Search

Protocol Reverse Engineering (PRE) is used to analyze protocols by inferring their structure and behavior. However, current PRE methods mainly focus on field identification within a single protocol and neglect Protocol State Machine (PSM) analysis in mixed protocol environments. This results in insufficient analysis of protocols' abnormal behavior and potential vulnerabilities, which are crucial for detecting and defending against new attack patterns. To address these challenges, we propose an automatic PSM inference framework for unknown protocols, including a fuzzy membership-based auto-converging DBSCAN algorithm for protocol format clustering, followed by a session clustering algorithm based on Needleman-Wunsch and K-Medoids algorithms to classify sessions by protocol type. Finally, we refine a probabilistic PSM algorithm to infer protocol states and the transition conditions between these states. Experimental results show that, compared with existing PRE techniques, our method can infer PSMs while enabling more precise classification of protocols., Comment: 4 pages,5 figures

Generating realistic 3D human-object interactions (HOIs) from text descriptions is a active research topic with potential applications in virtual and augmented reality, robotics, and animation. However, creating high-quality 3D HOIs remains challenging due to the lack of large-scale interaction data and the difficulty of ensuring physical plausibility, especially in out-of-domain (OOD) scenarios. Current methods tend to focus either on the body or the hands, which limits their ability to produce cohesive and realistic interactions. In this paper, we propose OOD-HOI, a text-driven framework for generating whole-body human-object interactions that generalize well to new objects and actions. Our approach integrates a dual-branch reciprocal diffusion model to synthesize initial interaction poses, a contact-guided interaction refiner to improve physical accuracy based on predicted contact areas, and a dynamic adaptation mechanism which includes semantic adjustment and geometry deformation to improve robustness. Experimental results demonstrate that our OOD-HOI could generate more realistic and physically plausible 3D interaction pose in OOD scenarios compared to existing methods.

The autobidding system generates huge revenue for advertising platforms, garnering substantial research attention. Existing studies in autobidding systems focus on designing Autobidding Incentive Compatible (AIC) mechanisms, where the mechanism is Incentive Compatible (IC) under ex ante expectations. However, upon deploying AIC mechanisms in advertising platforms, we observe a notable deviation between the actual auction outcomes and these expectations during runtime, particularly in the scene with few clicks (sparse-click). This discrepancy undermines truthful bidding among advertisers in AIC mechanisms, especially for risk-averse advertisers who are averse to outcomes that do not align with the expectations. To address this issue, we propose a mechanism, Decoupled First-Price Auction (DFP), that retains its IC property even during runtime. DFP dynamically adjusts the payment based on real-time user conversion outcomes, ensuring that advertisers' realized utilities closely approximate their expected utilities during runtime. To realize the payment mechanism of DFP, we propose a PPO-based RL algorithm, with a meticulously crafted reward function. This algorithm dynamically adjusts the payment to fit DFP mechanism. We conduct extensive experiments leveraging real-world data to validate our findings.

Prevalent in biological applications (e.g., human phenotype measurements), multimodal datasets can provide valuable insights into the underlying biological mechanisms. However, current machine learning models designed to analyze such datasets still lack interpretability and theoretical guarantees, which are essential to biological applications. Recent advances in causal representation learning have shown promise in uncovering the interpretable latent causal variables with formal theoretical certificates. Unfortunately, existing works for multimodal distributions either rely on restrictive parametric assumptions or provide rather coarse identification results, limiting their applicability to biological research which favors a detailed understanding of the mechanisms. In this work, we aim to develop flexible identification conditions for multimodal data and principled methods to facilitate the understanding of biological datasets. Theoretically, we consider a flexible nonparametric latent distribution (c.f., parametric assumptions in prior work) permitting causal relationships across potentially different modalities. We establish identifiability guarantees for each latent component, extending the subspace identification results from prior work. Our key theoretical ingredient is the structural sparsity of the causal connections among distinct modalities, which, as we will discuss, is natural for a large collection of biological systems. Empirically, we propose a practical framework to instantiate our theoretical insights. We demonstrate the effectiveness of our approach through extensive experiments on both numerical and synthetic datasets. Results on a real-world human phenotype dataset are consistent with established medical research, validating our theoretical and methodological framework.

Existing permanental processes often impose constraints on kernel types or stationarity, limiting the model's expressiveness. To overcome these limitations, we propose a novel approach utilizing the sparse spectral representation of nonstationary kernels. This technique relaxes the constraints on kernel types and stationarity, allowing for more flexible modeling while reducing computational complexity to the linear level. Additionally, we introduce a deep kernel variant by hierarchically stacking multiple spectral feature mappings, further enhancing the model's expressiveness to capture complex patterns in data. Experimental results on both synthetic and real-world datasets demonstrate the effectiveness of our approach, particularly in scenarios with pronounced data nonstationarity. Additionally, ablation studies are conducted to provide insights into the impact of various hyperparameters on model performance.

