Search

Self-anthropomorphism in robots manifests itself through their display of human-like characteristics in dialogue, such as expressing preferences and emotions. Our study systematically analyzes self-anthropomorphic expression within various dialogue datasets, outlining the contrasts between self-anthropomorphic and non-self-anthropomorphic responses in dialogue systems. We show significant differences in these two types of responses and propose transitioning from one type to the other. We also introduce Pix2Persona, a novel dataset aimed at developing ethical and engaging AI systems in various embodiments. This dataset preserves the original dialogues from existing corpora and enhances them with paired responses: self-anthropomorphic and non-self-anthropomorphic for each original bot response. Our work not only uncovers a new category of bot responses that were previously under-explored but also lays the groundwork for future studies about dynamically adjusting self-anthropomorphism levels in AI systems to align with ethical standards and user expectations., Comment: Findings of EMNLP 2024, 19 pages

Diffusion models have revolutionized image generation, and their extension to video generation has shown promise. However, current video diffusion models~(VDMs) rely on a scalar timestep variable applied at the clip level, which limits their ability to model complex temporal dependencies needed for various tasks like image-to-video generation. To address this limitation, we propose a frame-aware video diffusion model~(FVDM), which introduces a novel vectorized timestep variable~(VTV). Unlike conventional VDMs, our approach allows each frame to follow an independent noise schedule, enhancing the model's capacity to capture fine-grained temporal dependencies. FVDM's flexibility is demonstrated across multiple tasks, including standard video generation, image-to-video generation, video interpolation, and long video synthesis. Through a diverse set of VTV configurations, we achieve superior quality in generated videos, overcoming challenges such as catastrophic forgetting during fine-tuning and limited generalizability in zero-shot methods.Our empirical evaluations show that FVDM outperforms state-of-the-art methods in video generation quality, while also excelling in extended tasks. By addressing fundamental shortcomings in existing VDMs, FVDM sets a new paradigm in video synthesis, offering a robust framework with significant implications for generative modeling and multimedia applications., Comment: Code at https://github.com/Yaofang-Liu/FVDM

Statistical inference with non-probability survey samples is an emerging topic in survey sampling and official statistics and has gained increased attention from researchers and practitioners in the field. Much of the existing literature, however, assumes that the participation mechanism for non-probability samples is ignorable. In this paper, we develop a pseudo-likelihood approach to estimate participation probabilities for nonignorable non-probability samples when auxiliary information is available from an existing reference probability sample. We further construct three estimators for the finite population mean using regression-based prediction, inverse probability weighting (IPW), and augmented IPW estimators, and study their asymptotic properties. Variance estimation for the proposed methods is considered within the same framework. The efficiency of our proposed methods is demonstrated through simulation studies and a real data analysis using the ESPACOV survey on the effects of the COVID-19 pandemic in Spain., Comment: 34 pages, 0 figure

Recent advancements in large language models (LLMs) have revolutionized code intelligence by improving programming productivity and alleviating challenges faced by software developers. To further improve the performance of LLMs on specific code intelligence tasks and reduce training costs, researchers reveal a new capability of LLMs: in-context learning (ICL). ICL allows LLMs to learn from a few demonstrations within a specific context, achieving impressive results without parameter updating. However, the rise of ICL introduces new security vulnerabilities in the code intelligence field. In this paper, we explore a novel security scenario based on the ICL paradigm, where attackers act as third-party ICL agencies and provide users with bad ICL content to mislead LLMs outputs in code intelligence tasks. Our study demonstrates the feasibility and risks of such a scenario, revealing how attackers can leverage malicious demonstrations to construct bad ICL content and induce LLMs to produce incorrect outputs, posing significant threats to system security. We propose a novel method to construct bad ICL content called DICE, which is composed of two stages: Demonstration Selection and Bad ICL Construction, constructing targeted bad ICL content based on the user query and transferable across different query inputs. Ultimately, our findings emphasize the critical importance of securing ICL mechanisms to protect code intelligence systems from adversarial manipulation., Comment: 17 pages, 5 figures

The Diffusion Model has not only garnered noteworthy achievements in the realm of image generation but has also demonstrated its potential as an effective pretraining method utilizing unlabeled data. Drawing from the extensive potential unveiled by the Diffusion Model in both semantic correspondence and open vocabulary segmentation, our work initiates an investigation into employing the Latent Diffusion Model for Few-shot Semantic Segmentation. Recently, inspired by the in-context learning ability of large language models, Few-shot Semantic Segmentation has evolved into In-context Segmentation tasks, morphing into a crucial element in assessing generalist segmentation models. In this context, we concentrate on Few-shot Semantic Segmentation, establishing a solid foundation for the future development of a Diffusion-based generalist model for segmentation. Our initial focus lies in understanding how to facilitate interaction between the query image and the support image, resulting in the proposal of a KV fusion method within the self-attention framework. Subsequently, we delve deeper into optimizing the infusion of information from the support mask and simultaneously re-evaluating how to provide reasonable supervision from the query mask. Based on our analysis, we establish a simple and effective framework named DiffewS, maximally retaining the original Latent Diffusion Model's generative framework and effectively utilizing the pre-training prior. Experimental results demonstrate that our method significantly outperforms the previous SOTA models in multiple settings., Comment: Accepted to Proc. Annual Conference on Neural Information Processing Systems (NeurIPS) 2024. Webpage: https://github.com/aim-uofa/DiffewS

Vision Large Language Models (VLLMs) are transforming the intersection of computer vision and natural language processing. Nonetheless, the potential of using visual prompts for emotion recognition in these models remains largely unexplored and untapped. Traditional methods in VLLMs struggle with spatial localization and often discard valuable global context. To address this problem, we propose a Set-of-Vision prompting (SoV) approach that enhances zero-shot emotion recognition by using spatial information, such as bounding boxes and facial landmarks, to mark targets precisely. SoV improves accuracy in face count and emotion categorization while preserving the enriched image context. Through a battery of experimentation and analysis of recent commercial or open-source VLLMs, we evaluate the SoV model's ability to comprehend facial expressions in natural environments. Our findings demonstrate the effectiveness of integrating spatial visual prompts into VLLMs for improving emotion recognition performance., Comment: Accepted by EMNLP2024 (Main, Long paper)

Research into the external behaviors and internal mechanisms of large language models (LLMs) has shown promise in addressing complex tasks in the physical world. Studies suggest that powerful LLMs, like GPT-4, are beginning to exhibit human-like cognitive abilities, including planning, reasoning, and reflection. In this paper, we introduce a research line and methodology called LLM Psychology, leveraging human psychology experiments to investigate the cognitive behaviors and mechanisms of LLMs. We migrate the Typoglycemia phenomenon from psychology to explore the "mind" of LLMs. Unlike human brains, which rely on context and word patterns to comprehend scrambled text, LLMs use distinct encoding and decoding processes. Through Typoglycemia experiments at the character, word, and sentence levels, we observe: (I) LLMs demonstrate human-like behaviors on a macro scale, such as lower task accuracy and higher token/time consumption; (II) LLMs exhibit varying robustness to scrambled input, making Typoglycemia a benchmark for model evaluation without new datasets; (III) Different task types have varying impacts, with complex logical tasks (e.g., math) being more challenging in scrambled form; (IV) Each LLM has a unique and consistent "cognitive pattern" across tasks, revealing general mechanisms in its psychology process. We provide an in-depth analysis of hidden layers to explain these phenomena, paving the way for future research in LLM Psychology and deeper interpretability.

