Search

Discovering new solid-state materials requires rapidly exploring the vast space of crystal structures and locating stable regions. Generating stable materials with desired properties and compositions is extremely difficult as we search for very small isolated pockets in the exponentially many possibilities, considering elements from the periodic table and their 3D arrangements in crystal lattices. Materials discovery necessitates both optimized solution structures and diversity in the generated material structures. Existing methods struggle to explore large material spaces and generate diverse samples with desired properties and requirements. We propose the Symmetry-aware Hierarchical Architecture for Flow-based Traversal (SHAFT), a novel generative model employing a hierarchical exploration strategy to efficiently exploit the symmetry of the materials space to generate crystal structures given desired properties. In particular, our model decomposes the exponentially large materials space into a hierarchy of subspaces consisting of symmetric space groups, lattice parameters, and atoms. We demonstrate that SHAFT significantly outperforms state-of-the-art iterative generative methods, such as Generative Flow Networks (GFlowNets) and Crystal Diffusion Variational AutoEncoders (CDVAE), in crystal structure generation tasks, achieving higher validity, diversity, and stability of generated structures optimized for target properties and requirements.

This paper concerns the numerical approximation for the invariant distribution of Markovian switching L\'evy-driven stochastic differential equations. By combining the tamed-adaptive Euler-Maruyama scheme with the Multi-level Monte Carlo method, we propose an approximation scheme that can be applied to stochastic differential equations with super-linear growth drift and diffusion coefficients.

The Privacy Preserving Federated Learning Document VQA (PFL-DocVQA) competition challenged the community to develop provably private and communication-efficient solutions in a federated setting for a real-life use case: invoice processing. The competition introduced a dataset of real invoice documents, along with associated questions and answers requiring information extraction and reasoning over the document images. Thereby, it brings together researchers and expertise from the document analysis, privacy, and federated learning communities. Participants fine-tuned a pre-trained, state-of-the-art Document Visual Question Answering model provided by the organizers for this new domain, mimicking a typical federated invoice processing setup. The base model is a multi-modal generative language model, and sensitive information could be exposed through either the visual or textual input modality. Participants proposed elegant solutions to reduce communication costs while maintaining a minimum utility threshold in track 1 and to protect all information from each document provider using differential privacy in track 2. The competition served as a new testbed for developing and testing private federated learning methods, simultaneously raising awareness about privacy within the document image analysis and recognition community. Ultimately, the competition analysis provides best practices and recommendations for successfully running privacy-focused federated learning challenges in the future., Comment: 27 pages, 6 figures

Neutrino-nucleus cross section measurements are needed to improve interaction modeling to meet the precision needs of neutrino experiments in efforts to measure oscillation parameters and search for physics beyond the Standard Model. We review the difficulties associated with modeling neutrino-nucleus interactions that lead to a dependence on event generators in oscillation analyses and cross section measurements alike. We then describe data-driven model validation techniques intended to address this model dependence. The method relies on utilizing various goodness-of-fit tests and the correlations between different observables and channels to probe the model for defects in the phase space relevant for the desired analysis. These techniques shed light on relevant mis-modeling, allowing it to be detected before it begins to bias the cross section results. We compare more commonly used model validation methods which directly validate the model against alternative ones to these data-driven techniques and show their efficacy with fake data studies. These studies demonstrate that employing data-driven model validation in cross section measurements represents a reliable strategy to produce robust results that will stimulate the desired improvements to interaction modeling.

Federated Learning (FL) offers a promising solution to the privacy concerns associated with centralized Machine Learning (ML) by enabling decentralized, collaborative learning. However, FL is vulnerable to various security threats, including poisoning attacks, where adversarial clients manipulate the training data or model updates to degrade overall model performance. Recognizing this threat, researchers have focused on developing defense mechanisms to counteract poisoning attacks in FL systems. However, existing robust FL methods predominantly focus on computer vision tasks, leaving a gap in addressing the unique challenges of FL with time series data. In this paper, we present FLORAL, a defense mechanism designed to mitigate poisoning attacks in federated learning for time-series tasks, even in scenarios with heterogeneous client data and a large number of adversarial participants. Unlike traditional model-centric defenses, FLORAL leverages logical reasoning to evaluate client trustworthiness by aligning their predictions with global time-series patterns, rather than relying solely on the similarity of client updates. Our approach extracts logical reasoning properties from clients, then hierarchically infers global properties, and uses these to verify client updates. Through formal logic verification, we assess the robustness of each client contribution, identifying deviations indicative of adversarial behavior. Experimental results on two datasets demonstrate the superior performance of our approach compared to existing baseline methods, highlighting its potential to enhance the robustness of FL to time series applications. Notably, FLORAL reduced the prediction error by 93.27% in the best-case scenario compared to the second-best baseline. Our code is available at https://anonymous.4open.science/r/FLORAL-Robust-FTS., Comment: 12 pages, 4 figures, 6 tables

This paper proposes a distributed learning-based framework to tackle the sum ergodic rate maximization problem in cell-free massive multiple-input multiple-output (MIMO) systems by utilizing the graph neural network (GNN). Different from centralized schemes, which gather all the channel state information (CSI) at the central processing unit (CPU) for calculating the resource allocation, the local resource of access points (APs) is exploited in the proposed distributed GNN-based framework to allocate transmit powers. Specifically, APs can use a unique GNN model to allocate their power based on the local CSI. The GNN model is trained at the CPU using the local CSI of one AP, with partially exchanged information from other APs to calculate the loss function to reflect system characteristics, capturing comprehensive network information while avoiding computation burden. Numerical results show that the proposed distributed learning-based approach achieves a sum ergodic rate close to that of centralized learning while outperforming the model-based optimization., Comment: 6 pages, 4 figures, and 4 tables. Accepted by IEEE TVT