In materials science, microstructures and their associated extrinsic properties are critical for engineering advanced structural and functional materials, yet their robust reconstruction and generation remain significant challenges. In this work, we developed a microstructure generation model based on the Stable Diffusion (SD) model, training it on a dataset of 576,000 2D synthetic microstructures containing both phase and grain orientation information. This model was applied to a range of tasks, including microstructure reconstruction, interpolation, inpainting, and generation. Experimental results demonstrate that our image-based approach can analyze and generate complex microstructural features with exceptional statistical and morphological fidelity. Additionally, by integrating the ControlNet fine-tuning model, we achieved the inverse design of microstructures based on specific properties. Compared to conventional methods, our approach offers greater accuracy, efficiency, and versatility, showcasing its generative potential in exploring previously uncharted microstructures and paving the way for data-driven development of advanced materials with tailored properties., Comment: 41 pages, 9 figures, 3 tables

In addition to the forward inference of materials properties using machine learning, generative deep learning techniques applied on materials science allow the inverse design of materials, i.e., assessing the composition-processing-(micro-)structure-property relationships in a reversed way. In this review, we focus on the (micro-)structure-property mapping, i.e., crystal structure-intrinsic property and microstructure-extrinsic property, and summarize comprehensively how generative deep learning can be performed. Three key elements, i.e., the construction of latent spaces for both the crystal structures and microstructures, generative learning approaches, and property constraints, are discussed in detail. A perspective is given outlining the challenges of the existing methods in terms of computational resource consumption, data compatibility, and yield of generation., Comment: 36 pages, 3 figures, 3 tables

Neural health refers to the condition and functionality of the auditory nerve fibers (ANFs),which are crucial for transmitting sound signals from the cochlea to the brain.However, neural health cannot be directly measured due to current technological limitations. We utilize a computational model to evaluate different indirect methods for estimating ANF neural health.Two distinct measures for estimating neural health,(i)the threshold levels for focused quadrupolar stimulation and (ii) the change in the electrically evoked compound action potential (eCAP) amplitude growth function for different inter-phase gaps (IPGs), were evaluated in a computational model of an electrically stimulated implanted cochlea. The model combined a 3D finite element method model, an ANF geometry with a realistic spatial distribution, and a neuron model, including an existing phenomenological single-ANF model and an eCAP model. Our experiments simulated different neural health conditions (healthy, shrinked, and degenerated) to model dead regions in different locations of the cochlea.The results from the computational experiments demonstrated that the threshold levels with focused quadrupolar stimulation were more sensitive to neural health deficits than thresholds with monopolar stimulation. From our data, the difference in threshold levels between quadrupolar and monopolar stimulation seems to be a promising measure of neural health status. However, the results from the eCAP IPG slope and offset effects were not consistently associated with neural health conditions.Our results suggest that the difference in threshold levels with quadrupolar and monopolar stimulation is a possible method for estimating neural health. Significance: This study enhances the understanding of neural health and dead regions through a novel computational model, contributing to new approaches for neural health estimation.

Spin waves, or magnons, are fundamental excitations in magnetic materials that provide insights into their dynamic properties and interactions. Magnons are the building blocks of magnonics, which offer promising perspectives for data storage, quantum computing, and communication technologies. These excitations are typically measured through inelastic neutron or x-ray scattering techniques, which involve heavy and time-consuming measurements, data processing, and analysis based on various theoretical models. Here, we introduce a machine learning algorithm that integrates adaptive noise reduction and active learning sampling, which enables the restoration from minimal inelastic neutron scattering point data of spin wave information and the accurate extraction of magnetic parameters, including hidden interactions. Our findings, benchmarked against the magnon spectra of CrSBr, significantly enhance the efficiency and accuracy in addressing complex and noisy experimental measurements. This advancement offers a powerful machine learning tool for research in magnonics and spintronics, which can also be extended to other characterization techniques at large facilities.

In this work, we investigate stochastic approximation (SA) with Markovian data and nonlinear updates under constant stepsize $\alpha>0$. Existing work has primarily focused on either i.i.d. data or linear update rules. We take a new perspective and carefully examine the simultaneous presence of Markovian dependency of data and nonlinear update rules, delineating how the interplay between these two structures leads to complications that are not captured by prior techniques. By leveraging the smoothness and recurrence properties of the SA updates, we develop a fine-grained analysis of the correlation between the SA iterates $\theta_k$ and Markovian data $x_k$. This enables us to overcome the obstacles in existing analysis and establish for the first time the weak convergence of the joint process $(x_k, \theta_k)_{k\geq0}$. Furthermore, we present a precise characterization of the asymptotic bias of the SA iterates, given by $\mathbb{E}[\theta_\infty]-\theta^\ast=\alpha(b_\text{m}+b_\text{n}+b_\text{c})+O(\alpha^{3/2})$. Here, $b_\text{m}$ is associated with the Markovian noise, $b_\text{n}$ is tied to the nonlinearity, and notably, $b_\text{c}$ represents a multiplicative interaction between the Markovian noise and nonlinearity, which is absent in previous works. As a by-product of our analysis, we derive finite-time bounds on higher moment $\mathbb{E}[\|\theta_k-\theta^\ast\|^{2p}]$ and present non-asymptotic geometric convergence rates for the iterates, along with a Central Limit Theorem.