Solving partial differential equations (PDEs) serves as a cornerstone for modeling complex dynamical systems. Recent progresses have demonstrated grand benefits of data-driven neural-based models for predicting spatiotemporal dynamics (e.g., tremendous speedup gain compared with classical numerical methods). However, most existing neural models rely on rich training data, have limited extrapolation and generalization abilities, and suffer to produce precise or reliable physical prediction under intricate conditions (e.g., irregular mesh or geometry, complex boundary conditions, diverse PDE parameters, etc.). To this end, we propose a new graph learning approach, namely, Physics-encoded Message Passing Graph Network (PhyMPGN), to model spatiotemporal PDE systems on irregular meshes given small training datasets. Specifically, we incorporate a GNN into a numerical integrator to approximate the temporal marching of spatiotemporal dynamics for a given PDE system. Considering that many physical phenomena are governed by diffusion processes, we further design a learnable Laplace block, which encodes the discrete Laplace-Beltrami operator, to aid and guide the GNN learning in a physically feasible solution space. A boundary condition padding strategy is also designed to improve the model convergence and accuracy. Extensive experiments demonstrate that PhyMPGN is capable of accurately predicting various types of spatiotemporal dynamics on coarse unstructured meshes, consistently achieves the state-of-the-art results, and outperforms other baselines with considerable gains.

Task-specific fine-tuning is essential for the deployment of large language models (LLMs), but it requires significant computational resources and time. Existing solutions have proposed coreset selection methods to improve data efficiency and reduce model training overhead, but they still have limitations: 1) Overlooking valuable samples at high pruning rates, which degrades the coreset's performance. 2) Requiring high time overhead during coreset selection to fine-tune and evaluate the target LLM. In this paper, we introduce STAFF, a speculative coreset selection method. STAFF leverages a small model from the same family as the target LLM to efficiently estimate data scores and then verifies the scores on the target LLM to accurately identify and allocate more selection budget to important regions while maintaining coverage of easy regions. We evaluate STAFF on three LLMs and three downstream tasks and show that STAFF improves the performance of SOTA methods by up to 54.3% and reduces selection overhead by up to 70.5% at different pruning rates. Furthermore, we observe that the coreset selected by STAFF at low pruning rates (i.e., 20%) can even obtain better fine-tuning performance than the full dataset., Comment: 20 pages, 4 figures, 14 tables

Systemic risk is receiving increasing attention in the insurance industry, as these risks can have severe impacts on the entire financial system. In this paper, we propose a multi-dimensional L/'{e}vy process-based renewal risk model with heterogeneous insurance claims, where every dimension indicates a business line of an insurer. We use the systemic expected shortfall (SES) and marginal expected shortfall (MES) defined with a Value-at-Risk (VaR) target level as the measurement of systemic risks. Assuming that all the claim sizes are pairwise asymptotically independent (PAI), we derive asymptotic formulas for the tail probabilities of discounted aggregate claims and total loss, which holds uniformly for all time horizons. We further obtain the asymptotics of the above systemic risk measures. The main technical issues involve the treatment of uniform convergence in the dynamic time setting. Finally, we conduct a Monte Carlo numerical study and verify that our asymptotics are accurate and convenient in computation., Comment: 30 pages, 2 figures

As our lives, our businesses, and indeed our world economy become increasingly reliant on the secure operation of many interconnected software systems, the software engineering research community is faced with unprecedented research challenges, but also with exciting new opportunities. In this roadmap paper, we outline our vision of Software Security Analysis for the software systems of the future. Given the recent advances in generative AI, we need new methods to evaluate and maximize the security of code co-written by machines. As our software systems become increasingly heterogeneous, we need practical approaches that work even if some functions are automatically generated, e.g., by deep neural networks. As software systems depend evermore on the software supply chain, we need tools that scale to an entire ecosystem. What kind of vulnerabilities exist in future systems and how do we detect them? When all the shallow bugs are found, how do we discover vulnerabilities hidden deeply in the system? Assuming we cannot find all security flaws, how can we nevertheless protect our system? To answer these questions, we start our research roadmap with a survey of recent advances in software security, then discuss open challenges and opportunities, and conclude with a long-term perspective for the field., Comment: 25 pages single-column, Invited article for ACM TOSEM

Influence functions are a popular tool for attributing a model's output to training data. The traditional approach relies on the calculation of inverse Hessian-vector products (iHVP), but the classical solver "Linear time Stochastic Second-order Algorithm" (LiSSA, Agarwal et al. (2017)) is often deemed impractical for large models due to expensive computation and hyperparameter tuning. We show that the three hyperparameters -- the scaling factor, the batch size, and the number of steps -- can be chosen depending on the spectral properties of the Hessian, particularly its trace and largest eigenvalue. By evaluating with random sketching (Swartworth and Woodruff, 2023), we find that the batch size has to be sufficiently large for LiSSA to converge; however, for all of the models we consider, the requirement is mild. We confirm our findings empirically by comparing to Proximal Bregman Retraining Functions (PBRF, Bae et al. (2022)). Finally, we discuss what role the inverse Hessian plays in calculating the influence., Comment: 23 pages, 7 figures, 4 tables

We report the fabrication and characteristics of GaAs/Si p+/n+ heterojunction tunnel diodes. These diodes were fabricated via grafting the freestanding single-crystalline p-type degenerately doped GaAs (4E19 cm-3) nanomembrane (NM) onto single-crystalline n-type Si (5E19 cm-3) substrate. At the heterointerface, an amorphous ultrathin oxygen-enriched layer (UOL) was intentionally engineered through chemical oxidation and atomic layer deposition (ALD). Scanning transmission electron microscopy (STEM) confirmed the formation of the UOL and the single crystallinity of the grafted junction. The resulting tunnel diodes consistently exhibited negative differential resistance (NDR) behavior at room temperature, with a high maximum peak-to-valley current ratio (PVCR) of 36.38, valley voltages ranging from 1.3 to 1.8 V, and a peak tunneling current density of 0.95 kA/cm2. This study not only highlights the critical roles of the UOL as both an interface improvement layer and a quantum tunneling medium, but also establishes "semiconductor grafting" as an effective and versatile method for high-performance, lattice-mismatched heterojunction devices., Comment: 4 pages, 5 figures