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

In a model of fault-tolerant quantum computation with quick and noiseless polyloglog-time auxiliary classical computation, we construct a fault tolerance protocol with constant-space and $\widetilde{O}(\log N)$-time overhead, where $\widetilde{O}(\cdot)$ hides sub-polylog factors. Our construction utilizes constant-rate quantum locally testable codes (qLTC), new fault-tolerant gadgets on qLTCs and qLDPC codes, and a new analysis framework. In particular, 1) we develop a new simple and self-contained construction of magic state distillation for qubits using qudit quantum Reed-Solomon codes with $(\log \frac{1}{\varepsilon})^{\gamma}$ spacetime overhead, where $\gamma \rightarrow 0$. 2) We prove that the recent family of almost-good qLTCs of Dinur-Lin-Vidick admit parallel single-shot decoders against adversarial errors of weight scaling with the code distance. 3) We develop logical state preparation and logical gate procedures with $\widetilde{O}(1)$-spacetime overhead on qLTCs. 4) To combine these ingredients, we introduce a new framework of fault tolerance analysis called the weight enumerator formalism. The framework permits easy formal composition of fault-tolerant gadgets, so we expect it to be of independent interest. Our work gives the lowest spacetime overhead to date, which, for the first time, matches that of classical fault tolerance up to sub-polylog factors. We conjecture this is optimal up to sub-polylog factors.

Examples of algebraic surfaces of general type with maximal Picard number are not abundant in the literature. Moreover, most known examples either possess low invariants, lie near the Noether line $K^2=2\chi-6$ or are somewhat scattered. A notable exception is Persson's sequence of double covers of the projective plane with maximal Picard number, whose invariants converge to the Severi line $K^2=4\chi$. This note is devoted to the construction of infinitely many new sequences of surfaces of general type with maximal Picard number whose invariants converge to the Severi line., Comment: 12 pages, comments are welcome. arXiv admin note: text overlap with arXiv:2306.15241

Multilingual LLMs have achieved remarkable benchmark performance, but we find they continue to underperform on non-Latin script languages across contemporary LLM families. This discrepancy arises from the fact that LLMs are pretrained with orthographic scripts, which are dominated by Latin characters that obscure their shared phonology with non-Latin scripts. We propose leveraging phonemic transcriptions as complementary signals to induce script-invariant representations. Our study demonstrates that integrating phonemic signals improves performance across both non-Latin and Latin languages, with a particularly significant impact on closing the performance gap between the two. Through detailed experiments, we show that phonemic and orthographic scripts retrieve distinct examples for in-context learning (ICL). This motivates our proposed Mixed-ICL retrieval strategy, where further aggregation leads to our significant performance improvements for both Latin script languages (up to 12.6%) and non-Latin script languages (up to 15.1%) compared to randomized ICL retrieval.

When learning an input-output mapping from very few examples, is it better to first infer a latent function that explains the examples, or is it better to directly predict new test outputs, e.g. using a neural network? We study this question on ARC, a highly diverse dataset of abstract reasoning tasks. We train neural models for induction (inferring latent functions) and transduction (directly predicting the test output for a given test input). Our models are trained on synthetic data generated by prompting LLMs to produce Python code specifying a function to be inferred, plus a stochastic subroutine for generating inputs to that function. We find inductive and transductive models solve very different problems, despite training on the same problems, and despite sharing the same neural architecture.

We present 850 $\mu$m polarization observations of the IC 348 star-forming region in the Perseus molecular cloud as part of the B-fields In STar-forming Region Observation (BISTRO) survey. We study the magnetic properties of two cores (HH 211 MMS and IC 348 MMS) and a filamentary structure of IC 348. We find that the overall field tends to be more perpendicular than parallel to the filamentary structure of the region. The polarization fraction decreases with intensity, and we estimate the trend by power-law and the mean of the Rice distribution fittings. The power indices for the cores are much smaller than 1, indicative of possible grain growth to micron size in the cores. We also measure the magnetic field strengths of the two cores and the filamentary area separately by applying the Davis-Chandrasekhar-Fermi method and its alternative version for compressed medium. The estimated mass-to-flux ratios are 0.45-2.20 and 0.63-2.76 for HH 211 MMS and IC 348 MMS, respectively, while the ratios for the filament is 0.33-1.50. This result may suggest that the transition from subcritical to supercritical conditions occurs at the core scale ($\sim$ 0.05 pc) in the region. In addition, we study the energy balance of the cores and find that the relative strength of turbulence to the magnetic field tends to be stronger for IC 348 MMS than HH 211 MMS. The result could potentially explain the different configurations inside the two cores: a single protostellar system in HH 211 MMS and multiple protostars in IC 348 MMS., Comment: Accepted for publication in ApJ. 21 pages, 12 figures

This paper considers a class of thrust vectoring systems, which are nonlinear, overactuated, and time-invariant. We assume that the system is composed of two subsystems and there exist singular points around which the linearized system is uncontrollable. Furthermore, we assume that the system is stabilizable through a two-level control allocation. In this particular setting, we cannot do much with the linearized system, and a direct nonlinear control approach must be used to analyze the system stability. Under adequate assumptions and a suitable nonlinear continuous control-allocation law, we can prove uniform asymptotic convergence of the points of equilibrium using Lyapunov input-to-state stability and the small gain theorem. This control allocation, however, requires the design of an allocated mapping and introduces two exogenous inputs. In particular, the closed-loop system is cascaded, and the output of one subsystem is the disturbance of the other, and vice versa. In general, it is difficult to find a closed-form solution for the allocated mapping; it needs to satisfy restrictive conditions, among which Lipschitz continuity to ensure that the disturbances eventually vanish. Additionally, this mapping is in general nontrivial and non-unique. In this paper, we propose a new kernel-based predictive control allocation to substitute the need for designing an analytic mapping, and assess if it can produce a meaningful mapping ``on-the-fly" by solving online an optimization problem. The simulations include three examples, which are the manipulation of an object through an unmanned aerial vehicle in two and three dimensions, and the control of a surface vessel actuated by two azimuthal thrusters., Comment: The preliminary results were presented in `Nguyen, Tam W., Kenji Hirata, and Kyoungseok Han. "A Nullspace-Based Predictive Control Allocation for the Control of a Quadcopter Manipulating an Object Attached to the Ground." IFAC-PapersOnLine 56.2 (2023): 6286-6291.'

