparse group-level check-in data. Existing methods for group POI recommendations primarily rely on single ID-based features from check-in data, capturing only statistical correlations and failing to fully utilize the rich semantic information contained in the check-ins, resulting in suboptimal performance. To this end, we propose a framework that unleashes the power of the Large Language Model (LLM) for context-aware group POI recommendations (LLMGPR). Our approach first introduces POI tokens alongside the original word tokens of the LLM, which are initialized by applying the LLM to the rich information of each POI. We then propose a novel sequencing adapter guided by Quantized Low-Rank Adaptation (QLORA) to modify the LLM. The enhanced LLM can learn sequence representations by combining semantic-enhanced POI tokens and rich contextual information including positional encodings and spatio-temporal differences. This approach can be adapted for learning either group or user representations depending on the sequence type. Furthermore, we enhance group representations by aggregating individual member representations with another QLORA-based aggregation adapter and introducing a self-supervised learning task that predicts the purpose of check-in sequences, alleviating the data sparsity issue. Our experimental results demonstrate that LLMGPR outperforms existing methods, effectively addressing group-level data sparsity and providing superior recommendations.

In 1977, G\'erard Toulouse has proposed a new concept termed as "frustration" in spin systems. Using this definition, several frustrated models have been created and studied, among them we can mention the Villain's model, the fully frustrated simple cubic lattice, the antiferromagnetic triangular lattice. The former models are systems with mixed ferromagnetic and antiferromagnetic bonds, while in the latter containing only an antiferromagnetic interaction, the frustration is caused by the lattice geometry. These frustrated spin systems have novel properties that we will review in this paper. One of the striking aspects is the fact that well-established methods such as the renormalization group fail to deal with the nature of the phase transition in frustrated systems. Investigations of properties of frustrated spin systems have been intensive since the 80's. I myself got involved in several investigations of frustrated spin systems soon after my PhD. I have learned a lot from numerous discussions with G\'erard Toulouse. Until today, I am still working on frustrated systems such as skyrmions. In this review, I trace back a number of my works over the years on frustrated spin systems going from exactly solved 2D Ising frustrated models, to XY and Heisenberg 2D and 3D frustrated lattices. At the end I present my latest results on skyrmions resulting from the frustration caused by the competition between the exchange interaction and the Dzyaloshinskii-Moriya interaction under an applied magnetic field. A quantum spin-wave theory using the Green's function method is shown and discussed., Comment: 28 pages, 18 figures. arXiv admin note: text overlap with arXiv:1412.0184

We introduce Teacher2Task, a novel framework for multi-teacher learning that eliminates the need for manual aggregation heuristics. Existing multi-teacher methods typically rely on such heuristics to combine predictions from multiple teachers, often resulting in sub-optimal aggregated labels and the propagation of aggregation errors. Teacher2Task addresses these limitations by introducing teacher-specific input tokens and reformulating the training process. Instead of relying on aggregated labels, the framework transforms the training data, consisting of ground truth labels and annotations from N teachers, into N+1 distinct tasks: N auxiliary tasks that predict the labeling styles of the N individual teachers, and one primary task that focuses on the ground truth labels. This approach, drawing upon principles from multiple learning paradigms, demonstrates strong empirical results across a range of architectures, modalities, and tasks.

We show that the set $\mathcal{T}_{3, \mathrm{sm}}^{\mathrm{can}}$ of smooth threefold canonical thresholds coincides with $\mathcal{T}_{2, \mathrm{sm}}^{\mathrm{lc}}=\mathcal{HT}_{2}$, where $\mathcal{HT}_{2}$ is the $2$-dimensional hypersurface log canonical thresholds characterized by Kuwata \cite{K99a, K99b}. We classify the set $\mathcal{T}_{3}^{\mathrm{can}}$ of threefold canonical thresholds. More precisely, we prove $\mathcal{T}_{3}^{\mathrm{can}}= \{0\} \cup \{\frac{4}{5}\} \cup \mathcal{T}_{3, \mathrm{sm}}^{\mathrm{can}}$., Comment: 26 pages, comments are welcome

Hyperedge prediction is crucial in hypergraph analysis for understanding complex multi-entity interactions in various web-based applications, including social networks and e-commerce systems. Traditional methods often face difficulties in generating high-quality negative samples due to the imbalance between positive and negative instances. To address this, we present the Scalable and Effective Negative Sample Generation for Hyperedge Prediction (SEHP) framework, which utilizes diffusion models to tackle these challenges. SEHP employs a boundary-aware loss function that iteratively refines negative samples, moving them closer to decision boundaries to improve classification performance. SEHP samples positive instances to form sub-hypergraphs for scalable batch processing. By using structural information from sub-hypergraphs as conditions within the diffusion process, SEHP effectively captures global patterns. To enhance efficiency, our approach operates directly in latent space, avoiding the need for discrete ID generation and resulting in significant speed improvements while preserving accuracy. Extensive experiments show that SEHP outperforms existing methods in accuracy, efficiency, and scalability, representing a substantial advancement in hyperedge prediction techniques. Our code is available here., Comment: 11