Knowledge of the global magnetic field distribution and its evolution on the Sun's surface is crucial for modeling the coronal magnetic field, understanding solar wind dynamics, computing the heliospheric open flux distribution and predicting solar cycle strength. As the far side of the Sun cannot be observed directly and high-latitude observations always suffer from projection effects, we often rely on surface flux transport simulations (SFT) to model long-term global magnetic field distribution. Meridional circulation, the large-scale north-south component of the surface flow profile, is one of the key components of the SFT simulation that requires further constraints near high latitudes. Prediction of the photospheric magnetic field distribution requires knowledge of the flow profile in the future, which demands reconstruction of that same flow at the current time so that it can be estimated at a later time. By performing Observing System Simulation Experiments, we demonstrate how the Ensemble Kalman Filter technique, when used with a SFT model, can be utilized to make ``posterior'' estimates of flow profiles into the future that can be used to drive the model forward to forecast photospheric magnetic field distribution., Comment: Accepted for publication in The Astrophysical Journal

The rise of malicious packages in public registries poses a significant threat to software supply chain (SSC) security. Although academia and industry employ methods like software composition analysis (SCA) to address this issue, existing approaches often lack timely and comprehensive intelligence updates. This paper introduces PackageIntel, a novel platform that revolutionizes the collection, processing, and retrieval of malicious package intelligence. By utilizing exhaustive search techniques, snowball sampling from diverse sources, and large language models (LLMs) with specialized prompts, PackageIntel ensures enhanced coverage, timeliness, and accuracy. We have developed a comprehensive database containing 20,692 malicious NPM and PyPI packages sourced from 21 distinct intelligence repositories. Empirical evaluations demonstrate that PackageIntel achieves a precision of 98.6% and an F1 score of 92.0 in intelligence extraction. Additionally, it detects threats on average 70% earlier than leading databases like Snyk and OSV, and operates cost-effectively at $0.094 per intelligence piece. The platform has successfully identified and reported over 1,000 malicious packages in downstream package manager mirror registries. This research provides a robust, efficient, and timely solution for identifying and mitigating threats within the software supply chain ecosystem.

In recent years, Large Language Models (LLMs) have gained widespread use, raising concerns about their security. Traditional jailbreak attacks, which often rely on the model internal information or have limitations when exploring the unsafe behavior of the victim model, limiting their reducing their general applicability. In this paper, we introduce PathSeeker, a novel black-box jailbreak method, which is inspired by the game of rats escaping a maze. We think that each LLM has its unique "security maze", and attackers attempt to find the exit learning from the received feedback and their accumulated experience to compromise the target LLM's security defences. Our approach leverages multi-agent reinforcement learning, where smaller models collaborate to guide the main LLM in performing mutation operations to achieve the attack objectives. By progressively modifying inputs based on the model's feedback, our system induces richer, harmful responses. During our manual attempts to perform jailbreak attacks, we found that the vocabulary of the response of the target model gradually became richer and eventually produced harmful responses. Based on the observation, we also introduce a reward mechanism that exploits the expansion of vocabulary richness in LLM responses to weaken security constraints. Our method outperforms five state-of-the-art attack techniques when tested across 13 commercial and open-source LLMs, achieving high attack success rates, especially in strongly aligned commercial models like GPT-4o-mini, Claude-3.5, and GLM-4-air with strong safety alignment. This study aims to improve the understanding of LLM security vulnerabilities and we hope that this sturdy can contribute to the development of more robust defenses., Comment: update the abstract and cite a new related work

In recent years, the e-commerce industry has seen a rapid increase in the demand for advanced AI-driven customer service solutions. Traditional cloud-based models face limitations in terms of latency, personalized services, and privacy concerns. Furthermore, end devices often lack the computational resources to deploy large AI models effectively. In this paper, we propose an innovative End-Cloud Collaboration (ECC) framework for advanced AI customer service in e-commerce. This framework integrates the advantages of large cloud models and mid/small-sized end models by deeply exploring the generalization potential of cloud models and effectively utilizing the computing power resources of terminal chips, alleviating the strain on computing resources to some extent. Specifically, the large cloud model acts as a teacher, guiding and promoting the learning of the end model, which significantly reduces the end model's reliance on large-scale, high-quality data and thereby addresses the data bottleneck in traditional end model training, offering a new paradigm for the rapid deployment of industry applications. Additionally, we introduce an online evolutive learning strategy that enables the end model to continuously iterate and upgrade based on guidance from the cloud model and real-time user feedback. This strategy ensures that the model can flexibly adapt to the rapid changes in application scenarios while avoiding the uploading of sensitive information by performing local fine-tuning, achieving the dual goals of privacy protection and personalized service. %We make systematic contributions to the customized model fine-tuning methods in the e-commerce domain. To conclude, we implement in-depth corpus collection (e.g., data organization, cleaning, and preprocessing) and train an ECC-based industry-specific model for e-commerce customer service., Comment: Accepted by 2024 IEEE 10th World Forum on Internet of Things (WF-IoT)

In this paper, we present a novel approach, called LogicPro, to enhance Large Language Models (LLMs) complex Logical reasoning through Program Examples. We do this effectively by simply utilizing widely available algorithmic problems and their code solutions. First, we constructed diverse test samples input based on algorithmic questions and code solutions. Then, we designed different complex reasoning questions based on algorithmic problems and test samples. Finally, combining the intermediate variable outputs of the code solutions and the complex reasoning questions, we derived the reasoning process and the final answer. With this approach, we can construct a dataset that is sufficiently difficult (all models are ineffective), diverse (synthesized from 2,360 different algorithmic questions), and scalable (building different test samples and collecting more algorithmic questions). In addition, we obtain a high-quality reasoning process guided by the values of intermediate variables. As a result, our approach achieves significant improvements in multiple models for the BBH$^{27}$, GSM8K, HellSwag, Logicqa, Reclor, and RTE datasets, outperforming a wide range of existing reasoning datasets.