Localization is one of the most crucial tasks for Unmanned Aerial Vehicle systems (UAVs) directly impacting overall performance, which can be achieved with various sensors and applied to numerous tasks related to search and rescue operations, object tracking, construction, etc. However, due to the negative effects of challenging environments, UAVs may lose signals for localization. In this paper, we present an effective path-planning system leveraging semantic segmentation information to navigate around texture-less and problematic areas like lakes, oceans, and high-rise buildings using a monocular camera. We introduce a real-time semantic segmentation architecture and a novel keyframe decision pipeline to optimize image inputs based on pixel distribution, reducing processing time. A hierarchical planner based on the Dynamic Window Approach (DWA) algorithm, integrated with a cost map, is designed to facilitate efficient path planning. The system is implemented in a photo-realistic simulation environment using Unity, aligning with segmentation model parameters. Comprehensive qualitative and quantitative evaluations validate the effectiveness of our approach, showing significant improvements in the reliability and efficiency of UAV localization in challenging environments., Comment: In The 24th International Conference on Control, Automation, and Systems (ICCAS 2024), Jeju, Korea

Navigating safely in dynamic human environments is crucial for mobile service robots, and social navigation is a key aspect of this process. In this paper, we proposed an integrative approach that combines motion prediction and trajectory planning to enable safe and socially-aware robot navigation. The main idea of the proposed method is to leverage the advantages of Socially Acceptable trajectory prediction and Timed Elastic Band (TEB) by incorporating human interactive information including position, orientation, and motion into the objective function of the TEB algorithms. In addition, we designed social constraints to ensure the safety of robot navigation. The proposed system is evaluated through physical simulation using both quantitative and qualitative metrics, demonstrating its superior performance in avoiding human and dynamic obstacles, thereby ensuring safe navigation. The implementations are open source at: \url{https://github.com/thanhnguyencanh/SGan-TEB.git}, Comment: In the 24th International Conference on Control, Automation, and Systems (ICCAS 2024), Jeju, Korea

We present a search for long-lived particles (LLPs) produced from kaon decay that decay to two muons inside the ICARUS neutrino detector. This channel would be a signal of hidden sector models that can address outstanding issues in particle physics such as the strong CP problem and the microphysical origin of dark matter. The search is performed with data collected in the Neutrinos at the Main Injector (NuMI) beam at Fermilab corresponding to $2.41\times 10^{20}$ protons-on-target. No new physics signal is observed, and we set world-leading limits on heavy QCD axions, as well as for the Higgs portal scalar among dedicated searches. Limits are also presented in a model-independent way applicable to any new physics model predicting the process $K\to \pi+S(\to\mu\mu)$, for a long-lived particle S. This result is the first search for new physics performed with the ICARUS detector at Fermilab. It paves the way for the future program of long-lived particle searches at ICARUS.

The best arm identification problem requires identifying the best alternative (i.e., arm) in active experimentation using the smallest number of experiments (i.e., arm pulls), which is crucial for cost-efficient and timely decision-making processes. In the fixed confidence setting, an algorithm must stop data-dependently and return the estimated best arm with a correctness guarantee. Since this stopping time is random, we desire its distribution to have light tails. Unfortunately, many existing studies focus on high probability or in expectation bounds on the stopping time, which allow heavy tails and, for high probability bounds, even not stopping at all. We first prove that this never-stopping event can indeed happen for some popular algorithms. Motivated by this, we propose algorithms that provably enjoy an exponential-tailed stopping time, which improves upon the polynomial tail bound reported by Kalyanakrishnan et al. (2012). The first algorithm is based on a fixed budget algorithm called Sequential Halving along with a doubling trick. The second algorithm is a meta algorithm that takes in any fixed confidence algorithm with a high probability stopping guarantee and turns it into one that enjoys an exponential-tailed stopping time. Our results imply that there is much more to be desired for contemporary fixed confidence algorithms.

Image registration techniques usually assume that the images to be registered are of a certain type (e.g. single- vs. multi-modal, 2D vs. 3D, rigid vs. deformable) and there lacks a general method that can work for data under all conditions. We propose a registration method that utilizes neural networks for image representation. Our method uses untrained networks with limited representation capacity as an implicit prior to guide for a good registration. Unlike previous approaches that are specialized for specific data types, our method handles both rigid and non-rigid, as well as single- and multi-modal registration, without requiring changes to the model or objective function. We have performed a comprehensive evaluation study using a variety of datasets and demonstrated promising performance.

Feature attributions attempt to highlight what inputs drive predictive power. Good attributions or explanations are thus those that produce inputs that retain this predictive power; accordingly, evaluations of explanations score their quality of prediction. However, evaluations produce scores better than what appears possible from the values in the explanation for a class of explanations, called encoding explanations. Probing for encoding remains a challenge because there is no general characterization of what gives the extra predictive power. We develop a definition of encoding that identifies this extra predictive power via conditional dependence and show that the definition fits existing examples of encoding. This definition implies, in contrast to encoding explanations, that non-encoding explanations contain all the informative inputs used to produce the explanation, giving them a "what you see is what you get" property, which makes them transparent and simple to use. Next, we prove that existing scores (ROAR, FRESH, EVAL-X) do not rank non-encoding explanations above encoding ones, and develop STRIPE-X which ranks them correctly. After empirically demonstrating the theoretical insights, we use STRIPE-X to uncover encoding in LLM-generated explanations for predicting the sentiment in movie reviews., Comment: 35 pages, 7 figures, 6 tables, 38th Conference on Neural Information Processing Systems (NeurIPS 2024)

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.