During surgical training, real-time feedback from trainers to trainees is important for preventing errors and enhancing long-term skill acquisition. Accurately predicting the effectiveness of this feedback, specifically whether it leads to a change in trainee behavior, is crucial for developing methods for improving surgical training and education. However, relying on human annotations to assess feedback effectiveness is laborious and prone to biases, underscoring the need for an automated, scalable, and objective method. Creating such an automated system poses challenges, as it requires an understanding of both the verbal feedback delivered by the trainer and the visual context of the real-time surgical scene. To address this, we propose a method that integrates information from transcribed verbal feedback and corresponding surgical video to predict feedback effectiveness. Our findings show that both transcribed feedback and surgical video are individually predictive of trainee behavior changes, and their combination achieves an AUROC of 0.70+/-0.02, improving prediction accuracy by up to 6.6%. Additionally, we introduce self-supervised fine-tuning as a strategy for enhancing surgical video representation learning, which is scalable and further enhances prediction performance. Our results demonstrate the potential of multi-modal learning to advance the automated assessment of surgical feedback., Comment: Accepted as a spotlight proceedings paper at Machine Learning for Health 2024

The rapid advancement of large language models (LLMs) and multimodal learning has transformed digital content creation and manipulation. Traditional visual editing tools require significant expertise, limiting accessibility. Recent strides in instruction-based editing have enabled intuitive interaction with visual content, using natural language as a bridge between user intent and complex editing operations. This survey provides an overview of these techniques, focusing on how LLMs and multimodal models empower users to achieve precise visual modifications without deep technical knowledge. By synthesizing over 100 publications, we explore methods from generative adversarial networks to diffusion models, examining multimodal integration for fine-grained content control. We discuss practical applications across domains such as fashion, 3D scene manipulation, and video synthesis, highlighting increased accessibility and alignment with human intuition. Our survey compares existing literature, emphasizing LLM-empowered editing, and identifies key challenges to stimulate further research. We aim to democratize powerful visual editing across various industries, from entertainment to education. Interested readers are encouraged to access our repository at https://github.com/tamlhp/awesome-instruction-editing., Comment: Fixed a serious error in author information

Audience feedback is crucial for refining video content, yet it typically comes after publication, limiting creators' ability to make timely adjustments. To bridge this gap, we introduce SimTube, a generative AI system designed to simulate audience feedback in the form of video comments before a video's release. SimTube features a computational pipeline that integrates multimodal data from the video-such as visuals, audio, and metadata-with user personas derived from a broad and diverse corpus of audience demographics, generating varied and contextually relevant feedback. Furthermore, the system's UI allows creators to explore and customize the simulated comments. Through a comprehensive evaluation-comprising quantitative analysis, crowd-sourced assessments, and qualitative user studies-we show that SimTube's generated comments are not only relevant, believable, and diverse but often more detailed and informative than actual audience comments, highlighting its potential to help creators refine their content before release.

Materials science datasets are inherently heterogeneous and are available in different modalities such as characterization spectra, atomic structures, microscopic images, and text-based synthesis conditions. The advancements in multi-modal learning, particularly in vision and language models, have opened new avenues for integrating data in different forms. In this work, we evaluate common techniques in multi-modal learning (alignment and fusion) in unifying some of the most important modalities in materials science: atomic structure, X-ray diffraction patterns (XRD), and composition. We show that structure graph modality can be enhanced by aligning with XRD patterns. Additionally, we show that aligning and fusing more experimentally accessible data formats, such as XRD patterns and compositions, can create more robust joint embeddings than individual modalities across various tasks. This lays the groundwork for future studies aiming to exploit the full potential of multi-modal data in materials science, facilitating more informed decision-making in materials design and discovery.