Large Language models have achieved impressive performance in automated software engineering. Extensive efforts have been made to evaluate the abilities of code LLMs in various aspects, with an increasing number of benchmarks and evaluation frameworks proposed. Apart from the most sought-after capability of code generation, the capability of code comprehension is being granted growing attention. Nevertheless, existing works assessing the code comprehension capability of LLMs exhibit varied limitations. Evaluation frameworks like CRUXEval and REval usually focus on code reasoning tasks over a certain input case, leading to a limited range of execution traces covered, resulting in a loss in code semantics examined and the inability to assess the comprehensive understanding of LLMs concerning the target program. To tackle the challenges above, we propose SpecEval, a novel black-box evaluation framework to evaluate code comprehension in LLMs via program specifications. Inspired by the idea that specifications can comprehensively articulate program behaviors concerning all possible execution traces, we employ formal specifications to represent program semantics and perform thorough evaluations. In particular, four specification-related tasks are designed to assess the capability of LLMs from basic to advanced levels. Moreover, counterfactual analysis is conducted to study the performance variance of LLMs under semantics-preserving perturbations, and progressive consistency analysis is performed to study the performance consistency of LLMs over a series of tasks with sequential dependence. Systematic experiments are conducted on six state-of-the-art LLMs. Experimental results present a below-satisfactory performance of LLMs on specification-related tasks, revealing the limitations of existing LLMs in articulating program semantics, underscoring future directions for enhancement.

Convolutional neural network (CNN) performs well in Hyperspectral Image (HSI) classification tasks, but its high energy consumption and complex network structure make it difficult to directly apply it to edge computing devices. At present, spiking neural networks (SNN) have developed rapidly in HSI classification tasks due to their low energy consumption and event driven characteristics. However, it usually requires a longer time step to achieve optimal accuracy. In response to the above problems, this paper builds a spiking neural network (SNN-SWMR) based on the leaky integrate-and-fire (LIF) neuron model for HSI classification tasks. The network uses the spiking width mixed residual (SWMR) module as the basic unit to perform feature extraction operations. The spiking width mixed residual module is composed of spiking mixed convolution (SMC), which can effectively extract spatial-spectral features. Secondly, this paper designs a simple and efficient arcsine approximate derivative (AAD), which solves the non-differentiable problem of spike firing by fitting the Dirac function. Through AAD, we can directly train supervised spike neural networks. Finally, this paper conducts comparative experiments with multiple advanced HSI classification algorithms based on spiking neural networks on six public hyperspectral data sets. Experimental results show that the AAD function has strong robustness and a good fitting effect. Meanwhile, compared with other algorithms, SNN-SWMR requires a time step reduction of about 84%, training time, and testing time reduction of about 63% and 70% at the same accuracy. This study solves the key problem of SNN based HSI classification algorithms, which has important practical significance for promoting the practical application of HSI classification algorithms in edge devices such as spaceborne and airborne devices., Comment: 15pages,12figures

Phase transition is a fundamental phenomenon in condensed matter physics, in which states of matter transform to each other with various critical behaviors under different conditions. The magnetic martensitic transformation features significant multi-caloric effects that benefit the solid-state cooling or heat pumping. Meanwhile, the electronic topological transition (ETT) driven by pressure has been rarely reported in martensitic systems. Here, the modulation effects of hydrostatic pressure on phase transitions in a magnetic martensitic alloy are reported. Owing to the huge volume expansion during the transition, the martensitic transition temperature is driven from 339 to 273 K by pressure within 1 GPa, resulting in highly tunable giant baro- and magneto-caloric effects (BCE and MCE) in a wide working temperature range. Interestingly, an ETT was further induced by pressure in the martensite phase, with a sudden drop of the measured saturation magnetization around 0.6 GPa. First-principles calculations reveal a sharp change in the density of states (DOS) due to the orbit shift around the Fermi level at the same pressure and reproduce the experimental observation of magnetization. Besides, the ETT is accompanied by remarkable changes in the lattice parameters and the unit-cell orthorhombicity. The study provides insight into pressure-modulated exotic phase-transition phenomena in magnetic martensitic systems., Comment: 4 figs

Group IV GeSn double-heterostructure (DHS) lasers offer unique advantages of a direct bandgap and CMOS compatibility. However, further improvements in laser performance have been bottlenecked by limited junction properties of GeSn through conventional epitaxy and wafer bonding. This work leverages semiconductor grafting to synthesize and characterize optically pumped ridge edge-emitting lasers (EELs) with an AlGaAs nanomembrane (NM) transfer-printed onto an epitaxially grown GeSn substrate, interfaced by an ultrathin Al2O3 layer. The grafted AlGaAs/GeSn DHS lasers show a lasing threshold of 11.06 mW at 77 K and a maximum lasing temperature of 130 K. These results highlight the potential of the grafting technique for enhancing charge carrier and optical field confinements, paving the way for room-temperature electrically injected GeSn lasers., Comment: 5 pages, 5 figures. Supplementary Information included

All-d-metal full-Heusler alloys possess superior mechanical properties and high spin polarization, which would play an important role in spintronic applications. Despite this, their electrical and thermal transport properties have not been comprehensively investigated till now. In this work, we present an analysis on the evolution of structural, magnetic and transport properties of Cr- and Ti-substituted Fe2CrV all-d-metal Heusler alloys by combining theoretical calculations and experiments. Both series of alloys crystallize in Hg2CuTi-type structure. With increasing Ti doping, the calculated total magnetic moments of Fe50Cr25V25-xTix decrease linearly. The experimental saturation magnetization is highly consistent with theoretical calculations and Slater-Pauling rule when x < 4, indicating the highly ordered atomic occupation. The magnetization and Curie temperature can be significantly tuned by altering spin polarizations and exchange interactions. The introduction of the foreign atom, Ti, results in a linear increase in residual resistivity, while electron-phonon scattering keeps relatively constant. The maximum values for electrical and thermal transport properties are observed in the stoichiometric Fe2CrV composition., Comment: 6 figs and 4 tables

Autonomous driving systems (ADSs) have undergone remarkable development and are increasingly employed in safety-critical applications. However, recently reported data on fatal accidents involving ADSs suggests that the desired level of safety has not yet been fully achieved. Consequently, there is a growing need for more comprehensive and targeted testing approaches to ensure safe driving. Scenarios from real-world accident reports provide valuable resources for ADS testing, including critical scenarios and high-quality seeds. However, existing scenario reconstruction methods from accident reports often exhibit limited accuracy in information extraction. Moreover, due to the diversity and complexity of road environments, matching current accident information with the simulation map data for reconstruction poses significant challenges. In this paper, we design and implement SoVAR, a tool for automatically generating road-generalizable scenarios from accident reports. SoVAR utilizes well-designed prompts with linguistic patterns to guide the large language model in extracting accident information from textual data. Subsequently, it formulates and solves accident-related constraints in conjunction with the extracted accident information to generate accident trajectories. Finally, SoVAR reconstructs accident scenarios on various map structures and converts them into test scenarios to evaluate its capability to detect defects in industrial ADSs. We experiment with SoVAR, using accident reports from the National Highway Traffic Safety Administration's database to generate test scenarios for the industrial-grade ADS Apollo. The experimental findings demonstrate that SoVAR can effectively generate generalized accident scenarios across different road structures. Furthermore, the results confirm that SoVAR identified 5 distinct safety violation types that contributed to the crash of Baidu Apollo.