In domain-specific contexts, particularly mental health, abstractive summarization requires advanced techniques adept at handling specialized content to generate domain-relevant and faithful summaries. In response to this, we introduce a guided summarizer equipped with a dual-encoder and an adapted decoder that utilizes novel domain-specific guidance signals, i.e., mental health terminologies and contextually rich sentences from the source document, to enhance its capacity to align closely with the content and context of guidance, thereby generating a domain-relevant summary. Additionally, we present a post-editing correction model to rectify errors in the generated summary, thus enhancing its consistency with the original content in detail. Evaluation on the MentSum dataset reveals that our model outperforms existing baseline models in terms of both ROUGE and FactCC scores. Although the experiments are specifically designed for mental health posts, the methodology we've developed offers broad applicability, highlighting its versatility and effectiveness in producing high-quality domain-specific summaries., Comment: Accepted at PACLIC 2024. Camera-ready version

We investigate an internet-of-things system where energy-harvesting devices send status updates to a common receiver using the irregular repetition slotted ALOHA (IRSA) protocol. Energy shortages in these devices can cause transmission failures that are unknown to the receiver, halting the decoding process. We resolve this issue by proposing a method for the receiver to perfectly identify these failures. Furthermore, we optimize the degree distribution of the protocol to ensure the freshness of the status updates. The optimized degree distribution offsets the negative impact of the potential transmission failures. Our numerical results show that, despite energy harvesting, IRSA can maintain a level of information freshness comparable to systems with unlimited energy., Comment: submitted to IEEE WCNC 2025

In Federated Learning (FL), training is conducted on client devices, typically with limited computational resources and storage capacity. To address these constraints, we propose an automatic pruning scheme tailored for FL systems. Our solution improves computation efficiency on client devices, while minimizing communication costs. One of the challenges of tuning pruning hyper-parameters in FL systems is the restricted access to local data. Thus, we introduce an automatic pruning paradigm that dynamically determines pruning boundaries. Additionally, we utilized a structured pruning algorithm optimized for mobile devices that lack hardware support for sparse computations. Experimental results demonstrate the effectiveness of our approach, achieving accuracy comparable to existing methods. Our method notably reduces the number of parameters by 89% and FLOPS by 90%, with minimal impact on the accuracy of the FEMNIST and CelebFaces datasets. Furthermore, our pruning method decreases communication overhead by up to 5x and halves inference time when deployed on Android devices.

Existing LLM agent systems typically select actions from a fixed and predefined set at every step. While this approach is effective in closed, narrowly-scoped environments, we argue that it presents two major challenges when deploying LLM agents in real-world scenarios: (1) selecting from a fixed set of actions significantly restricts the planning and acting capabilities of LLM agents, and (2) this approach requires substantial human effort to enumerate and implement all possible actions, which becomes impractical in complex environments with a vast number of potential actions. In this work, we propose an LLM agent framework that enables the dynamic creation and composition of actions in an online manner. In this framework, the agent interacts with the environment by generating and executing programs written in a general-purpose programming language at each step. Furthermore, generated actions are accumulated over time for future reuse. Our extensive experiments on the GAIA benchmark demonstrate that this framework offers significantly greater flexibility and outperforms previous methods. Notably, it allows an LLM agent to recover in scenarios where no relevant action exists in the predefined set or when existing actions fail due to unforeseen edge cases. At the time of writing, we hold the top position on the GAIA public leaderboard. Our code can be found in \href{https://github.com/adobe-research/dynasaur}{https://github.com/adobe-research/dynasaur}., Comment: 15 pages, 8 figures

Smart metering networks are increasingly susceptible to cyber threats, where false data injection (FDI) appears as a critical attack. Data-driven-based machine learning (ML) methods have shown immense benefits in detecting FDI attacks via data learning and prediction abilities. Literature works have mostly focused on centralized learning and deploying FDI attack detection models at the control center, which requires data collection from local utilities like meters and transformers. However, this data sharing may raise privacy concerns due to the potential disclosure of household information like energy usage patterns. This paper proposes a new privacy-preserved FDI attack detection by developing an efficient federated learning (FL) framework in the smart meter network with edge computing. Distributed edge servers located at the network edge run an ML-based FDI attack detection model and share the trained model with the grid operator, aiming to build a strong FDI attack detection model without data sharing. Simulation results demonstrate the efficiency of our proposed FL method over the conventional method without collaboration., Comment: This work has been accepted by IEEE Consumer Communications & Networking Conference (CCNC)

A smooth diamond film, characterized by exceptional thermal conductivity, chemical stability, and optical properties, is highly suitable for a wide range of advanced applications. However, achieving uniform film quality presents a significant challenge for the CVD method due to non-uniformities in microwave distribution, electric fields, and the densities of reactive radicals during deposition processes involving $CH_4$ and $H_2$ precursors. Here, we systematically investigate the effects of microwave power and chamber pressure on surface roughness, crystalline quality, and the uniformity of diamond films. These findings provide valuable insights into the production of atomically smooth, high-quality diamond films with enhanced uniformity. By optimizing deposition parameters, we achieved a root-mean-square (RMS) surface roughness of 2 nm, comparable to high-pressure, high-temperature (HPHT) diamond substrates. Moreover, these conditions facilitated the formation of a pure single-crystal diamond phase, confirmed by the absence of contamination peaks in the Raman spectra

