Search

Translating high-level linguistic instructions into precise robotic actions in the physical world remains challenging, particularly when considering the feasibility of interacting with 3D objects. In this paper, we introduce 3D-TAFS, a novel training-free multimodal framework for 3D affordance segmentation, alongside a benchmark for evaluating interactive language-guided affordance in everyday environments. In particular, our framework integrates a large multimodal model with a specialized 3D vision network, enabling seamless fusion of 2D and 3D visual understanding with language comprehension. To facilitate evaluation, we present a dataset of ten typical indoor environments, each with 50 images annotated for object actions and 3D affordance segmentation. Extensive experiments validate the proposed 3D-TAFS's capability in handling interactive 3D affordance segmentation tasks across diverse settings, showcasing competitive performance across various metrics. Our results highlight 3D-TAFS's potential for enhancing human-robot interaction based on affordance understanding in complex indoor environments, advancing the development of more intuitive and efficient robotic frameworks for real-world applications.

Achieving reliable multidimensional Vehicle-to-Vehicle (V2V) channel state information (CSI) prediction is both challenging and crucial for optimizing downstream tasks that depend on instantaneous CSI. This work extends traditional prediction approaches by focusing on four-dimensional (4D) CSI, which includes predictions over time, bandwidth, and antenna (TX and RX) space. Such a comprehensive framework is essential for addressing the dynamic nature of mobility environments within intelligent transportation systems, necessitating the capture of both temporal and spatial dependencies across diverse domains. To address this complexity, we propose a novel context-conditioned spatiotemporal predictive learning method. This method leverages causal convolutional long short-term memory (CA-ConvLSTM) to effectively capture dependencies within 4D CSI data, and incorporates context-conditioned attention mechanisms to enhance the efficiency of spatiotemporal memory updates. Additionally, we introduce an adaptive meta-learning scheme tailored for recurrent networks to mitigate the issue of accumulative prediction errors. We validate the proposed method through empirical studies conducted across three different geometric configurations and mobility scenarios. Our results demonstrate that the proposed approach outperforms existing state-of-the-art predictive models, achieving superior performance across various geometries. Moreover, we show that the meta-learning framework significantly enhances the performance of recurrent-based predictive models in highly challenging cross-geometry settings, thus highlighting its robustness and adaptability.

This work presents RNAdiffusion, a latent diffusion model for generating and optimizing discrete RNA sequences of variable lengths. RNA is a key intermediary between DNA and protein, exhibiting high sequence diversity and complex three-dimensional structures to support a wide range of functions. We utilize pretrained BERT-type models to encode raw RNA sequences into token-level, biologically meaningful representations. A Query Transformer is employed to compress such representations into a set of fixed-length latent vectors, with an autoregressive decoder trained to reconstruct RNA sequences from these latent variables. We then develop a continuous diffusion model within this latent space. To enable optimization, we integrate the gradients of reward models--surrogates for RNA functional properties--into the backward diffusion process, thereby generating RNAs with high reward scores. Empirical results confirm that RNAdiffusion generates non-coding RNAs that align with natural distributions across various biological metrics. Further, we fine-tune the diffusion model on mRNA 5' untranslated regions (5'-UTRs) and optimize sequences for high translation efficiencies. Our guided diffusion model effectively generates diverse 5'-UTRs with high Mean Ribosome Loading (MRL) and Translation Efficiency (TE), outperforming baselines in balancing rewards and structural stability trade-off. Our findings hold potential for advancing RNA sequence-function research and therapeutic RNA design.

Students frequently make mistakes while solving mathematical problems, and traditional error correction methods are both time-consuming and labor-intensive. This paper introduces an innovative \textbf{V}irtual \textbf{A}I \textbf{T}eacher system designed to autonomously analyze and correct student \textbf{E}rrors (VATE). Leveraging advanced large language models (LLMs), the system uses student drafts as a primary source for error analysis, which enhances understanding of the student's learning process. It incorporates sophisticated prompt engineering and maintains an error pool to reduce computational overhead. The AI-driven system also features a real-time dialogue component for efficient student interaction. Our approach demonstrates significant advantages over traditional and machine learning-based error correction methods, including reduced educational costs, high scalability, and superior generalizability. The system has been deployed on the Squirrel AI learning platform for elementary mathematics education, where it achieves 78.3\% accuracy in error analysis and shows a marked improvement in student learning efficiency. Satisfaction surveys indicate a strong positive reception, highlighting the system's potential to transform educational practices.