This paper presents a scheduling algorithm that divides a manufacturing/warehouse floor into zones that an Autonomous Mobile Robot (AMR) will occupy and complete part pick-up and drop-off tasks. Each zone is balanced so that each AMR will share each task equally. These zones change over time to accommodate fluctuations in production and to avoid overloading an AMR with tasks. A decentralized dynamic zoning (DDZ) algorithm is introduced to find the optimal zone design, eliminating the possibility of single-point failure from a centralized unit. Then a simulation is built comparing the adaptability of DDZ and other dynamic zoning algorithms from previous works. Initial results show that DDZ has a much lower throughput than other dynamic zoning algorithms but DDZ can achieve a better distribution of tasks. Initial results show that DDZ had a lower standard deviation of AMR total travel distance which was 2874.7 feet less than previous works. This 68.7\% decrease in standard deviation suggests that AMRs under DDZ travel a similar distance during production. This could be useful for real-world applications by making it easier to design charging and maintenance schedules without much downtime. Video demonstration of the system working can be seen here: \url{https://youtu.be/yVi026oVD7U}, Comment: 11 pages, 5 figures, submitted to Scientific Reports special edition Robotics and Automation in Advanced Manufacturing

This technical report presents our initial attempt to build a spoken large language model (LLM) for Taiwanese Mandarin, specifically tailored to enable real-time, speech-to-speech interaction in multi-turn conversations. Our end-to-end model incorporates a decoder-only transformer architecture and aims to achieve seamless interaction while preserving the conversational flow, including full-duplex capabilities allowing simultaneous speaking and listening. The paper also details the training process, including data preparation with synthesized dialogues and adjustments for real-time interaction. We also developed a platform to evaluate conversational fluency and response coherence in multi-turn dialogues. We hope the release of the report can contribute to the future development of spoken LLMs in Taiwanese Mandarin., Comment: Work in progress

In this paper, we address the quantitative regularity and blow-up criteria for classical solutions to the three-dimensional incompressible Navier-Stokes equations in a critical Besov space setting. Specifically, we consider solutions $u\in L^\infty_T(\dot{B}_{p,\infty}^{-1+\frac{3}{p}})$ such that $|D|^{-1+\frac{3}{p}}|u|\in L^\infty_t (L_x^p)$ with $3

Large Language Models (LLMs), with gradually improving reading comprehension and reasoning capabilities, are being applied to a range of complex language tasks, including the automatic generation of language data for various purposes. However, research on applying LLMs for automatic data generation in low-resource languages like Vietnamese is still underdeveloped and lacks comprehensive evaluation. In this paper, we explore the use of LLMs for automatic data generation for the Vietnamese fact-checking task, which faces significant data limitations. Specifically, we focus on fact-checking data where claims are synthesized from multiple evidence sentences to assess the information synthesis capabilities of LLMs. We develop an automatic data construction process using simple prompt techniques on LLMs and explore several methods to improve the quality of the generated data. To evaluate the quality of the data generated by LLMs, we conduct both manual quality assessments and performance evaluations using language models. Experimental results and manual evaluations illustrate that while the quality of the generated data has significantly improved through fine-tuning techniques, LLMs still cannot match the data quality produced by humans.

Game solving is the process of finding the theoretical outcome for a game, assuming that all player choices are optimal. This paper focuses on a technique that can reduce the heuristic search space significantly for 7x7 Killall-Go. In Go and Killall-Go, live patterns are stones that are protected from opponent capture. Mutual life, also referred to as seki, is when both players' stones achieve life by sharing liberties with their opponent. Whichever player attempts to capture the opponent first will leave their own stones vulnerable. Therefore, it is critical to recognize seki patterns to avoid putting oneself in jeopardy. Recognizing seki can reduce the search depth significantly. In this paper, we enumerate all seki patterns up to a predetermined area size, then store these patterns into a seki table. This allows us to recognize seki during search, which significantly improves solving efficiency for the game of Killall-Go. Experiments show that a day-long, unsolvable position can be solved in 482 seconds with the addition of a seki table. For general positions, a 10% to 20% improvement in wall clock time and node count is observed., Comment: Accepted by the Computers and Games conference (CG 2024)

Let $E$ be a subset in $\mathbb{F}_p^2$ and $S$ be a subset in the special linear group $SL_2(\mathbb{F}_p)$ or the $1$-dimensional Heisenberg linear group $\mathbb{H}_1(\mathbb{F}_p)$. We define $S(E):= \bigcup_{\theta \in S} \theta (E)$. In this paper, we provide optimal conditions on $S$ and $E$ such that the set $S(E)$ covers a positive proportion of all elements in the plane $\mathbb{F}_p$. When the sizes of $S$ and $E$ are small, we prove structural theorems that guarantee that $|S(E)|\gg |E|^{1+\epsilon}$ for some $\epsilon>0$. The main ingredients in our proofs are novel results on algebraic incidence-type structures associated with the groups, in which energy estimates play a crucial role. The higher-dimensional version will also be discussed in this paper., Comment: 34 pages