As human-agent teaming (HAT) research continues to grow, computational methods for modeling HAT behaviors and measuring HAT effectiveness also continue to develop. One rising method involves the use of human digital twins (HDT) to approximate human behaviors and socio-emotional-cognitive reactions to AI-driven agent team members. In this paper, we address three research questions relating to the use of digital twins for modeling trust in HATs. First, to address the question of how we can appropriately model and operationalize HAT trust through HDT HAT experiments, we conducted causal analytics of team communication data to understand the impact of empathy, socio-cognitive, and emotional constructs on trust formation. Additionally, we reflect on the current state of the HAT trust science to discuss characteristics of HAT trust that must be replicable by a HDT such as individual differences in trust tendencies, emergent trust patterns, and appropriate measurement of these characteristics over time. Second, to address the question of how valid measures of HDT trust are for approximating human trust in HATs, we discuss the properties of HDT trust: self-report measures, interaction-based measures, and compliance type behavioral measures. Additionally, we share results of preliminary simulations comparing different LLM models for generating HDT communications and analyze their ability to replicate human-like trust dynamics. Third, to address how HAT experimental manipulations will extend to human digital twin studies, we share experimental design focusing on propensity to trust for HDTs vs. transparency and competency-based trust for AI agents., Comment: in review; submitted to Interaction Studies

In time-series analysis, many recent works seek to provide a unified view and representation for time-series across multiple domains, leading to the development of foundation models for time-series data. Despite diverse modeling techniques, existing models are black boxes and fail to provide insights and explanations about their representations. In this paper, we present VQShape, a pre-trained, generalizable, and interpretable model for time-series representation learning and classification. By introducing a novel representation for time-series data, we forge a connection between the latent space of VQShape and shape-level features. Using vector quantization, we show that time-series from different domains can be described using a unified set of low-dimensional codes, where each code can be represented as an abstracted shape in the time domain. On classification tasks, we show that the representations of VQShape can be utilized to build interpretable classifiers, achieving comparable performance to specialist models. Additionally, in zero-shot learning, VQShape and its codebook can generalize to previously unseen datasets and domains that are not included in the pre-training process. The code and pre-trained weights are available at https://github.com/YunshiWen/VQShape., Comment: Accepted by Neural Information Processing Systems (NeurIPS) 2024

Additive Manufacturing (AM) is transforming the manufacturing sector by enabling efficient production of intricately designed products and small-batch components. However, metal parts produced via AM can include flaws that cause inferior mechanical properties, including reduced fatigue response, yield strength, and fracture toughness. To address this issue, we leverage convolutional neural networks (CNN) to analyze thermal images of printed layers, automatically identifying anomalies that impact these properties. We also investigate various synthetic data generation techniques to address limited and imbalanced AM training data. Our models' defect detection capabilities were assessed using images of Nickel alloy 718 layers produced on a laser powder bed fusion AM machine and synthetic datasets with and without added noise. Our results show significant accuracy improvements with synthetic data, emphasizing the importance of expanding training sets for reliable defect detection. Specifically, Generative Adversarial Networks (GAN)-generated datasets streamlined data preparation by eliminating human intervention while maintaining high performance, thereby enhancing defect detection capabilities. Additionally, our denoising approach effectively improves image quality, ensuring reliable defect detection. Finally, our work integrates these models in the CLoud ADditive MAnufacturing (CLADMA) module, a user-friendly interface, to enhance their accessibility and practicality for AM applications. This integration supports broader adoption and practical implementation of advanced defect detection in AM processes., Comment: 29 pages

We study learning in a dynamically evolving environment modeled as a Markov game between a learner and a strategic opponent that can adapt to the learner's strategies. While most existing works in Markov games focus on external regret as the learning objective, external regret becomes inadequate when the adversaries are adaptive. In this work, we focus on \emph{policy regret} -- a counterfactual notion that aims to compete with the return that would have been attained if the learner had followed the best fixed sequence of policy, in hindsight. We show that if the opponent has unbounded memory or if it is non-stationary, then sample-efficient learning is not possible. For memory-bounded and stationary, we show that learning is still statistically hard if the set of feasible strategies for the learner is exponentially large. To guarantee learnability, we introduce a new notion of \emph{consistent} adaptive adversaries, wherein, the adversary responds similarly to similar strategies of the learner. We provide algorithms that achieve $\sqrt{T}$ policy regret against memory-bounded, stationary, and consistent adversaries., Comment: NeurIPS'24

$\mathcal C^2$-partial smoothness of functions has been an important subject of research in optimization, on both theoretical and algorithmic aspects, since it was first introduced by Lewis in 2002. Our work aims at providing a fresh variational analysis viewpoint on the class of $\mathcal C^2$-partly smooth functions. Namely, we explore the relationship between $\mathcal C^2$-partial smoothness and strict twice epi-differentiability and demonstrate that functions from the latter class are always strictly twice epi-differentiable. On the other hand, we provide two examples to show that the opposite conclusion does not hold in general. As a consequence of our analysis, we calculate the second subderivative of $\mathcal C^2$-partly smooth functions. Applications to stability analysis of related generalized equations involving a general perturbation and to asymptotic analysis of the well-known sample average approximation method for stochastic programs with $\mathcal C^2$-partly smooth regularizers are also given., Comment: 27 pages

We study the problem of estimating the \emph{value} of the largest mean among $K$ distributions via samples from them (rather than estimating \emph{which} distribution has the largest mean), which arises from various machine learning tasks including Q-learning and Monte Carlo tree search. While there have been a few proposed algorithms, their performance analyses have been limited to their biases rather than a precise error metric. In this paper, we propose a novel algorithm called HAVER (Head AVERaging) and analyze its mean squared error. Our analysis reveals that HAVER has a compelling performance in two respects. First, HAVER estimates the maximum mean as well as the oracle who knows the identity of the best distribution and reports its sample mean. Second, perhaps surprisingly, HAVER exhibits even better rates than this oracle when there are many distributions near the best one. Both of these improvements are the first of their kind in the literature, and we also prove that the naive algorithm that reports the largest empirical mean does not achieve these bounds. Finally, we confirm our theoretical findings via numerical experiments including bandits and Q-learning scenarios where HAVER outperforms baseline methods.