Diamond particles have many interesting properties and possible applications. However, producing diamond particles with well-defined shapes at scale is challenging because diamonds are chemically inert and extremely hard. Here, we show air oxidation, a routine method for purifying diamonds, can be used to precisely shape diamond particles at scale. By exploiting the distinct reactivities of different crystal facets and defects inside the diamond, layer-by-layer outward-to-inward and inward-to-outward oxidation produced diverse diamond shapes including sphere, twisted surface, pyramidal islands, inverted pyramids, nano-flowers, and hollow polygons. The nanosculpted diamonds had more and finer features that enabled them to outperform the original raw diamonds in various applications. Using experimental observations and Monte Carlo simulations, we built a shape library that guides the design and fabrication of diamond particles with well-defined shapes and functional value. Our study presents a simple, economical and scalable way to produce shape-customized diamonds for various photonics, catalysis, quantum and information technology applications.

In 1989, B. White conjectured that every Riemannian 3-sphere has at least 5 embedded minimal tori. We confirm this conjecture for 3-spheres of positive Ricci curvature. While our proof uses min-max theory, the underlying heuristics are largely inspired by mean curvature flow., Comment: 104 pages

The discontinuous operations inherent in quantization and sparsification introduce obstacles to backpropagation. This is particularly challenging when training deep neural networks in ultra-low precision and sparse regimes. We propose a novel, robust, and universal solution: a denoising affine transform that stabilizes training under these challenging conditions. By formulating quantization and sparsification as perturbations during training, we derive a perturbation-resilient approach based on ridge regression. Our solution employs a piecewise constant backbone model to ensure a performance lower bound and features an inherent noise reduction mechanism to mitigate perturbation-induced corruption. This formulation allows existing models to be trained at arbitrarily low precision and sparsity levels with off-the-shelf recipes. Furthermore, our method provides a novel perspective on training temporal binary neural networks, contributing to ongoing efforts to narrow the gap between artificial and biological neural networks.

This study presents a dynamic Bayesian network framework that facilitates intuitive gradual edge changes. We use two conditional dynamics to model the edge addition and deletion, and edge selection separately. Unlike previous research that uses a mixture network approach, which restricts the number of possible edge changes, or structural priors to induce gradual changes, which can lead to unclear network evolution, our model induces more frequent and intuitive edge change dynamics. We employ Markov chain Monte Carlo (MCMC) sampling to estimate the model structures and parameters and demonstrate the model's effectiveness in a portfolio selection application.

HPC datacenters offer a backbone to the modern digital society. Increasingly, they run Machine Learning (ML) jobs next to generic, compute-intensive workloads, supporting science, business, and other decision-making processes. However, understanding how ML jobs impact the operation of HPC datacenters, relative to generic jobs, remains desirable but understudied. In this work, we leverage long-term operational data, collected from a national-scale production HPC datacenter, and statistically compare how ML and generic jobs can impact the performance, failures, resource utilization, and energy consumption of HPC datacenters. Our study provides key insights, e.g., ML-related power usage causes GPU nodes to run into temperature limitations, median/mean runtime and failure rates are higher for ML jobs than for generic jobs, both ML and generic jobs exhibit highly variable arrival processes and resource demands, significant amounts of energy are spent on unsuccessfully terminating jobs, and concurrent jobs tend to terminate in the same state. We open-source our cleaned-up data traces on Zenodo (https://doi.org/10.5281/zenodo.13685426), and provide our analysis toolkit as software hosted on GitHub (https://github.com/atlarge-research/2024-icpads-hpc-workload-characterization). This study offers multiple benefits for data center administrators, who can improve operational efficiency, and for researchers, who can further improve system designs, scheduling techniques, etc., Comment: 10 pages, 10 figures, 6 tables, ICPADS 2024

Large language models (LLMs) have shown considerable success in a range of domain-specific tasks, especially after fine-tuning. However, fine-tuning with real-world data usually leads to privacy risks, particularly when the fine-tuning samples exist in the pre-training data. To avoid the shortcomings of real data, developers often employ methods to automatically generate synthetic data for fine-tuning, as data generated by traditional models are often far away from the real-world pertaining data. However, given the advanced capabilities of LLMs, the distinction between real data and LLM-generated data has become negligible, which may also lead to privacy risks like real data. In this paper, we present an empirical analysis of this underexplored issue by investigating a key question: "Does fine-tuning with LLM-generated data enhance privacy, or does it pose additional privacy risks?" Based on the structure of LLM's generated data, our research focuses on two primary approaches to fine-tuning with generated data: supervised fine-tuning with unstructured generated data and self-instruct tuning. The number of successful Personal Information Identifier (PII) extractions for Pythia after fine-tuning our generated data raised over $20\%$. Furthermore, the ROC-AUC score of membership inference attacks for Pythia-6.9b after self-instruct methods also achieves more than $40\%$ improvements on ROC-AUC score than base models. The results indicate the potential privacy risks in LLMs when fine-tuning with the generated data.