Multimodal foundation models, such as Gemini and ChatGPT, have revolutionized human-machine interactions by seamlessly integrating various forms of data. Developing a universal spoken language model that comprehends a wide range of natural language instructions is critical for bridging communication gaps and facilitating more intuitive interactions. However, the absence of a comprehensive evaluation benchmark poses a significant challenge. We present Dynamic-SUPERB Phase-2, an open and evolving benchmark for the comprehensive evaluation of instruction-based universal speech models. Building upon the first generation, this second version incorporates 125 new tasks contributed collaboratively by the global research community, expanding the benchmark to a total of 180 tasks, making it the largest benchmark for speech and audio evaluation. While the first generation of Dynamic-SUPERB was limited to classification tasks, Dynamic-SUPERB Phase-2 broadens its evaluation capabilities by introducing a wide array of novel and diverse tasks, including regression and sequence generation, across speech, music, and environmental audio. Evaluation results indicate that none of the models performed well universally. SALMONN-13B excelled in English ASR, while WavLLM demonstrated high accuracy in emotion recognition, but current models still require further innovations to handle a broader range of tasks. We will soon open-source all task data and the evaluation pipeline.

MuZero has achieved superhuman performance in various games by using a dynamics network to predict environment dynamics for planning, without relying on simulators. However, the latent states learned by the dynamics network make its planning process opaque. This paper aims to demystify MuZero's model by interpreting the learned latent states. We incorporate observation reconstruction and state consistency into MuZero training and conduct an in-depth analysis to evaluate latent states across two board games: 9x9 Go and Outer-Open Gomoku, and three Atari games: Breakout, Ms. Pacman, and Pong. Our findings reveal that while the dynamics network becomes less accurate over longer simulations, MuZero still performs effectively by using planning to correct errors. Our experiments also show that the dynamics network learns better latent states in board games than in Atari games. These insights contribute to a better understanding of MuZero and offer directions for future research to improve the playing performance, robustness, and interpretability of the MuZero algorithm., Comment: Accepted by the 29th International Conference on Technologies and Applications of Artificial Intelligence (TAAI 2024)

Visual inspections of bridges are critical to ensure their safety and identify potential failures early. This inspection process can be rapidly and accurately automated by using unmanned aerial vehicles (UAVs) integrated with deep learning models. However, choosing an appropriate model that is lightweight enough to integrate into the UAV and fulfills the strict requirements for inference time and accuracy is challenging. Therefore, our work contributes to the advancement of this model selection process by conducting a benchmark of 23 models belonging to the four newest YOLO variants (YOLOv5, YOLOv6, YOLOv7, YOLOv8) on COCO-Bridge-2021+, a dataset for bridge details detection. Through comprehensive benchmarking, we identify YOLOv8n, YOLOv7tiny, YOLOv6m, and YOLOv6m6 as the models offering an optimal balance between accuracy and processing speed, with mAP@50 scores of 0.803, 0.837, 0.853, and 0.872, and inference times of 5.3ms, 7.5ms, 14.06ms, and 39.33ms, respectively. Our findings accelerate the model selection process for UAVs, enabling more efficient and reliable bridge inspections.

Determining the difficulty of a text involves assessing various textual features that may impact the reader's text comprehension, yet current research in Vietnamese has only focused on statistical features. This paper introduces a new approach that integrates statistical and semantic approaches to assessing text readability. Our research utilized three distinct datasets: the Vietnamese Text Readability Dataset (ViRead), OneStopEnglish, and RACE, with the latter two translated into Vietnamese. Advanced semantic analysis methods were employed for the semantic aspect using state-of-the-art language models such as PhoBERT, ViDeBERTa, and ViBERT. In addition, statistical methods were incorporated to extract syntactic and lexical features of the text. We conducted experiments using various machine learning models, including Support Vector Machine (SVM), Random Forest, and Extra Trees and evaluated their performance using accuracy and F1 score metrics. Our results indicate that a joint approach that combines semantic and statistical features significantly enhances the accuracy of readability classification compared to using each method in isolation. The current study emphasizes the importance of considering both statistical and semantic aspects for a more accurate assessment of text difficulty in Vietnamese. This contribution to the field provides insights into the adaptability of advanced language models in the context of Vietnamese text readability. It lays the groundwork for future research in this area.