Intermolecular charge-transfer (xCT) excited states important for various practical applications are challenging for many standard computational methods. It is highly desirable to have an affordable method that can treat xCT states accurately. In the present work, we extend our self-consistent perturbation methods, named one-body second-order M{\o}ller-Plesset (OBMP2) and its spin-opposite scaling variant, for excited states without additional costs to the ground state. We then assessed their performance for the prediction of xCT excitation energies. Thanks to self-consistency, our methods yield small errors relative to high-level coupled cluster methods and outperform other same scaling ($N^5$) methods like CC2 and ADC(2). In particular, the spin-opposite scaling variant (O2BMP2), whose scaling can be reduced to $N^4$, can even reach the accuracy of CC3 ($N^7$) with errors less than 0.1 eV. This method is thus highly promising for treating xCT states in large compounds vital for applications., Comment: 16 pages, 5 figures, 3 tables

A major obstacle to the advancements of machine learning models in marine science, particularly in sonar imagery analysis, is the scarcity of AI-ready datasets. While there have been efforts to make AI-ready sonar image dataset publicly available, they suffer from limitations in terms of environment setting and scale. To bridge this gap, we introduce SeafloorAI, the first extensive AI-ready datasets for seafloor mapping across 5 geological layers that is curated in collaboration with marine scientists. We further extend the dataset to SeafloorGenAI by incorporating the language component in order to facilitate the development of both vision- and language-capable machine learning models for sonar imagery. The dataset consists of 62 geo-distributed data surveys spanning 17,300 square kilometers, with 696K sonar images, 827K annotated segmentation masks, 696K detailed language descriptions and approximately 7M question-answer pairs. By making our data processing source code publicly available, we aim to engage the marine science community to enrich the data pool and inspire the machine learning community to develop more robust models. This collaborative approach will enhance the capabilities and applications of our datasets within both fields.

Beyond the well-known fermions and bosons, anyons-an exotic class of particles-emerge in the fractional quantum Hall effect and exhibit fractional quantum statistics. Anyons can be categorized by their charge, with extensive research focused on those carrying fractional charge, while charge-neutral anyons in 2D electron liquids remain largely unexplored. Here, we introduce bilayer excitons as a new pathway to realizing charge-neutral anyons. By pairing quasiparticles and quasiholes from Laughlin states, we report bilayer excitons that obey fractional quantum statistics. Through layer-asymmetric field-effect doping, we achieve precise control of the anyon population, stabilizing anyonic dipoles at temperatures below the charge gap. Furthermore, we investigate neutral anyons in even-denominator FQHE states, which are likely described by non-Abelian wavefunctions. These findings open the door to exploring non-Abelian statistics in neutral anyons, with the potential to reshape future research in topological quantum phases., Comment: 9 pages for main text, 4 main figures, total of 16 pages, total of 6 figures

The magnetised near detector (ND280) of the T2K long-baseline neutrino oscillation experiment has been recently upgraded aiming to satisfy the requirement of reducing the systematic uncertainty from measuring the neutrinonucleus interaction cross section, which is the largest systematic uncertainty in the search for leptonic charge-parity symmetry violation. A key component of the upgrade is SuperFGD, a 3D segmented plastic scintillator detector made of approximately 2,000,000 optically-isolated 1 cm3 cubes. It will provide a 3D image of GeV neutrino interactions by combining tracking and stopping power measurements of final state particles with sub-nanosecond time resolution. The performance of SuperFGD is characterized by the precision of its response to charged particles as well as the systematic effects that might affect the physics measurements. Hence, a detailed Geant4 based optical simulation of the SuperFGD building block, i.e. a plastic scintillating cube read out by three wavelength shifting fibers, has been developed and validated with the different datasets collected in various beam tests. In this manuscript the description of the optical model as well as the comparison with data are reported., Comment: 31 pages, 15 figures

We study the long-standing open question of the power of unique witness in quantum protocols, which asks if UniqueQMA, a variant of QMA whose accepting witness space is 1-dimensional, is equal to QMA. We show a quantum oracle separation between UniqueQMA and QMA via an extension of the Aaronson-Kuperberg's QCMA vs QMA oracle separation. In particular, we show that any UniqueQMA protocol must make $\Omega(\sqrt{D})$ queries to a subspace phase oracle of unknown dimension $\leq D$ to "find" the subspace. This presents an obstacle to relativizing techniques in resolving this question (unlike its classical analogue - the Valiant-Vazirani theorem - which is essentially a black-box reduction) and suggests the need to study the structure of the ground space of local Hamiltonians in distilling a potential unique witness. Our techniques also yield a quantum oracle separation between QXC, the class characterizing quantum approximate counting, and QMA. Very few structural properties are known that place the complexity of local Hamiltonians in UniqueQMA. We expand this set of properties by showing that the ground energy of local Hamiltonians that satisfy the eigenstate thermalization hypothesis (ETH) can be estimated through a UniqueQMA protocol. Specifically, our protocol can be viewed as a quantum expander test in a low energy subspace of the Hamiltonian and verifies a unique entangled state in two copies of the subspace. This allows us to conclude that if UniqueQMA $\neq$ QMA, then QMA-hard Hamiltonians must violate ETH under adversarial perturbations (more accurately, under the quantum PCP conjecture if ETH only applies to extensive energy subspaces). Our results serve as evidence that chaotic local Hamiltonians, such as the SYK model, contain polynomial verifiable quantum states in their low energy regime and may be simpler than general local Hamiltonians if UniqueQMA $\neq$ QMA.