Computational design of protein-binding proteins is a fundamental capability with broad utility in biomedical research and biotechnology. Recent methods have made strides against some target proteins, but on-demand creation of high-affinity binders without multiple rounds of experimental testing remains an unsolved challenge. This technical report introduces AlphaProteo, a family of machine learning models for protein design, and details its performance on the de novo binder design problem. With AlphaProteo, we achieve 3- to 300-fold better binding affinities and higher experimental success rates than the best existing methods on seven target proteins. Our results suggest that AlphaProteo can generate binders "ready-to-use" for many research applications using only one round of medium-throughput screening and no further optimization., Comment: 45 pages, 17 figures

This study introduces \textbf{InteractEval}, a framework that integrates human expertise and Large Language Models (LLMs) using the Think-Aloud (TA) method to generate attributes for checklist-based text evaluation. By combining human flexibility and reasoning with LLM consistency, InteractEval outperforms traditional non-LLM-based and LLM-based baselines across four distinct dimensions, consisting of Coherence, Fluency, Consistency, and Relevance. The experiment also investigates the effectiveness of the TA method, showing that it promotes divergent thinking in both humans and LLMs, leading to the generation of a wider range of relevant attributes and enhance text evaluation performance. Comparative analysis reveals that humans excel at identifying attributes related to internal quality (Coherence and Fluency), but LLMs perform better at those attributes related to external alignment (Consistency and Relevance). Consequently, leveraging both humans and LLMs together produces the best evaluation outcomes. In other words, this study emphasizes the necessity of effectively combining humans and LLMs in an automated checklist-based text evaluation framework. The code is available at \textbf{\url{https://github.com/BBeeChu/InteractEval.git}}.

Employing the renormalization group approach, we carefully investigate the critical behavior of two-dimensional tilted semi-Dirac semimetals induced by the fermion-fermion interactions in the low-energy regime. After incorporating all one-loop corrections, we derive the coupled RG equations of all related parameters and introduce two distinct strategies, named as Strategy I and Strategy II, to describe different scenarios. A detailed numerical analysis yields several interesting behavior in the low-energy limit. At first, we notice that the fermion-fermion interactions either vanish or diverge in the Strategy I, depending on the initial values of the tilting parameter and the fermionic couplings, whereas these interactions in the Strategy II always diverge at a certain critical energy scale, which is associated with the initial conditions. Next, the microstructural parameter $\alpha$ and the fermion velocity $v_F$ in the Strategy I share the similar behavior with their Strategy II counterparts. It is observed that fermion-fermion interactions lead to an increase in $\alpha$ while driving a decrease in $v_F$. Furthermore, the system can either be attracted by the Gaussian fixed point (GFP) or certain relatively fixed point (RFP) in the Strategy I. However, it always flow towards the RFP in the Strategy II at the lowest-energy limit. These results would provide helpful insights into the studies on observable quantities and phase transitions in the two-dimensional tilted semi-Dirac semimetals and the analogous semimetals., Comment: 14 pages, 11 figures

In the Quantum-Train (QT) framework, mapping quantum state measurements to classical neural network weights is a critical challenge that affects the scalability and efficiency of hybrid quantum-classical models. The traditional QT framework employs a multi-layer perceptron (MLP) for this task, but it struggles with scalability and interpretability. To address these issues, we propose replacing the MLP with a tensor network-based model and introducing a distributed circuit ansatz designed for large-scale quantum machine learning with multiple small quantum processing unit nodes. This approach enhances scalability, efficiently represents high-dimensional data, and maintains a compact model structure. Our enhanced QT framework retains the benefits of reduced parameter count and independence from quantum resources during inference. Experimental results on benchmark datasets demonstrate that the tensor network-based QT framework achieves competitive performance with improved efficiency and generalization, offering a practical solution for scalable hybrid quantum-classical machine learning., Comment: 4 pages, 3 figures