Fueled by the Large Language Models (LLMs) wave, Large Visual-Language Models (LVLMs) have emerged as a pivotal advancement, bridging the gap between image and text. However, video making it challenging for LVLMs to perform adequately due to the complexity of the relationship between language and spatial-temporal data structure. Recent Large Video-Language Models (LVidLMs) align feature of static visual data like image into latent space of language feature, by general multi-modal tasks to leverage abilities of LLMs sufficiently. In this paper, we explore fine-grained alignment approach via object trajectory for different modalities across both spatial and temporal dimensions simultaneously. Thus, we propose a novel LVidLM by trajectory-guided Pixel-Temporal Alignment, dubbed PiTe, that exhibits promising applicable model property. To achieve fine-grained video-language alignment, we curate a multi-modal pre-training dataset PiTe-143k, the dataset provision of moving trajectories in pixel level for all individual objects, that appear and mention in the video and caption both, by our automatic annotation pipeline. Meanwhile, PiTe demonstrates astounding capabilities on myriad video-related multi-modal tasks through beat the state-of-the-art methods by a large margin.

Decentralized federated learning (DFL) uses peer-to-peer communication to avoid the single point of failure problem in federated learning and has been considered an attractive solution for machine learning tasks on distributed devices. We provide the first solution to a fundamental network problem of DFL: what overlay network should DFL use to achieve fast training of highly accurate models, low communication, and decentralized construction and maintenance? Overlay topologies of DFL have been investigated, but no existing DFL topology includes decentralized protocols for network construction and topology maintenance. Without these protocols, DFL cannot run in practice. This work presents an overlay network, called FedLay, which provides fast training and low communication cost for practical DFL. FedLay is the first solution for constructing near-random regular topologies in a decentralized manner and maintaining the topologies under node joins and failures. Experiments based on prototype implementation and simulations show that FedLay achieves the fastest model convergence and highest accuracy on real datasets compared to existing DFL solutions while incurring small communication costs and being resilient to node joins and failures.

Accurate crystal structure determination is critical across all scientific disciplines involving crystalline materials. However, solving and refining inorganic crystal structures from powder X-ray diffraction (PXRD) data is traditionally a labor-intensive and time-consuming process that demands substantial expertise. In this work, we introduce PXRDGen, an end-to-end neural network that determines crystal structures by learning joint structural distributions from experimentally stable crystals and their PXRD, producing atomically accurate structures refined through PXRD data. PXRDGen integrates a pretrained XRD encoder, a diffusion/flow-based structure generator, and a Rietveld refinement module, enabling the solution of structures with unparalleled accuracy in a matter of seconds. Evaluation on MP-20 inorganic dataset reveals a remarkable matching rate of 82% (1 sample) and 96% (20 samples) for valid compounds, with Root Mean Square Error (RMSE) approaching the precision limits of Rietveld refinement. PXRDGen effectively tackles key challenges in XRD, such as the precise localization of light atoms, differentiation of neighboring elements, and resolution of overlapping peaks. Overall, PXRDGen marks a significant advancement in the automated determination of crystal structures from powder diffraction data.

Generative models aim to simulate realistic effects of various actions across different contexts, from text generation to visual effects. Despite efforts to build real-world simulators, leveraging generative models for virtual worlds, like financial markets, remains underexplored. In financial markets, generative models can simulate market effects of various behaviors, enabling interaction with market scenes and players, and training strategies without financial risk. This simulation relies on the finest structured data in financial market like orders thus building the finest realistic simulation. We propose Large Market Model (LMM), an order-level generative foundation model, for financial market simulation, akin to language modeling in the digital world. Our financial Market Simulation engine (MarS), powered by LMM, addresses the need for realistic, interactive and controllable order generation. Key objectives of this paper include evaluating LMM's scaling law in financial markets, assessing MarS's realism, balancing controlled generation with market impact, and demonstrating MarS's potential applications. We showcase MarS as a forecast tool, detection system, analysis platform, and agent training environment. Our contributions include pioneering a generative model for financial markets, designing MarS to meet domain-specific needs, and demonstrating MarS-based applications' industry potential., Comment: 19 pages, 12 figures

A notable feature of the elephant trunk is the pronounced wrinkling that enables its great flexibility. Here, we devise a general mathematical model that accounts for the characteristic skin wrinkles formed during morphogenesis in the elephant trunk. Using physically realistic parameters and operating within the theoretical framework of nonlinear morphoelasticity, we elucidate analytically and numerically the effect of skin thickness, relative stiffness, and differential growth on the physiological pattern of transverse wrinkles distributed along the trunk. We conclude that since the skin and muscle components have similar material properties, geometric parameters, such as curvature, play an important role. In particular, our model predicts that, in the proximal region close to the skull, where the curvature is lower, fewer wrinkles form and will form sooner than in the distal narrower region, where more wrinkles develop. Similarly, less wrinkling is found on the ventral side, which is flatter, compared to the dorsal side. In summary, the mechanical compatibility between the skin and the muscle enables them to grow seamlessly, while the wrinkled skin acts as a protective barrier that is both thicker and more flexible than the unwrinkled skin.

In this paper, we propose two novel multi-agent systems for the resource allocation problems (RAPs) and consensus-based distributed optimization problems. Different from existing distributed optimal approaches, we propose the new time-base generators (TBGs) for predefined-time non-convex optimization. Leveraging the proposed time-base generator, we study the roughness and boundedness of Lyapunov function based on TBGs. We prove that our approach achieves predefined-time approximate convergence to the optimal solution if the cost functions exhibit non-strongly convex or even non-convex characteristics. Furthermore, we prove that our approaches converge to the optimal solution if cost functions are generalized smoothness, and exhibit faster convergence rate and CPU speed. Finally, we present numerous numerical simulation examples to confirm the effectiveness of our approaches.