Predicting program behavior and reasoning about code execution remain significant challenges in software engineering, particularly for large language models (LLMs) designed for code analysis. While these models excel at understanding static syntax, they often struggle with dynamic reasoning tasks. We introduce Visual Coder, a simple yet effective approach that enhances code reasoning by integrating multimodal Chain-of-Thought (CoT) reasoning with a visual Control Flow Graph (CFG). By aligning code snippets with their corresponding CFGs, Visual Coder provides deeper insights into execution flow, enabling more accurate predictions of code behavior. Our experiments demonstrate that augmenting LLMs with visual CFGs significantly outperforms text-based CFG descriptions in code reasoning tasks. We address challenges in multimodal CoT integration through a reference mechanism, ensuring consistency between code and its execution path, thereby improving performance in program behavior prediction, error detection, and output generation.

Robotic systems show significant promise for water environmental sensing applications such as water quality monitoring, pollution mapping and biodiversity data collection. Conventional deployment methods often disrupt fragile ecosystems, preventing depiction of the undisturbed environmental condition. In response to this challenge, we propose a novel framework utilizing a lightweight tumbler system equipped with a sensing unit, deployed via a drone. This design minimizes disruption to the water habitat by maintaining a slow descent. The sensing unit is detached once on the water surface, enabling precise and non-invasive data collection from the benthic zone. The tumbler is designed to be lightweight and compact, enabling deployment via a drone. The sensing pod, which detaches from the tumbler and descends to the bottom of the water body, is equipped with temperature and pressure sensors, as well as a buoyancy system. The later, activated upon task completion, utilizes a silicon membrane inflated via a chemical reaction. The reaction generates a pressure of 70 kPa, causing the silicon membrane to expand by 30\%, which exceeds the 5.7\% volume increase required for positive buoyancy. The tumblers, made from ecofriendly materials to minimize environmental impact when lost during the mission, were tested for their gliding ratio and descent rate. They exhibit a low descent rate, in the range of 0.8 to 2.5 meters per seconds, which minimizes disturbance to the ecosystem upon water landing. Additionally, the system demonstrated robustness in moderate to strong wind conditions during outdoor tests, validating the overall framework., Comment: Submitted to IEEE Robosoft 2025

Continuous-time trajectory representation has gained significant popularity in recent years, as it offers an elegant formulation that allows the fusion of a larger number of sensors and sensing modalities, overcoming limitations of traditional discrete-time frameworks. To bolster the adoption of the continuous-time paradigm, we propose a so-called Gaussian Process Trajectory Representation (GPTR) framework for continuous-time motion estimation (CTME) tasks. Our approach stands out by employing a third-order random jerk model, featuring closed-form expressions for both rotational and translational state derivatives. This model provides smooth, continuous trajectory representations that are crucial for precise estimation of complex motion. To support the wider robotics and computer vision communities, we have made the source code for GPTR available as a light-weight header-only library. This format was chosen for its ease of integration, allowing developers to incorporate GPTR into existing systems without needing extensive code modifications. Moreover, we also provide a set of optimization examples with LiDAR, camera, IMU, UWB factors, and closed-form analytical Jacobians under the proposed GP framework. Our experiments demonstrate the efficacy and efficiency of GP-based trajectory representation in various motion estimation tasks, and the examples can serve as the prototype to help researchers quickly develop future applications such as batch optimization, calibration, sensor fusion, trajectory planning, etc., with continuous-time trajectory representation. Our project is accessible at https://github.com/brytsknguyen/gptr ., Comment: The source code has been released. All feedbacks are welcome

Large time dynamics of reaction-diffusion systems modeling some irreversible reaction networks are investigated. Depending on initial masses, these networks possibly possess boundary equilibria, where some of the chemical concentrations are completely used up. In the absence of these equilibria, we show an explicit convergence to equilibrium by a modified entropy method, where it is shown that reactions in a measurable set with positive measure is sufficient to combine with diffusion and to drive the system towards equilibrium. When the boundary equilibria are present, we show that they are unstable (in Lyapunov sense) using some bootstrap instability technique from fluid mechanics, while the nonlinear stability of the positive equilibrium is proved by exploiting a spectral gap of the linearized operator and the uniform-in-time boundedness of solutions., Comment: Title slightly modified. Comments are welcome

In recent years, motion planning for urban self-driving cars (SDV) has become a popular problem due to its complex interaction of road components. To tackle this, many methods have relied on large-scale, human-sampled data processed through Imitation learning (IL). Although effective, IL alone cannot adequately handle safety and reliability concerns. Combining IL with Reinforcement learning (RL) by adding KL divergence between RL and IL policy to the RL loss can alleviate IL's weakness but suffer from over-conservation caused by covariate shift of IL. To address this limitation, we introduce a method that combines IL with RL using an implicit entropy-KL control that offers a simple way to reduce the over-conservation characteristic. In particular, we validate different challenging simulated urban scenarios from the unseen dataset, indicating that although IL can perform well in imitation tasks, our proposed method significantly improves robustness (over 17\% reduction in failures) and generates human-like driving behavior., Comment: submitted to IEEE Open Journal of Intelligent Transportation Systems

Recently, Vision Transformers (ViTs) have achieved unprecedented effectiveness in the general domain of image classification. Nonetheless, these models remain underexplored in the field of deepfake detection, given their lower performance as compared to Convolution Neural Networks (CNNs) in that specific context. In this paper, we start by investigating why plain ViT architectures exhibit a suboptimal performance when dealing with the detection of facial forgeries. Our analysis reveals that, as compared to CNNs, ViT struggles to model localized forgery artifacts that typically characterize deepfakes. Based on this observation, we propose a deepfake detection framework called FakeFormer, which extends ViTs to enforce the extraction of subtle inconsistency-prone information. For that purpose, an explicit attention learning guided by artifact-vulnerable patches and tailored to ViTs is introduced. Extensive experiments are conducted on diverse well-known datasets, including FF++, Celeb-DF, WildDeepfake, DFD, DFDCP, and DFDC. The results show that FakeFormer outperforms the state-of-the-art in terms of generalization and computational cost, without the need for large-scale training datasets. The code is available at \url{https://github.com/10Ring/FakeFormer}.