The integration of AI assistants, especially through the development of Large Language Models (LLMs), into computer science education has sparked significant debate. An emerging body of work has looked into using LLMs in education, but few have examined the impacts of LLMs on students in entry-level programming courses, particularly in real-world contexts and over extended periods. To address this research gap, we conducted a semester-long, between-subjects study with 50 students using CodeTutor, an LLM-powered assistant developed by our research team. Our study results show that students who used CodeTutor (the experimental group) achieved statistically significant improvements in their final scores compared to peers who did not use the tool (the control group). Within the experimental group, those without prior experience with LLM-powered tools demonstrated significantly greater performance gain than their counterparts. We also found that students expressed positive feedback regarding CodeTutor's capability, though they also had concerns about CodeTutor's limited role in developing critical thinking skills. Over the semester, students' agreement with CodeTutor's suggestions decreased, with a growing preference for support from traditional human teaching assistants. Our analysis further reveals that the quality of user prompts was significantly correlated with CodeTutor's response effectiveness. Building upon our results, we discuss the implications of our findings for integrating Generative AI literacy into curricula to foster critical thinking skills and turn to examining the temporal dynamics of user engagement with LLM-powered tools. We further discuss the discrepancy between the anticipated functions of tools and students' actual capabilities, which sheds light on the need for tailored strategies to improve educational outcomes., Comment: Accepted to Learning @ Scale 2024

WebAssembly (abbreviated as Wasm) was initially introduced for the Web but quickly extended its reach into various domains beyond the Web. To create Wasm applications, developers can compile high-level programming languages into Wasm binaries or manually convert equivalent textual formats into Wasm binaries. Regardless of whether it is utilized within or outside the Web, the execution of Wasm binaries is supported by the Wasm runtime. Such a runtime provides a secure, memory-efficient, and sandboxed execution environment designed explicitly for Wasm applications. This paper provides a comprehensive survey of research on WebAssembly runtimes. It covers 98 articles on WebAssembly runtimes and characterizes existing studies from two different angles, including the "internal" research of Wasm runtimes(Wasm runtime design, testing, and analysis) and the "external" research(applying Wasm runtimes to various domains). This paper also proposes future research directions about WebAssembly runtimes.

Polar topologies, such as vortex and skyrmion, have attracted significant interest due to their unique physical properties and promising applications in high-density memory devices. Currently, most polar vortices are observed in heterostructures containing ferroelectric materials and constrained by substrates. In this study, we unravel arrays of polar vortices formed in twisted freestanding bilayers composed of SrTiO3, a quantum-paraelectric material. Depth-resolved structures of the bilayers are measured with deep-sub-angstrom resolution and one picometer accuracy using multislice ptychography, enabling identification of the three-dimensional variations of polarization topology. Our findings reveal the evolution of the polar vortices in the twisted overlapping layers, demonstrating the reverse of rotation manner in the depth direction. Twisted freestanding bilayers provide a unique platform for exploration and modulation of novel polar topologies.

Motivated by Q-learning, we study nonsmooth contractive stochastic approximation (SA) with constant stepsize. We focus on two important classes of dynamics: 1) nonsmooth contractive SA with additive noise, and 2) synchronous and asynchronous Q-learning, which features both additive and multiplicative noise. For both dynamics, we establish weak convergence of the iterates to a stationary limit distribution in Wasserstein distance. Furthermore, we propose a prelimit coupling technique for establishing steady-state convergence and characterize the limit of the stationary distribution as the stepsize goes to zero. Using this result, we derive that the asymptotic bias of nonsmooth SA is proportional to the square root of the stepsize, which stands in sharp contrast to smooth SA. This bias characterization allows for the use of Richardson-Romberg extrapolation for bias reduction in nonsmooth SA., Comment: ACM SIGMETRICS 2024. 71 pages, 3 figures

Mathematical modeling (MM) is considered a fundamental skill for students in STEM disciplines. Practicing the MM skill is often the most effective when students can engage in group discussion and collaborative problem-solving. However, due to unevenly distributed teachers and educational resources needed to monitor such group activities, students do not always receive equal opportunities for this practice. Excitingly, large language models (LLMs) have recently demonstrated strong capability in both modeling mathematical problems and simulating characters with different traits and properties. Drawing inspiration from the advancement of LLMs, in this work, we present MATHVC, the very first LLM-powered virtual classroom containing multiple LLM-simulated student characters, with whom a human student can practice their MM skill. To encourage each LLM character's behaviors to be aligned with their specified math-relevant properties (termed "characteristics alignment") and the overall conversational procedure to be close to an authentic student MM discussion (termed "conversational procedural alignment"), we proposed three innovations: integrating MM domain knowledge into the simulation, defining a symbolic schema as the ground for character simulation, and designing a meta planner at the platform level to drive the conversational procedure. Through experiments and ablation studies, we confirmed the effectiveness of our simulation approach and showed the promise for MATHVC to benefit real-life students in the future., Comment: Work in progress

Generative models are rapidly gaining popularity and being integrated into everyday applications, raising concerns over their safe use as various vulnerabilities are exposed. In light of this, the field of red teaming is undergoing fast-paced growth, highlighting the need for a comprehensive survey covering the entire pipeline and addressing emerging topics. Our extensive survey, which examines over 120 papers, introduces a taxonomy of fine-grained attack strategies grounded in the inherent capabilities of language models. Additionally, we have developed the "searcher" framework to unify various automatic red teaming approaches. Moreover, our survey covers novel areas including multimodal attacks and defenses, risks around LLM-based agents, overkill of harmless queries, and the balance between harmlessness and helpfulness.