Many nations are promoting the green transition in the energy sector to attain neutral carbon emissions by 2050. Smart Grid 2.0 (SG2) is expected to explore data-driven analytics and enhance communication technologies to improve the efficiency and sustainability of distributed renewable energy systems. These features are beyond smart metering and electric surplus distribution in conventional smart grids. Given the high dependence on communication networks to connect distributed microgrids in SG2, potential cascading failures of connectivity can cause disruption to data synchronization to the remote control systems. This paper reviews security threats and defense tactics for three stakeholders: power grid operators, communication network providers, and consumers. Through the survey, we found that SG2's stakeholders are particularly vulnerable to substation attacks/vandalism, malware/ransomware threats, blockchain vulnerabilities and supply chain breakdowns. Furthermore, incorporating artificial intelligence (AI) into autonomous energy management in distributed energy resources of SG2 creates new challenges. Accordingly, adversarial samples and false data injection on electricity reading and measurement sensors at power plants can fool AI-powered control functions and cause messy error-checking operations in energy storage, wrong energy estimation in electric vehicle charging, and even fraudulent transactions in peer-to-peer energy trading models. Scalable blockchain-based models, physical unclonable function, interoperable security protocols, and trustworthy AI models designed for managing distributed microgrids in SG2 are typical promising protection models for future research., Comment: 30 pages, 21 figures, 5 tables, accepted to appear in IEEE COMST

Pre-trained on massive amounts of code and text data, large language models (LLMs) have demonstrated remarkable achievements in performing code generation tasks. With additional execution-based feedback, these models can act as agents with capabilities to self-refine and improve generated code autonomously. However, on challenging coding tasks with extremely large search space, current agentic approaches still struggle with multi-stage planning, generating, and debugging. To address this problem, we propose CodeTree, a framework for LLM agents to efficiently explore the search space in different stages of the code generation process. Specifically, we adopted a unified tree structure to explicitly explore different coding strategies, generate corresponding coding solutions, and subsequently refine the solutions. In each stage, critical decision-making (ranking, termination, expanding) of the exploration process is guided by both the environmental execution-based feedback and LLM-agent-generated feedback. We comprehensively evaluated CodeTree on 7 code generation benchmarks and demonstrated the significant performance gains of CodeTree against strong baselines. Using GPT-4o as the base model, we consistently achieved top results of 95.1 on HumanEval, 98.7 on MBPP, and 43.0 on CodeContests. On the challenging SWEBench benchmark, our approach led to significant performance gains.

Interacting with human agents in complex scenarios presents a significant challenge for robotic navigation, particularly in environments that necessitate both collision avoidance and collaborative interaction, such as indoor spaces. Unlike static or predictably moving obstacles, human behavior is inherently complex and unpredictable, stemming from dynamic interactions with other agents. Existing simulation tools frequently fail to adequately model such reactive and collaborative behaviors, impeding the development and evaluation of robust social navigation strategies. This paper introduces a novel framework utilizing distributed potential games to simulate human-like interactions in highly interactive scenarios. Within this framework, each agent imagines a virtual cooperative game with others based on its estimation. We demonstrate this formulation can facilitate the generation of diverse and realistic interaction patterns in a configurable manner across various scenarios. Additionally, we have developed a gym-like environment leveraging our interactive agent model to facilitate the learning and evaluation of interactive navigation algorithms., Comment: 13 pages, 10 figures. arXiv admin note: substantial text overlap with arXiv:2310.01614

Large language models (LLMs) have shown remarkable progress in encoding clinical knowledge and responding to complex medical queries with appropriate clinical reasoning. However, their applicability in subspecialist or complex medical settings remains underexplored. In this work, we probe the performance of AMIE, a research conversational diagnostic AI system, in the subspecialist domain of breast oncology care without specific fine-tuning to this challenging domain. To perform this evaluation, we curated a set of 50 synthetic breast cancer vignettes representing a range of treatment-naive and treatment-refractory cases and mirroring the key information available to a multidisciplinary tumor board for decision-making (openly released with this work). We developed a detailed clinical rubric for evaluating management plans, including axes such as the quality of case summarization, safety of the proposed care plan, and recommendations for chemotherapy, radiotherapy, surgery and hormonal therapy. To improve performance, we enhanced AMIE with the inference-time ability to perform web search retrieval to gather relevant and up-to-date clinical knowledge and refine its responses with a multi-stage self-critique pipeline. We compare response quality of AMIE with internal medicine trainees, oncology fellows, and general oncology attendings under both automated and specialist clinician evaluations. In our evaluations, AMIE outperformed trainees and fellows demonstrating the potential of the system in this challenging and important domain. We further demonstrate through qualitative examples, how systems such as AMIE might facilitate conversational interactions to assist clinicians in their decision making. However, AMIE's performance was overall inferior to attending oncologists suggesting that further research is needed prior to consideration of prospective uses.