Fracture toughness is the material property characterizing resistance to failure. Predicting its value from the solid structure at the atomistic scale remains elusive, even in the simplest situations of brittle fracture. We report here numerical simulations of crack propagation in two-dimensional fuse networks of different periodic geometries, which are electrical analogs of bidimensional brittle crystals under antiplanar loading. Fracture energy is determined from Griffith's analysis of energy balance during crack propagation, and fracture toughness is determined from fits of the displacement fields with Williams' asymptotic solutions. Significant size dependencies are evidenced in small lattices, with fracture energy and fracture toughness both converging algebraically with system size toward well-defined material-constant values in the limit of infinite system size. The convergence speed depends on the loading conditions and is faster when the symmetry of the considered lattice increases. The material constants at infinity obey Irwin's relation and properly define the material resistance to failure. Their values are approached up to $\sim$ 15 % using the recent analytical method proposed in Nguyen and Bonamy (Phys Rev Lett 123:205503, 2019). Nevertheless, the deviation remains finite and does not vanish when the system size goes to infinity. We finally show that this deviation is a consequence of the lattice discreetness and decreases when the super-singular terms of Williams' solutions (absent in a continuum medium but present here due to lattice discreetness) are taken into account., Comment: International Journal of Fracture, In press

In automotive industry, client needs evolve quickly in a competitiveness context, particularly, regarding the fan involved in the engine cooling module. This study has been done in cooperation with the automotive supplier Valeo. Here, we propose to use the Kriging interpolation and the Expected Improvement algorithm to provide new fan designs with high performances in terms of eciency. As far as we know, such a use of Kriging and Expected Improvement methodologies are innovative and provide really promising results.

Emergent communication, driven by generative models, enables agents to develop a shared language for describing their individual views of the same objects through interactions. Meanwhile, self-supervised learning (SSL), particularly SimSiam, uses discriminative representation learning to make representations of augmented views of the same data point closer in the representation space. Building on the prior work of VI-SimSiam, which incorporates a generative and Bayesian perspective into the SimSiam framework via variational inference (VI) interpretation, we propose SimSiam+VAE, a unified approach for both representation learning and emergent communication. SimSiam+VAE integrates a variational autoencoder (VAE) into the predictor of the SimSiam network to enhance representation learning and capture uncertainty. Experimental results show that SimSiam+VAE outperforms both SimSiam and VI-SimSiam. We further extend this model into a communication framework called the SimSiam Naming Game (SSNG), which applies the generative and Bayesian approach based on VI to develop internal representations and emergent language, while utilizing the discriminative process of SimSiam to facilitate mutual understanding between agents. In experiments with established models, despite the dynamic alternation of agent roles during interactions, SSNG demonstrates comparable performance to the referential game and slightly outperforms the Metropolis-Hastings naming game.

Machine learning (ML) for text classification has been widely used in various domains, such as toxicity detection, chatbot consulting, and review analysis. These applications can significantly impact ethics, economics, and human behavior, raising serious concerns about trusting ML decisions. Several studies indicate that traditional metrics, such as model confidence and accuracy, are insufficient to build human trust in ML models. These models often learn spurious correlations during training and predict based on them during inference. In the real world, where such correlations are absent, their performance can deteriorate significantly. To avoid this, a common practice is to test whether predictions are reasonable. Along with this, a challenge known as the trustworthiness oracle problem has been introduced. Due to the lack of automated trustworthiness oracles, the assessment requires manual validation of the decision process disclosed by explanation methods, which is time-consuming and not scalable. We propose TOKI, the first automated trustworthiness oracle generation method for text classifiers, which automatically checks whether the prediction-contributing words are related to the predicted class using explanation methods and word embeddings. To demonstrate its practical usefulness, we introduce a novel adversarial attack method targeting trustworthiness issues identified by TOKI. We compare TOKI with a naive baseline based solely on model confidence using human-created ground truths of 6,000 predictions. We also compare TOKI-guided adversarial attack method with A2T, a SOTA adversarial attack method. Results show that relying on prediction uncertainty cannot distinguish between trustworthy and untrustworthy predictions, TOKI achieves 142% higher accuracy than the naive baseline, and TOKI-guided adversarial attack method is more effective with fewer perturbations than A2T.

Precoding is a critical and long-standing technique in multi-user communication systems. However, the majority of existing precoding methods do not consider channel coding in their designs. In this paper, we consider the precoding problem in multi-user multiple-input single-output (MISO) systems, incorporating channel coding into the design. By leveraging the error-correcting capability of channel codes we increase the degrees of freedom in the transmit signal design, thereby enhancing the overall system performance. We first propose a novel data-dependent precoding framework for coded MISO systems, referred to as channel-coded precoding (CCP), which maximizes the probability that information bits can be correctly recovered by the channel decoder. This proposed CCP framework allows the transmit signals to produce data symbol errors at the users' receivers, as long as the overall information BER performance can be improved. We develop the CCP framework for both one-bit and multi-bit error-correcting capacity and devise a projected gradient-based approach to solve the design problem. We also develop a robust CCP framework for the case where knowledge of perfect channel state information (CSI) is unavailable at the transmitter, taking into account the effect of both noise and channel estimation errors. Finally, we conduct numerous simulations to verify the effectiveness of the proposed CCP and its superiority compared to existing precoding methods, and we identify situations where the proposed CCP yields the most significant gains., Comment: 13 pages, 11 figures