Fine-tuning pre-trained models is a widely employed technique in numerous real-world applications. However, fine-tuning these models on new tasks can lead to unfair outcomes. This is due to the absence of generalization guarantees for fairness properties, regardless of whether the original pre-trained model was developed with fairness considerations. To tackle this issue, we introduce an efficient and robust fine-tuning framework specifically designed to mitigate biases in new tasks. Our empirical analysis shows that the parameters in the pre-trained model that affect predictions for different demographic groups are different, so based on this observation, we employ a transfer learning strategy that neutralizes the importance of these influential weights, determined using Fisher information across demographic groups. Additionally, we integrate this weight importance neutralization strategy with a matrix factorization technique, which provides a low-rank approximation of the weight matrix using fewer parameters, reducing the computational demands. Experiments on multiple pre-trained models and new tasks demonstrate the effectiveness of our method.

The recent success of Large Language Models (LLMs) has catalyzed an increasing interest in their self-correction capabilities. This paper presents a comprehensive investigation into the intrinsic self-correction of LLMs, attempting to address the ongoing debate about its feasibility. Our research has identified an important latent factor - the "confidence" of LLMs - during the self-correction process. Overlooking this factor may cause the models to over-criticize themselves, resulting in unreliable conclusions regarding the efficacy of self-correction. We have experimentally observed that LLMs possess the capability to understand the "confidence" in their own responses. It motivates us to develop an "If-or-Else" (IoE) prompting framework, designed to guide LLMs in assessing their own "confidence", facilitating intrinsic self-corrections. We conduct extensive experiments and demonstrate that our IoE-based Prompt can achieve a consistent improvement regarding the accuracy of self-corrected responses over the initial answers. Our study not only sheds light on the underlying factors affecting self-correction in LLMs, but also introduces a practical framework that utilizes the IoE prompting principle to efficiently improve self-correction capabilities with "confidence". The code is available at https://github.com/MBZUAI-CLeaR/IoE-Prompting.git., Comment: 12 figures, 9 tables

Large language models (LLMs) have achieved success in acting as agents, which interact with environments through tools such as search engines. However, LLMs are optimized for language generation instead of tool use during training or alignment, limiting their effectiveness as agents. To resolve this problem, previous work has first collected interaction trajectories between LLMs and environments, using only trajectories that successfully finished the task to fine-tune smaller models, making fine-tuning data scarce and acquiring it both difficult and costly. Discarding failed trajectories also leads to significant wastage of data and resources and limits the possible optimization paths during fine-tuning. In this paper, we argue that unsuccessful trajectories offer valuable insights, and LLMs can learn from these trajectories through appropriate quality control and fine-tuning strategies. By simply adding a prefix or suffix that tells the model whether to generate a successful trajectory during training, we improve model performance by a large margin on mathematical reasoning, multi-hop question answering, and strategic question answering tasks. We further analyze the inference results and find that our method provides a better trade-off between valuable information and errors in unsuccessful trajectories. To our knowledge, we are the first to demonstrate the value of negative trajectories and their application in agent-tunning scenarios. Our findings offer guidance for developing better agent-tuning methods and low-resource data usage techniques., Comment: Agent, LLM, Large Language Model

Objective: In cochlear implant users with residual acoustic hearing, compound action potentials (CAPs) can be evoked by acoustic (aCAP) or electric (eCAP) stimulation and recorded through the electrodes of the implant. We propose a novel computational model to simulate aCAPs and eCAPs in humans, considering the interaction between combined electric-acoustic stimulation that occurs in the auditory nerve. Methods: The model consists of three components: a 3D finite element method model of an implanted cochlea, a phenomenological single-neuron spiking model for electric-acoustic stimulation, and a physiological multi-compartment neuron model to simulate the individual nerve fiber contributions to the CAP. Results: The CAP morphologies closely resembled those known from humans. The spread of excitation derived from eCAPs by varying the recording electrode along the cochlear implant electrode array was consistent with published human data. The predicted CAP amplitude growth functions largely resembled human data, with deviations in absolute CAP amplitudes for acoustic stimulation. The model reproduced the suppression of eCAPs by simultaneously presented acoustic tone bursts for different masker frequencies and probe stimulation electrodes. Conclusion: The proposed model can simulate CAP responses to electric, acoustic, or combined electric-acoustic stimulation. It considers the dependence on stimulation and recording sites in the cochlea, as well as the interaction between electric and acoustic stimulation in the auditory nerve. Significance: The model enhances comprehension of CAPs and peripheral electric-acoustic interaction. It can be used in the future to investigate objective methods, such as hearing threshold assessment or estimation of neural health through aCAPs or eCAPs., Comment: This work has been submitted to the IEEE for possible publication