Recently, we notice that a pressure-based lattice Boltzmann (LB) method was established to recover the volume-averaged Navier-Stokes equations (VANSE), which serve as the cornerstone of various fluid-solid multiphase models. It decouples the pressure from density and exhibits excellent numerical performance, however, the widely adopted density-based LB scheme still suffers from significant spurious velocities and inconsistency with VANSE. To remedy this issue, a multiple-relaxation-time LB method is devised in this work, which incorporates a provisional equation of state in an adjusted density equilibrium distribution to decouple the void fraction from density. The Galilean invariance of the recovered VANSE is guaranteed by introducing a penalty source term in moment space, effectively eliminating unwanted numerical errors. Through the Chapman-Enskog analysis and detailed numerical validations, this novel method is proved to be capable of recovering VANSE with second-order accuracy consistently, and well-suited for handling void fraction fields with large gradients and spatiotemporal distributions., Comment: 23 pages

The recent advances in large language models (LLMs) have significantly expanded their applications across various fields such as language generation, summarization, and complex question answering. However, their application to privacy compliance and technical privacy reviews remains under-explored, raising critical concerns about their ability to adhere to global privacy standards and protect sensitive user data. This paper seeks to address this gap by providing a comprehensive case study evaluating LLMs' performance in privacy-related tasks such as privacy information extraction (PIE), legal and regulatory key point detection (KPD), and question answering (QA) with respect to privacy policies and data protection regulations. We introduce a Privacy Technical Review (PTR) framework, highlighting its role in mitigating privacy risks during the software development life-cycle. Through an empirical assessment, we investigate the capacity of several prominent LLMs, including BERT, GPT-3.5, GPT-4, and custom models, in executing privacy compliance checks and technical privacy reviews. Our experiments benchmark the models across multiple dimensions, focusing on their precision, recall, and F1-scores in extracting privacy-sensitive information and detecting key regulatory compliance points. While LLMs show promise in automating privacy reviews and identifying regulatory discrepancies, significant gaps persist in their ability to fully comply with evolving legal standards. We provide actionable recommendations for enhancing LLMs' capabilities in privacy compliance, emphasizing the need for robust model improvements and better integration with legal and regulatory requirements. This study underscores the growing importance of developing privacy-aware LLMs that can both support businesses in compliance efforts and safeguard user privacy rights., Comment: 8 pages, 4 figures

Large Language Models (LLMs) have recently displayed their extraordinary capabilities in language understanding. However, how to comprehensively assess the sentiment capabilities of LLMs continues to be a challenge. This paper investigates the ability of LLMs to detect and react to sentiment in text modal. As the integration of LLMs into diverse applications is on the rise, it becomes highly critical to comprehend their sensitivity to emotional tone, as it can influence the user experience and the efficacy of sentiment-driven tasks. We conduct a series of experiments to evaluate the performance of several prominent LLMs in identifying and responding appropriately to sentiments like positive, negative, and neutral emotions. The models' outputs are analyzed across various sentiment benchmarks, and their responses are compared with human evaluations. Our discoveries indicate that although LLMs show a basic sensitivity to sentiment, there are substantial variations in their accuracy and consistency, emphasizing the requirement for further enhancements in their training processes to better capture subtle emotional cues. Take an example in our findings, in some cases, the models might wrongly classify a strongly positive sentiment as neutral, or fail to recognize sarcasm or irony in the text. Such misclassifications highlight the complexity of sentiment analysis and the areas where the models need to be refined. Another aspect is that different LLMs might perform differently on the same set of data, depending on their architecture and training datasets. This variance calls for a more in-depth study of the factors that contribute to the performance differences and how they can be optimized., Comment: 10 pages, 2 figures

The study of cosmic birefringence through Cosmic Microwave Background (CMB) experiments is a key research area in cosmology and particle physics, providing a critical test for Lorentz and CPT symmetries. This paper focuses on an upcoming CMB experiment in the mid-latitude of the Northern Hemisphere, and investigates the potential to detect anisotropies in cosmic birefringence. Applying a quadratic estimator on simulated polarization data, we reconstruct the power spectrum of anisotropic cosmic birefringence successfully and estimate constraints on the amplitude of the spectrum, $A_{\mathrm{CB}}$, assuming scale invariance. The forecast is based on a wide-scan observation strategy during winter, yielding an effective sky coverage of approximately 23.6%. We consider two noise scenarios corresponding to the short-term and long-term phases of the experiment. Our results show that with a small aperture telescope operating at 95/150GHz, the $2\sigma$ upper bound for $A_{\mathrm{CB}}$ can reach 0.017 under the low noise scenario when adopting the method of merging multi-frequency data in map domain, and merging multi-frequency data in spectrum domain tightens the limit by about 10%.A large-aperture telescope with the same bands is found to be more effective, tightening the $2\sigma$ upper limit to 0.0062., Comment: 18 pages, 2 figures

Recent advancements in large-scale video-language models have shown significant potential for real-time planning and detailed interactions. However, their high computational demands and the scarcity of annotated datasets limit their practicality for academic researchers. In this work, we introduce VideoLLaMB, a novel framework that utilizes temporal memory tokens within bridge layers to allow for the encoding of entire video sequences alongside historical visual data, effectively preserving semantic continuity and enhancing model performance across various tasks. This approach includes recurrent memory tokens and a SceneTilling algorithm, which segments videos into independent semantic units to preserve semantic integrity. Empirically, VideoLLaMB significantly outstrips existing video-language models, demonstrating a 5.5 points improvement over its competitors across three VideoQA benchmarks, and 2.06 points on egocentric planning. Comprehensive results on the MVBench show that VideoLLaMB-7B achieves markedly better results than previous 7B models of same LLM. Remarkably, it maintains robust performance as PLLaVA even as video length increases up to 8 times. Besides, the frame retrieval results on our specialized Needle in a Video Haystack (NIAVH) benchmark, further validate VideoLLaMB's prowess in accurately identifying specific frames within lengthy videos. Our SceneTilling algorithm also enables the generation of streaming video captions directly, without necessitating additional training. In terms of efficiency, VideoLLaMB, trained on 16 frames, supports up to 320 frames on a single Nvidia A100 GPU with linear GPU memory scaling, ensuring both high performance and cost-effectiveness, thereby setting a new foundation for long-form video-language models in both academic and practical applications.