Direct Z-scheme heterostructures with enhanced redox potential are increasingly regarded as promising materials for solar-driven water splitting. This potential arises from the synergistic interaction between the intrinsic dipoles in Janus materials and the interfacial electric fields across the layers. In this study, we explore the photocatalytic potential of 20 two-dimensional (2D) Janus transition metal dichalcogenide (TMDC) heterobilayers for efficient water splitting. Utilizing density functional theory (DFT) calculations, we first screen these materials based on key properties such as band gaps and the magnitude of intrinsic electric fields to identify promising candidates. We then evaluate additional critical factors, including carrier mobility and surface chemical reactions, to fully assess their performance. The intrinsic dipole moments in Janus materials generate built-in electric fields that enhance charge separation and reduce carrier recombination, thereby improving photocatalytic efficiency. Furthermore, we employ the Fr\"{o}hlich interaction model to quantify the mobility contributions from the longitudinal optical phonon mode, providing detailed insights into how carrier mobility, influenced by phonon scattering, affects photocatalytic performance. Our results reveal that several Janus-TMDC heterobilayers, including WSe$_2$-SWSe, WSe$_2$-TeWSe, and WS$_2$-SMoSe, exhibit strong absorption in the visible spectrum and achieve solar-to-hydrogen (STH) conversion efficiencies of up to 33.24%. These findings demonstrate the potential of Janus-based Z-scheme systems to overcome existing limitations in photocatalytic water splitting by optimizing the electronic and structural properties of 2D materials. This research highlights a viable pathway for advancing clean energy generation through enhanced photocatalytic processes., Comment: 30 pages, 6 figures, 4 tables

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

While textless Spoken Language Models (SLMs) have shown potential in end-to-end speech-to-speech modeling, they still lag behind text-based Large Language Models (LLMs) in terms of semantic coherence and relevance. This work introduces the Align-SLM framework, which leverages preference optimization inspired by Reinforcement Learning with AI Feedback (RLAIF) to enhance the semantic understanding of SLMs. Our approach generates multiple speech continuations from a given prompt and uses semantic metrics to create preference data for Direct Preference Optimization (DPO). We evaluate the framework using ZeroSpeech 2021 benchmarks for lexical and syntactic modeling, the spoken version of the StoryCloze dataset for semantic coherence, and other speech generation metrics, including the GPT4-o score and human evaluation. Experimental results show that our method achieves state-of-the-art performance for SLMs on most benchmarks, highlighting the importance of preference optimization to improve the semantics of SLMs.

We study a class of semi-linear differential Volterra equations with polynomial-type potentials that incorporates the effects of memory while being subjected to random perturbations via an additive Gaussian noise. We show that for a broad class of non-linear potentials, the system always admits invariant probability measures. However, the presence of memory effects precludes access to compactness in a typical fashion. In this paper, this obstacle is overcome by introducing functional spaces adapted to the memory kernels, thereby allowing one to recover compactness. Under the assumption of sufficiently smooth noise, it is then shown that the statistically stationary states possess higher-order regularity properties dictated by the structure of the nonlinearity. This is established through a control argument that asymptotically transfers regularity onto the solution by exploiting the underlying Lyapunov structure of the system in a novel way., Comment: arXiv admin note: substantial text overlap with arXiv:2212.05646

In this paper, we establish local well-posedness results for the Muskat equation in any dimension using modulus of continuity techniques. By introducing a novel quantity \(\beta_\sigma(f_0')\) which encapsulates local monotonicity and slope, we identify a new class of initial data within \(W^{1,\infty}(\mathbb{R}^d)\). This includes scenarios where the product of the maximal and minimal slopes is large, thereby guaranteeing the local existence of a classical solution., Comment: 38 pages, 1 figure

This work proposes a novel degradation-infused energy portfolio allocation (DI-EPA) framework for enabling the participation of battery energy storage systems in multi-service electricity markets. The proposed framework attempts to address the challenge of including the rainflow algorithm for cycle counting by directly developing a closed-form of marginal degradation as a function of dispatch decisions. Further, this closed-form degradation profile is embedded into an energy portfolio allocation (EPA) problem designed for making the optimal dispatch decisions for all the batteries together, in a shared economy manner. We term the entity taking these decisions as `facilitator' which works as a link between storage units and market operators. The proposed EPA formulation is quipped with a conditional-value-at-risk (CVaR)-based mechanism to bring risk-averseness against uncertainty in market prices. The proposed DI-EPA problem introduces fairness by dividing the profits into various units using the idea of marginal contribution. Simulation results regarding the accuracy of the closed-form of degradation, effectiveness of CVaR in handling uncertainty within the EPA problem, and fairness in the context of degradation awareness are discussed. Numerical results indicate that the DI-EPA framework improves the net profit of the storage units by considering the effect of degradation in optimal market participation.