Deep equilibrium models (DEQs), as a typical implicit neural network, have demonstrated remarkable success on various tasks. There is, however, a lack of theoretical understanding of the connections and differences between implicit DEQs and explicit neural network models. In this paper, leveraging recent advances in random matrix theory (RMT), we perform an in-depth analysis on the eigenspectra of the conjugate kernel (CK) and neural tangent kernel (NTK) matrices for implicit DEQs, when the input data are drawn from a high-dimensional Gaussian mixture. We prove, in this setting, that the spectral behavior of these Implicit-CKs and NTKs depend on the DEQ activation function and initial weight variances, but only via a system of four nonlinear equations. As a direct consequence of this theoretical result, we demonstrate that a shallow explicit network can be carefully designed to produce the same CK or NTK as a given DEQ. Despite derived here for Gaussian mixture data, empirical results show the proposed theory and design principle also apply to popular real-world datasets., Comment: Accepted by ICML 2024

Stochastic Approximation (SA) is a widely used algorithmic approach in various fields, including optimization and reinforcement learning (RL). Among RL algorithms, Q-learning is particularly popular due to its empirical success. In this paper, we study asynchronous Q-learning with constant stepsize, which is commonly used in practice for its fast convergence. By connecting the constant stepsize Q-learning to a time-homogeneous Markov chain, we show the distributional convergence of the iterates in Wasserstein distance and establish its exponential convergence rate. We also establish a Central Limit Theory for Q-learning iterates, demonstrating the asymptotic normality of the averaged iterates. Moreover, we provide an explicit expansion of the asymptotic bias of the averaged iterate in stepsize. Specifically, the bias is proportional to the stepsize up to higher-order terms and we provide an explicit expression for the linear coefficient. This precise characterization of the bias allows the application of Richardson-Romberg (RR) extrapolation technique to construct a new estimate that is provably closer to the optimal Q function. Numerical results corroborate our theoretical finding on the improvement of the RR extrapolation method., Comment: 41 pages, 3 figures

Large language models (LLMs), exemplified by ChatGPT, have gained considerable attention for their excellent natural language processing capabilities. Nonetheless, these LLMs present many challenges, particularly in the realm of trustworthiness. Therefore, ensuring the trustworthiness of LLMs emerges as an important topic. This paper introduces TrustLLM, a comprehensive study of trustworthiness in LLMs, including principles for different dimensions of trustworthiness, established benchmark, evaluation, and analysis of trustworthiness for mainstream LLMs, and discussion of open challenges and future directions. Specifically, we first propose a set of principles for trustworthy LLMs that span eight different dimensions. Based on these principles, we further establish a benchmark across six dimensions including truthfulness, safety, fairness, robustness, privacy, and machine ethics. We then present a study evaluating 16 mainstream LLMs in TrustLLM, consisting of over 30 datasets. Our findings firstly show that in general trustworthiness and utility (i.e., functional effectiveness) are positively related. Secondly, our observations reveal that proprietary LLMs generally outperform most open-source counterparts in terms of trustworthiness, raising concerns about the potential risks of widely accessible open-source LLMs. However, a few open-source LLMs come very close to proprietary ones. Thirdly, it is important to note that some LLMs may be overly calibrated towards exhibiting trustworthiness, to the extent that they compromise their utility by mistakenly treating benign prompts as harmful and consequently not responding. Finally, we emphasize the importance of ensuring transparency not only in the models themselves but also in the technologies that underpin trustworthiness. Knowing the specific trustworthy technologies that have been employed is crucial for analyzing their effectiveness., Comment: This work is still under work and we welcome your contribution

Emotion significantly impacts our daily behaviors and interactions. While recent generative AI models, such as large language models, have shown impressive performance in various tasks, it remains unclear whether they truly comprehend emotions. This paper aims to address this gap by incorporating psychological theories to gain a holistic understanding of emotions in generative AI models. Specifically, we propose three approaches: 1) EmotionPrompt to enhance AI model performance, 2) EmotionAttack to impair AI model performance, and 3) EmotionDecode to explain the effects of emotional stimuli, both benign and malignant. Through extensive experiments involving language and multi-modal models on semantic understanding, logical reasoning, and generation tasks, we demonstrate that both textual and visual EmotionPrompt can boost the performance of AI models while EmotionAttack can hinder it. Additionally, EmotionDecode reveals that AI models can comprehend emotional stimuli akin to the mechanism of dopamine in the human brain. Our work heralds a novel avenue for exploring psychology to enhance our understanding of generative AI models., Comment: International Conference on Machine Learning (ICML) 2024; an extension to EmotionPrompt (arXiv:2307.11760)

Wasm runtime is a fundamental component in the Wasm ecosystem, as it directly impacts whether Wasm applications can be executed as expected. Bugs in Wasm runtime bugs are frequently reported, thus our research community has made a few attempts to design automated testing frameworks for detecting bugs in Wasm runtimes. However, existing testing frameworks are limited by the quality of test cases, i.e., they face challenges of generating both semantic-rich and syntactic-correct Wasm binaries, thus complicated bugs cannot be triggered. In this work, we present WRTester, a novel differential testing framework that can generated complicated Wasm test cases by disassembling and assembling of real-world Wasm binaries, which can trigger hidden inconsistencies among Wasm runtimes. For further pinpointing the root causes of unexpected behaviors, we design a runtime-agnostic root cause location method to accurately locate bugs. Extensive evaluation suggests that WRTester outperforms SOTA techniques in terms of both efficiency and effectiveness. We have uncovered 33 unique bugs in popular Wasm runtimes, among which 25 have been confirmed.