Self-correction is a novel method that can stimulate the potential reasoning abilities of large language models (LLMs). It involves detecting and correcting errors during the inference process when LLMs solve reasoning problems. However, recent works do not regard self-correction as a spontaneous and intrinsic capability of LLMs. Instead, such correction is achieved through post-hoc generation, external knowledge introduction, multi-model collaboration, and similar techniques. In this paper, we propose a series of mathematical LLMs called S$^3$c-Math, which are able to perform Spontaneous Step-level Self-correction for Mathematical reasoning. This capability helps LLMs to recognize whether their ongoing inference tends to contain errors and simultaneously correct these errors to produce a more reliable response. We proposed a method, which employs a step-level sampling approach to construct step-wise self-correction data for achieving such ability. Additionally, we implement a training strategy that uses above constructed data to equip LLMs with spontaneous step-level self-correction capacities. Our data and methods have been demonstrated to be effective across various foundation LLMs, consistently showing significant progress in evaluations on GSM8K, MATH, and other mathematical benchmarks. To the best of our knowledge, we are the first to introduce the spontaneous step-level self-correction ability of LLMs in mathematical reasoning.

With the advancement of large-scale language modeling techniques, large multimodal models combining visual encoders with large language models have demonstrated exceptional performance in various visual tasks. Most of the current large-scale multimodal models achieve this by mapping visual features obtained from the visual encoder into a large language model and using them as inputs alongside text for downstream tasks. Therefore, the number of visual tokens directly affects the training and inference speed of the model. There has been significant work on token pruning for visual transformers, but for large multimodal models, only relying on visual information for token pruning or compression may lead to significant loss of important information. On the other hand, the textual input in the form of a question may contain valuable information that can aid in answering the question, providing additional knowledge to the model. To address the potential oversimplification and excessive pruning that can occur with most purely visual token pruning methods, we propose a text information-guided dynamic visual token recovery mechanism that does not require training. This mechanism leverages the similarity between the question text and visual tokens to recover visually meaningful tokens with important text information while merging other less important tokens. Experimental results demonstrate that our proposed method achieves comparable performance to the original approach while compressing the visual tokens to an average of 10% of the original quantity. Our source code will be made publicly available following acceptance., Comment: AAAI2025 Accepted

Visual grounding aims to localize the object referred to in an image based on a natural language query. Although progress has been made recently, accurately localizing target objects within multiple-instance distractions (multiple objects of the same category as the target) remains a significant challenge. Existing methods demonstrate a significant performance drop when there are multiple distractions in an image, indicating an insufficient understanding of the fine-grained semantics and spatial relationships between objects. In this paper, we propose a novel approach, the Relation and Semantic-sensitive Visual Grounding (ResVG) model, to address this issue. Firstly, we enhance the model's understanding of fine-grained semantics by injecting semantic prior information derived from text queries into the model. This is achieved by leveraging text-to-image generation models to produce images representing the semantic attributes of target objects described in queries. Secondly, we tackle the lack of training samples with multiple distractions by introducing a relation-sensitive data augmentation method. This method generates additional training data by synthesizing images containing multiple objects of the same category and pseudo queries based on their spatial relationships. The proposed ReSVG model significantly improves the model's ability to comprehend both object semantics and spatial relations, leading to enhanced performance in visual grounding tasks, particularly in scenarios with multiple-instance distractions. We conduct extensive experiments to validate the effectiveness of our methods on five datasets. Code is available at https://github.com/minghangz/ResVG., Comment: Accepted by ACM MM 2024

The AlphaFold series has transformed protein structure prediction with remarkable accuracy, often matching experimental methods. AlphaFold2, AlphaFold-Multimer, and the latest AlphaFold3 represent significant strides in predicting single protein chains, protein complexes, and biomolecular structures. While AlphaFold2 and AlphaFold-Multimer are open-sourced, facilitating rapid and reliable predictions, AlphaFold3 remains partially accessible through a limited online server and has not been open-sourced, restricting further development. To address these challenges, the PaddleHelix team is developing HelixFold3, aiming to replicate AlphaFold3's capabilities. Using insights from previous models and extensive datasets, HelixFold3 achieves an accuracy comparable to AlphaFold3 in predicting the structures of conventional ligands, nucleic acids, and proteins. The initial release of HelixFold3 is available as open source on GitHub for academic research, promising to advance biomolecular research and accelerate discoveries. We also provide online service at PaddleHelix website at https://paddlehelix.baidu.com/app/all/helixfold3/forecast.

GeSn-based SWIR lasers featuring imaging, sensing, and communications has gained dynamic development recently. However, the existing SiGeSn/GeSn double heterostructure lacks adequate electron confinement and is insufficient for room temperature lasing. The recently demonstrated semiconductor grafting technique provides a viable approach towards AlGaAs/GeSn p-i-n heterojunctions with better electron confinement and high-quality interfaces, promising for room temperature electrically pumped GeSn laser devices. Therefore, understanding and quantitatively characterizing the band alignment in this grafted heterojunction is crucial. In this study, we explore the band alignment in the grafted monocrystalline Al0.3Ga0.7As /Ge0.853Sn0.147 p-i-n heterojunction. We determined the bandgap values of AlGaAs and GeSn to be 1.81 eV and 0.434 eV by photoluminescence measurements, respectively. We further conducted X-ray photoelectron spectroscopy measurements and extracted a valence band offset of 0.19 eV and a conduction band offset of 1.186 eV. A Type-I band alignment was confirmed which effectively confining electrons at the AlGaAs/GeSn interface. This study improves our understanding of the interfacial band structure in grafted AlGaAs/GeSn heterostructure, providing experimental evidence of the Type-I band alignment between AlGaAs and GeSn, and paving the way for their application in laser technologies., Comment: 18 pages, 4 figures

Video temporal grounding aims to identify video segments within untrimmed videos that are most relevant to a given natural language query. Existing video temporal localization models rely on specific datasets for training and have high data collection costs, but they exhibit poor generalization capability under the across-dataset and out-of-distribution (OOD) settings. In this paper, we propose a Training-Free Video Temporal Grounding (TFVTG) approach that leverages the ability of pre-trained large models. A naive baseline is to enumerate proposals in the video and use the pre-trained visual language models (VLMs) to select the best proposal according to the vision-language alignment. However, most existing VLMs are trained on image-text pairs or trimmed video clip-text pairs, making it struggle to (1) grasp the relationship and distinguish the temporal boundaries of multiple events within the same video; (2) comprehend and be sensitive to the dynamic transition of events (the transition from one event to another) in the video. To address these issues, we propose leveraging large language models (LLMs) to analyze multiple sub-events contained in the query text and analyze the temporal order and relationships between these events. Secondly, we split a sub-event into dynamic transition and static status parts and propose the dynamic and static scoring functions using VLMs to better evaluate the relevance between the event and the description. Finally, for each sub-event description, we use VLMs to locate the top-k proposals and leverage the order and relationships between sub-events provided by LLMs to filter and integrate these proposals. Our method achieves the best performance on zero-shot video temporal grounding on Charades-STA and ActivityNet Captions datasets without any training and demonstrates better generalization capabilities in cross-dataset and OOD settings., Comment: Accepted by ECCV 2024