Recent work has demonstrated that a promising strategy for teaching robots a wide range of complex skills is by training them on a curriculum of progressively more challenging environments. However, developing an effective curriculum of environment distributions currently requires significant expertise, which must be repeated for every new domain. Our key insight is that environments are often naturally represented as code. Thus, we probe whether effective environment curriculum design can be achieved and automated via code generation by large language models (LLM). In this paper, we introduce Eurekaverse, an unsupervised environment design algorithm that uses LLMs to sample progressively more challenging, diverse, and learnable environments for skill training. We validate Eurekaverse's effectiveness in the domain of quadrupedal parkour learning, in which a quadruped robot must traverse through a variety of obstacle courses. The automatic curriculum designed by Eurekaverse enables gradual learning of complex parkour skills in simulation and can successfully transfer to the real-world, outperforming manual training courses designed by humans., Comment: Conference on Robot Learning (CoRL), 2024. Project website and code: https://eureka-research.github.io/eurekaverse

We present a lattice-QCD calculation of the long-distance two-photon contribution to the decay amplitude of a long-lived kaon to a pair of muons on a $24^3\times 64$ physical-pion-mass ensemble. In these proceedings, the theoretical foundation of this calculation will be reviewed and preliminary numerical results will be presented for all diagrams with the exception of those that are quark-line disconnected SU(3)-flavor-suppressed. At this stage, the intermediate $\eta$ contribution appears to be the largest source of statistical uncertainty. Our proposed strategies to reduce these statistical errors are discussed in great detail., Comment: 11 pages, 6 figures, contribution to the 41st International Symposium on Lattice Field Theory, Lattice 2024, Liverpool, UK

Large Language Models (LLMs) have revolutionized various domains but remain vulnerable to prompt injection attacks, where malicious inputs manipulate the model into ignoring original instructions and executing designated action. In this paper, we investigate the underlying mechanisms of these attacks by analyzing the attention patterns within LLMs. We introduce the concept of the distraction effect, where specific attention heads, termed important heads, shift focus from the original instruction to the injected instruction. Building on this discovery, we propose Attention Tracker, a training-free detection method that tracks attention patterns on instruction to detect prompt injection attacks without the need for additional LLM inference. Our method generalizes effectively across diverse models, datasets, and attack types, showing an AUROC improvement of up to 10.0% over existing methods, and performs well even on small LLMs. We demonstrate the robustness of our approach through extensive evaluations and provide insights into safeguarding LLM-integrated systems from prompt injection vulnerabilities., Comment: Project page: https://huggingface.co/spaces/TrustSafeAI/Attention-Tracker

Background: Breast density, as derived from mammographic images and defined by the American College of Radiology's Breast Imaging Reporting and Data System (BI-RADS), is one of the strongest risk factors for breast cancer. Breast ultrasound (BUS) is an alternative breast cancer screening modality, particularly useful for early detection in low-resource, rural contexts. The purpose of this study was to explore an artificial intelligence (AI) model to predict BI-RADS mammographic breast density category from clinical, handheld BUS imaging. Methods: All data are sourced from the Hawaii and Pacific Islands Mammography Registry. We compared deep learning methods from BUS imaging, as well as machine learning models from image statistics alone. The use of AI-derived BUS density as a risk factor for breast cancer was then compared to clinical BI-RADS breast density while adjusting for age. The BUS data were split by individual into 70/20/10% groups for training, validation, and testing. Results: 405,120 clinical BUS images from 14.066 women were selected for inclusion in this study, resulting in 9.846 women for training (302,574 images), 2,813 for validation (11,223 images), and 1,406 for testing (4,042 images). On the held-out testing set, the strongest AI model achieves AUROC 0.854 predicting BI-RADS mammographic breast density from BUS imaging and outperforms all shallow machine learning methods based on image statistics. In cancer risk prediction, age-adjusted AI BUS breast density predicted 5-year breast cancer risk with 0.633 AUROC, as compared to 0.637 AUROC from age-adjusted clinical breast density. Conclusions: BI-RADS mammographic breast density can be estimated from BUS imaging with high accuracy using a deep learning model. Furthermore, we demonstrate that AI-derived BUS breast density is predictive of 5-year breast cancer risk in our population.