Discrimination can occur when the underlying unbiased labels are overwritten by an agent with potential bias, resulting in biased datasets that unfairly harm specific groups and cause classifiers to inherit these biases. In this paper, we demonstrate that despite only having access to the biased labels, it is possible to eliminate bias by filtering the fairest instances within the framework of confident learning. In the context of confident learning, low self-confidence usually indicates potential label errors; however, this is not always the case. Instances, particularly those from underrepresented groups, might exhibit low confidence scores for reasons other than labeling errors. To address this limitation, our approach employs truncation of the confidence score and extends the confidence interval of the probabilistic threshold. Additionally, we incorporate with co-teaching paradigm for providing a more robust and reliable selection of fair instances and effectively mitigating the adverse effects of biased labels. Through extensive experimentation and evaluation of various datasets, we demonstrate the efficacy of our approach in promoting fairness and reducing the impact of label bias in machine learning models.

Accurately detecting voiced intervals in speech signals is a critical step in pitch tracking and has numerous applications. While conventional signal processing methods and deep learning algorithms have been proposed for this task, their need to fine-tune threshold parameters for different datasets and limited generalization restrict their utility in real-world applications. To address these challenges, this study proposes a supervised voicing detection model that leverages recorded laryngograph data. The model is based on a densely-connected convolutional recurrent neural network (DC-CRN), and trained on data with reference voicing decisions extracted from laryngograph data sets. Pretraining is also investigated to improve the generalization ability of the model. The proposed model produces robust voicing detection results, outperforming other strong baseline methods, and generalizes well to unseen datasets. The source code of the proposed model with pretraining is provided along with the list of used laryngograph datasets to facilitate further research in this area.

Out-of-distribution (OOD) detection is essential in identifying test samples that deviate from the in-distribution (ID) data upon which a standard network is trained, ensuring network robustness and reliability. This paper introduces OOD knowledge distillation, a pioneering learning framework applicable whether or not training ID data is available, given a standard network. This framework harnesses unknown OOD-sensitive knowledge from the standard network to craft a certain binary classifier adept at distinguishing between ID and OOD samples. To accomplish this, we introduce Confidence Amendment (CA), an innovative methodology that transforms an OOD sample into an ID one while progressively amending prediction confidence derived from the standard network. This approach enables the simultaneous synthesis of both ID and OOD samples, each accompanied by an adjusted prediction confidence, thereby facilitating the training of a binary classifier sensitive to OOD. Theoretical analysis provides bounds on the generalization error of the binary classifier, demonstrating the pivotal role of confidence amendment in enhancing OOD sensitivity. Extensive experiments spanning various datasets and network architectures confirm the efficacy of the proposed method in detecting OOD samples.

Large language models (LLMs) have been widely used as agents to complete different tasks, such as personal assistance or event planning. While most of the work has focused on cooperation and collaboration between agents, little work explores competition, another important mechanism that promotes the development of society and economy. In this paper, we seek to examine the competition dynamics in LLM-based agents. We first propose a general framework for studying the competition between agents. Then, we implement a practical competitive environment using GPT-4 to simulate a virtual town with two types of agents, restaurant agents and customer agents. Specifically, the restaurant agents compete with each other to attract more customers, where competition encourages them to transform, such as cultivating new operating strategies. Simulation experiments reveal several interesting findings at the micro and macro levels, which align well with existing market and sociological theories. We hope that the framework and environment can be a promising testbed to study competition that fosters understanding of society. Code is available at: https://github.com/microsoft/competeai., Comment: International Conference on Machine Learning (ICML) 2024 Oral; 16 pages; code is at: https://github.com/microsoft/competeai

Large language models (LLMs) have showcased remarkable capabilities in understanding and generating language. However, their ability in comprehending ancient languages, particularly ancient Chinese, remains largely unexplored. To bridge this gap, we present ACLUE, an evaluation benchmark designed to assess the capability of language models in comprehending ancient Chinese. ACLUE consists of 15 tasks cover a range of skills, spanning phonetic, lexical, syntactic, semantic, inference and knowledge. Through the evaluation of eight state-of-the-art LLMs, we observed a noticeable disparity in their performance between modern Chinese and ancient Chinese. Among the assessed models, ChatGLM2 demonstrates the most remarkable performance, achieving an average score of 37.4%. We have made our code and data public available., Comment: Accepted at RANLP 2023

Significant advancements have occurred in the application of Large Language Models (LLMs) for various tasks and social simulations. Despite this, their capacities to coordinate within task-oriented social contexts are under-explored. Such capabilities are crucial if LLMs are to effectively mimic human-like social behavior and produce meaningful results. To bridge this gap, we introduce collaborative generative agents, endowing LLM-based Agents with consistent behavior patterns and task-solving abilities. We situate these agents in a simulated job fair environment as a case study to scrutinize their coordination skills. We propose a novel framework that equips collaborative generative agents with human-like reasoning abilities and specialized skills. Our evaluation demonstrates that these agents show promising performance. However, we also uncover limitations that hinder their effectiveness in more complex coordination tasks. Our work provides valuable insights into the role and evolution of LLMs in task-oriented social simulations.