Facial expression recognition (FER) aims to analyze emotional states from static images and dynamic sequences, which is pivotal in enhancing anthropomorphic communication among humans, robots, and digital avatars by leveraging AI technologies. As the FER field evolves from controlled laboratory environments to more complex in-the-wild scenarios, advanced methods have been rapidly developed and new challenges and apporaches are encounted, which are not well addressed in existing reviews of FER. This paper offers a comprehensive survey of both image-based static FER (SFER) and video-based dynamic FER (DFER) methods, analyzing from model-oriented development to challenge-focused categorization. We begin with a critical comparison of recent reviews, an introduction to common datasets and evaluation criteria, and an in-depth workflow on FER to establish a robust research foundation. We then systematically review representative approaches addressing eight main challenges in SFER (such as expression disturbance, uncertainties, compound emotions, and cross-domain inconsistency) as well as seven main challenges in DFER (such as key frame sampling, expression intensity variations, and cross-modal alignment). Additionally, we analyze recent advancements, benchmark performances, major applications, and ethical considerations. Finally, we propose five promising future directions and development trends to guide ongoing research. The project page for this paper can be found at https://github.com/wangyanckxx/SurveyFER.

The swift advancement of large language models (LLMs) has profoundly shaped the landscape of artificial intelligence; however, their deployment in sensitive domains raises grave concerns, particularly due to their susceptibility to malicious exploitation. This situation underscores the insufficiencies in pre-deployment testing, highlighting the urgent need for more rigorous and comprehensive evaluation methods. This study presents a comprehensive empirical analysis assessing the efficacy of conventional coverage criteria in identifying these vulnerabilities, with a particular emphasis on the pressing issue of jailbreak attacks. Our investigation begins with a clustering analysis of the hidden states in LLMs, demonstrating that intrinsic characteristics of these states can distinctly differentiate between various types of queries. Subsequently, we assess the performance of these criteria across three critical dimensions: criterion level, layer level, and token level. Our findings uncover significant disparities in neuron activation patterns between the processing of normal and jailbreak queries, thereby corroborating the clustering results. Leveraging these findings, we propose an innovative approach for the real-time detection of jailbreak attacks by utilizing neural activation features. Our classifier demonstrates remarkable accuracy, averaging 96.33% in identifying jailbreak queries, including those that could lead to adversarial attacks. The importance of our research lies in its comprehensive approach to addressing the intricate challenges of LLM security. By enabling instantaneous detection from the model's first token output, our method holds promise for future systems integrating LLMs, offering robust real-time detection capabilities. This study advances our understanding of LLM security testing, and lays a critical foundation for the development of more resilient AI systems.

Molecular Dynamics (MD) is crucial in various fields such as materials science, chemistry, and pharmacology to name a few. Conventional MD software struggles with the balance between time cost and prediction accuracy, which restricts its wider application. Recently, data-driven approaches based on deep generative models have been devised for time-coarsened dynamics, which aim at learning dynamics of diverse molecular systems over a long timestep, enjoying both universality and efficiency. Nevertheless, most current methods are designed solely to learn from the data distribution regardless of the underlying Boltzmann distribution, and the physics priors such as energies and forces are constantly overlooked. In this work, we propose a conditional generative model called Force-guided Bridge Matching (FBM), which learns full-atom time-coarsened dynamics and targets the Boltzmann-constrained distribution. With the guidance of our delicately-designed intermediate force field, FBM leverages favourable physics priors into the generation process, giving rise to enhanced simulations. Experiments on two datasets consisting of peptides verify our superiority in terms of comprehensive metrics and demonstrate transferability to unseen systems.

Knowledge graph embedding (KGE) constitutes a foundational task, directed towards learning representations for entities and relations within knowledge graphs (KGs), with the objective of crafting representations comprehensive enough to approximate the logical and symbolic interconnections among entities. In this paper, we define a metric Z-counts to measure the difficulty of training each triple ($<$head entity, relation, tail entity$>$) in KGs with theoretical analysis. Based on this metric, we propose \textbf{CL4KGE}, an efficient \textbf{C}urriculum \textbf{L}earning based training strategy for \textbf{KGE}. This method includes a difficulty measurer and a training scheduler that aids in the training of KGE models. Our approach possesses the flexibility to act as a plugin within a wide range of KGE models, with the added advantage of adaptability to the majority of KGs in existence. The proposed method has been evaluated on popular KGE models, and the results demonstrate that it enhances the state-of-the-art methods. The use of Z-counts as a metric has enabled the identification of challenging triples in KGs, which helps in devising effective training strategies., Comment: 16 pages, 3 figures

Knowledge Distillation (KD) is a powerful approach for compressing a large model into a smaller, more efficient model, particularly beneficial for latency-sensitive applications like recommender systems. However, current KD research predominantly focuses on Computer Vision (CV) and NLP tasks, overlooking unique data characteristics and challenges inherent to recommender systems. This paper addresses these overlooked challenges, specifically: (1) mitigating data distribution shifts between teacher and student models, (2) efficiently identifying optimal teacher configurations within time and budgetary constraints, and (3) enabling computationally efficient and rapid sharing of teacher labels to support multiple students. We present a robust KD system developed and rigorously evaluated on multiple large-scale personalized video recommendation systems within Google. Our live experiment results demonstrate significant improvements in student model performance while ensuring consistent and reliable generation of high quality teacher labels from a continuous data stream of data.

Text-to-Image(T2I) models have achieved remarkable success in image generation and editing, yet these models still have many potential issues, particularly in generating inappropriate or Not-Safe-For-Work(NSFW) content. Strengthening attacks and uncovering such vulnerabilities can advance the development of reliable and practical T2I models. Most of the previous works treat T2I models as white-box systems, using gradient optimization to generate adversarial prompts. However, accessing the model's gradient is often impossible in real-world scenarios. Moreover, existing defense methods, those using gradient masking, are designed to prevent attackers from obtaining accurate gradient information. While several black-box jailbreak attacks have been explored, they achieve the limited performance of jailbreaking T2I models due to difficulties associated with optimization in discrete spaces. To address this, we propose HTS-Attack, a heuristic token search attack method. HTS-Attack begins with an initialization that removes sensitive tokens, followed by a heuristic search where high-performing candidates are recombined and mutated. This process generates a new pool of candidates, and the optimal adversarial prompt is updated based on their effectiveness. By incorporating both optimal and suboptimal candidates, HTS-Attack avoids local optima and improves robustness in bypassing defenses. Extensive experiments validate the effectiveness of our method in attacking the latest prompt checkers, post-hoc image checkers, securely trained T2I models, and online commercial models.