The orbital Hall effect (OHE) is attracting recent interest due to its fundamental science implications and potential applications in orbitronics and spintronics. Unlike the spin Hall effect, the connection between the OHE and band topology is not well understood. Here we present a novel approach for understanding the OHE based on analyzing the projected orbital angular momentum (POAM) spectrum. By considering monolayers of group IV elements, we demonstrate that the Wannier charge centers of the POAM spectrum display topologically nontrivial windings. The orbital Hall conductivity is found to form a plateau within the band gap as a direct consequence of the Chern number carried by the POAM spectrum. The topological orbital Hall phase is shown to yield a new form of bulk-boundary correspondence, which features gapless states in the POAM spectrum and induces nonzero orbital textures at the boundaries that should be amenable to experimental verification through ARPES measurements. Our study presents a systematic method for investigating the topological OHE and provides a pathway for its broader exploration in two-dimensional materials.

Cohen-Addad, Le, Pilipczuk, and Pilipczuk [CLPP23] recently constructed a stochastic embedding with expected $1+\varepsilon$ distortion of $n$-vertex planar graphs (with polynomial aspect ratio) into graphs of treewidth $O(\varepsilon^{-1}\log^{13} n)$. Their embedding is the first to achieve polylogarithmic treewidth. However, there remains a large gap between the treewidth of their embedding and the treewidth lower bound of $\Omega(\log n)$ shown by Carroll and Goel [CG04]. In this work, we substantially narrow the gap by constructing a stochastic embedding with treewidth $O(\varepsilon^{-1}\log^{3} n)$. We obtain our embedding by improving various steps in the CLPP construction. First, we streamline their embedding construction by showing that one can construct a low-treewidth embedding for any graph from (i) a stochastic hierarchy of clusters and (ii) a stochastic balanced cut. We shave off some logarithmic factors in this step by using a single hierarchy of clusters. Next, we construct a stochastic hierarchy of clusters with optimal separating probability and hop bound based on shortcut partition [CCLMST23, CCLMST24]. Finally, we construct a stochastic balanced cut with an improved trade-off between the cut size and the number of cuts. This is done by a new analysis of the contraction sequence introduced by [CLPP23]; our analysis gives an optimal treewidth bound for graphs admitting a contraction sequence., Comment: 39 pages, 6 figures

We develop a technique to design efficiently computable estimators for sparse linear regression in the simultaneous presence of two adversaries: oblivious and adaptive. We design several robust algorithms that outperform the state of the art even in the special case when oblivious adversary simply adds Gaussian noise. In particular, we provide a polynomial-time algorithm that with high probability recovers the signal up to error $O(\sqrt{\varepsilon})$ as long as the number of samples $n \ge \tilde{O}(k^2/\varepsilon)$, only assuming some bounds on the third and the fourth moments of the distribution ${D}$ of the design. In addition, prior to this work, even in the special case of Gaussian design and noise, no polynomial time algorithm was known to achieve error $o(\sqrt{\varepsilon})$ in the sparse setting $n < d^2$. We show that under some assumptions on the fourth and the eighth moments of ${D}$, there is a polynomial-time algorithm that achieves error $o(\sqrt{\varepsilon})$ as long as $n \ge \tilde{O}(k^4 / \varepsilon^3)$. For Gaussian distribution, this algorithm achieves error $O(\varepsilon^{3/4})$. Moreover, our algorithm achieves error $o(\sqrt{\varepsilon})$ for all log-concave distributions if $\varepsilon \le 1/\text{polylog(d)}$. Our algorithms are based on the filtering of the covariates that uses sum-of-squares relaxations, and weighted Huber loss minimization with $\ell_1$ regularizer. We provide a novel analysis of weighted penalized Huber loss that is suitable for heavy-tailed designs in the presence of two adversaries. Furthermore, we complement our algorithmic results with Statistical Query lower bounds, providing evidence that our estimators are likely to have nearly optimal sample complexity., Comment: NeurIPS 2024; Authors have equal contribution

We introduce Dynamic Information Sub-Selection (DISS), a novel framework of AI assistance designed to enhance the performance of black-box decision-makers by tailoring their information processing on a per-instance basis. Blackbox decision-makers (e.g., humans or real-time systems) often face challenges in processing all possible information at hand (e.g., due to cognitive biases or resource constraints), which can degrade decision efficacy. DISS addresses these challenges through policies that dynamically select the most effective features and options to forward to the black-box decision-maker for prediction. We develop a scalable frequentist data acquisition strategy and a decision-maker mimicking technique for enhanced budget efficiency. We explore several impactful applications of DISS, including biased decision-maker support, expert assignment optimization, large language model decision support, and interpretability. Empirical validation of our proposed DISS methodology shows superior performance to state-of-the-art methods across various applications.