In this study, we propose a novel deep spatio-temporal point process model, Deep Kernel Mixture Point Processes (DKMPP), that incorporates multimodal covariate information. DKMPP is an enhanced version of Deep Mixture Point Processes (DMPP), which uses a more flexible deep kernel to model complex relationships between events and covariate data, improving the model's expressiveness. To address the intractable training procedure of DKMPP due to the non-integrable deep kernel, we utilize an integration-free method based on score matching, and further improve efficiency by adopting a scalable denoising score matching method. Our experiments demonstrate that DKMPP and its corresponding score-based estimators outperform baseline models, showcasing the advantages of incorporating covariate information, utilizing a deep kernel, and employing score-based estimators.

In this paper, we introduce a novel training framework designed to comprehensively address the acoustic howling issue by examining its fundamental formation process. This framework integrates a neural network (NN) module into the closed-loop system during training with signals generated recursively on the fly to closely mimic the streaming process of acoustic howling suppression (AHS). The proposed recursive training strategy bridges the gap between training and real-world inference scenarios, marking a departure from previous NN-based methods that typically approach AHS as either noise suppression or acoustic echo cancellation. Within this framework, we explore two methodologies: one exclusively relying on NN and the other combining NN with the traditional Kalman filter. Additionally, we propose strategies, including howling detection and initialization using pre-trained offline models, to bolster trainability and expedite the training process. Experimental results validate that this framework offers a substantial improvement over previous methodologies for acoustic howling suppression., Comment: Paper in submission

Acoustic howling suppression (AHS) is a critical challenge in audio communication systems. In this paper, we propose a novel approach that leverages the power of neural networks (NN) to enhance the performance of traditional Kalman filter algorithms for AHS. Specifically, our method involves the integration of NN modules into the Kalman filter, enabling refining reference signal, a key factor in effective adaptive filtering, and estimating covariance metrics for the filter which are crucial for adaptability in dynamic conditions, thereby obtaining improved AHS performance. As a result, the proposed method achieves improved AHS performance compared to both standalone NN and Kalman filter methods. Experimental evaluations validate the effectiveness of our approach., Comment: Paper in submission

Enhancing speech signal quality in adverse acoustic environments is a persistent challenge in speech processing. Existing deep learning based enhancement methods often struggle to effectively remove background noise and reverberation in real-world scenarios, hampering listening experiences. To address these challenges, we propose a novel approach that uses pre-trained generative methods to resynthesize clean, anechoic speech from degraded inputs. This study leverages pre-trained vocoder or codec models to synthesize high-quality speech while enhancing robustness in challenging scenarios. Generative methods effectively handle information loss in speech signals, resulting in regenerated speech that has improved fidelity and reduced artifacts. By harnessing the capabilities of pre-trained models, we achieve faithful reproduction of the original speech in adverse conditions. Experimental evaluations on both simulated datasets and realistic samples demonstrate the effectiveness and robustness of our proposed methods. Especially by leveraging codec, we achieve superior subjective scores for both simulated and realistic recordings. The generated speech exhibits enhanced audio quality, reduced background noise, and reverberation. Our findings highlight the potential of pre-trained generative techniques in speech processing, particularly in scenarios where traditional methods falter. Demos are available at https://whmrtm.github.io/SoundResynthesis., Comment: Paper in submission

Designing materials with enhanced spin charge conversion, i.e., with high spin Hall conductivity (SHC) and low longitudinal electric conductivity (hence large spin Hall angle (SHA)), is a challenging task, especially in the presence of a vast chemical space for compositionally complex alloys (CCAs). In this work, focusing on the Ta-Nb-Hf-Zr-Ti system, we confirm that CCAs exhibit significant spin Hall conductivities and propose a multi-objective Bayesian optimization approach (MOBO) incorporated with active learning (AL) in order to screen for the optimal compositions with significant SHC and SHA. As a result, within less than 5 iterations we are able to target the TaZr-dominated systems displaying both high magnitudes of SHC (~-2.0 (10$^{-3}$ $\Omega$ cm)$^{-1}$) and SHA (~0.03). The SHC is mainly ascribed to the extrinsic skew scattering mechanism. Our work provides an efficient route for identifying new materials with significant SHE, which can be straightforwardly generalized to optimize other properties in a vast chemical space.

Emotional intelligence significantly impacts our daily behaviors and interactions. Although Large Language Models (LLMs) are increasingly viewed as a stride toward artificial general intelligence, exhibiting impressive performance in numerous tasks, it is still uncertain if LLMs can genuinely grasp psychological emotional stimuli. Understanding and responding to emotional cues gives humans a distinct advantage in problem-solving. In this paper, we take the first step towards exploring the ability of LLMs to understand emotional stimuli. To this end, we first conduct automatic experiments on 45 tasks using various LLMs, including Flan-T5-Large, Vicuna, Llama 2, BLOOM, ChatGPT, and GPT-4. Our tasks span deterministic and generative applications that represent comprehensive evaluation scenarios. Our automatic experiments show that LLMs have a grasp of emotional intelligence, and their performance can be improved with emotional prompts (which we call "EmotionPrompt" that combines the original prompt with emotional stimuli), e.g., 8.00% relative performance improvement in Instruction Induction and 115% in BIG-Bench. In addition to those deterministic tasks that can be automatically evaluated using existing metrics, we conducted a human study with 106 participants to assess the quality of generative tasks using both vanilla and emotional prompts. Our human study results demonstrate that EmotionPrompt significantly boosts the performance of generative tasks (10.9% average improvement in terms of performance, truthfulness, and responsibility metrics). We provide an in-depth discussion regarding why EmotionPrompt works for LLMs and the factors that may influence its performance. We posit that EmotionPrompt heralds a novel avenue for exploring interdisciplinary knowledge for human-LLMs interaction., Comment: Technical report; updated the std error for human study; short version (v1) was accepted by LLM@IJCAI'23; 32 pages; more work: https://llm-enhance.github.io/

Motivated by an extremal problem on graph-codes that links coding theory and graph theory, Alon recently proposed a question aiming to find the smallest number $t$ such that there is an edge coloring of $K_{n}$ by $t$ colors with no copy of given graph $H$ in which every color appears an even number of times. When $H=K_{4}$, the question of whether $n^{o(1)}$ colors are enough, was initially emphasized by Alon. Through modifications to the coloring functions originally designed by Mubayi, and Conlon, Fox, Lee and Sudakov, the question of $K_{4}$ has already been addressed. Expanding on this line of inquiry, we further study this new variant of the generalized Ramsey problem and provide a conclusively affirmative answer to Alon's question concerning $K_{5}$., Comment: Note added: Heath and Zerbib also proved the result on $K_{5}$ independently. arXiv:2307.01314

As the capabilities of large language models (LLMs) continue to advance, evaluating their performance becomes increasingly crucial and challenging. This paper aims to bridge this gap by introducing CMMLU, a comprehensive Chinese benchmark that covers various subjects, including natural science, social sciences, engineering, and humanities. We conduct a thorough evaluation of 18 advanced multilingual- and Chinese-oriented LLMs, assessing their performance across different subjects and settings. The results reveal that most existing LLMs struggle to achieve an average accuracy of 50%, even when provided with in-context examples and chain-of-thought prompts, whereas the random baseline stands at 25%. This highlights significant room for improvement in LLMs. Additionally, we conduct extensive experiments to identify factors impacting the models' performance and propose directions for enhancing LLMs. CMMLU fills the gap in evaluating the knowledge and reasoning capabilities of large language models within the Chinese context.

Chalcogenides, which refer to chalcogen anions, have attracted considerable attention in multiple fields of applications, such as optoelectronics, thermoelectrics, transparent contacts, and thin film transistors. In comparison to oxide counterparts, chalcogenides have demonstrated higher mobility and \textit{p}-type dopability, owing to larger orbital overlaps between metal-X covalent chemical bondings and higher-energy valence bands derived by p-orbitals. Despite the potential of chalcogenides, the number of successfully synthesized compounds remains relatively low compared to oxides, suggesting the presence of numerous unexplored chalcogenides with fascinating physical characteristics. In this study, we implemented a systematic high-throughput screening process combined with first-principles calculations on ternary chalcogenides using 34 crystal structure prototypes. We generated a computational material database containing over 400,000 compounds by exploiting the ion-substitution approach at different atomic sites with elements in the periodic table. The thermodynamic stabilities of the candidates were validated using the chalcogenides included in the Open Quantum Materials Database. Moreover, we trained a model based on Crystal Graph Convolutional Neural Networks to predict the thermodynamic stability of novel materials. Furthermore, we theoretically evaluated the electronic structures of the stable candidates using accurate hybrid functionals. A series of in-depth characteristics, including the carrier effective masses, electronic configuration, and photovoltaic conversion efficiency, was also investigated. Our work provides useful guidance for further experimental research in the synthesis and characterization of such chalcogenides as promising candidates, as well as charting the stability and optoelectronic performance of ternary chalcogenides.

Aberrations and multiple scattering in biological tissues critically distort light beams into highly complex speckle patterns. In this regard, digital optical phase conjugation (DOPC) is a promising technique enabling in-depth focusing. However, DOPC becomes challenging when using fluorescent guide-stars for four main reasons: The low photon budget available, the large spectral bandwidth of the fluorescent signal, the Stokes shift between the emission and the excitation wavelength, and the absence of reference beam preventing holographic measurement. Here, we demonstrate the possibility to focus a laser beam through multiple-scattering samples by measuring speckle fields in a single acquisition step with a reference-free, high-resolution wavefront sensor. By taking advantage of the large spectral bandwidth of forward multiply scattering samples, Digital Fluorescence Phase Conjugation (DFPC) is achieved to focus a laser beam at the excitation wavelength while measuring the broadband speckle field arising from a micron-sized fluorescent bead., Comment: 21 pages, 31 figures, 2 tables