We propose a holographic duality for the boundary Lifshitz field theory (BLFT). Similar to holographic BCFT, holographic BLFT can be consistently defined by imposing either a Neumann boundary condition (NBC) or a conformal boundary condition (CBC) on the end of the world (EOW) brane. We propose $g$-functions and derive $g$-theorem for these two types of holographic BLFT. On the field theory side, we consider BLFT whose path integral is prescribed to include also paths bouncing off the boundary. The entanglement entropy for an interval for the Lifshitz invariant ground state is computed in the saddle point approximation, and is found to agree precisely with the holographic result in both limits when the interval is very close or very far away from the boundary., Comment: 22 Pages and 4 figures

We calculate the correlation functions for the $\bar K^0 p, \pi^+ \Sigma^0, \pi^0 \Sigma^+, \pi^+ \Lambda$, and $\eta \Sigma^+$ states, which in the chiral unitary approach predict an excited $\Sigma^*(1/2^-)$ state at the $\bar K N$ threshold, recently observed by the Belle collaboration. Once this is done, we tackle the inverse problem of seeing how much information one can obtain from these correlation functions. With the resampling method, one can determine the scattering parameters of all the channels with relative precision by means of the analysis in a general framework, and find a clear cusp-like structure corresponding to the $\Sigma^*(1/2^-)$ in the different amplitudes at the $\bar{K}N$ threshold., Comment: 10 pages, 4 figures, 7 tables

Over the past several years, various federated learning (FL) methodologies have been developed to improve model accuracy, a primary performance metric in machine learning. However, to utilize FL in practical decision-making scenarios, beyond considering accuracy, the trained model must also have a reliable confidence in each of its predictions, an aspect that has been largely overlooked in existing FL research. Motivated by this gap, we propose Non-Uniform Calibration for Federated Learning (NUCFL), a generic framework that integrates FL with the concept of model calibration. The inherent data heterogeneity in FL environments makes model calibration particularly difficult, as it must ensure reliability across diverse data distributions and client conditions. Our NUCFL addresses this challenge by dynamically adjusting the model calibration objectives based on statistical relationships between each client's local model and the global model in FL. In particular, NUCFL assesses the similarity between local and global model relationships, and controls the penalty term for the calibration loss during client-side local training. By doing so, NUCFL effectively aligns calibration needs for the global model in heterogeneous FL settings while not sacrificing accuracy. Extensive experiments show that NUCFL offers flexibility and effectiveness across various FL algorithms, enhancing accuracy as well as model calibration.

We have used the Dark Energy Camera (DECam) on the CTIO Blanco 4-m telescope to perform a new emission-line survey of the Large Magellanic Cloud (LMC) using narrow-band H-alpha and [SII] filters in addition to a continuum band for use in creating pure emission-line images. We refer to this new survey as DeMCELS, to distinguish it from the earlier Magellanic Cloud Emission Line Survey (MCELS) that has been in service for nearly 25 years. DeMCELS covers $\sim 54$ degrees$^{2}$, encompassing most of the bright optical disk of the LMC. With DECam's pixel size of only 0.27", our DeMCELS survey provides a seeing-limited improvement of 3-5 times over MCELS and is comparable in depth, with surface brightness limits of 3.3E-17 erg cm$^{-2}$ s$^{-1}$ arcsec$^{-2}$ in H-alpha and 2.9E-17 erg cm$^{-2}$ s$^{-1}$ arcsec$^{-2}$ in H-alpha and [SII], respectively. DeMCELS provides detailed morphological information on nebulae of all scales, from the largest supershells to individual [HII] regions and supernova remnants, to bubbles of emission surrounding individual stars, and even to faint structures in the diffuse ionized gas of the LMC. Many complex regions of emission show significant variations in the ratio of [SII] to H-alpha, a sign of the mixture of shocks from stellar winds and/or supernovae with photoionization by embedded hot, young stars. We present the details of the observing strategy and data processing for this survey, and show selected results in comparison with previous data. A companion project for the Small Magellanic Cloud is in progress and will be reported separately. We are making these new data available to the community at large via the NOIRLab's Data Lab site., Comment: 30 pages, 16 figures Accepted for publication (ApJ)

The uncertainty inherent in the environmental transition model of Reinforcement Learning (RL) necessitates a careful balance between exploration and exploitation to optimize the use of computational resources for accurately estimating an agent's expected reward. Achieving balance in control systems is particularly challenging in scenarios with sparse rewards. However, given the extensive prior knowledge available for many environments, it is redundant to begin learning from scratch in such settings. To address this, we introduce \textbf{L}anguage \textbf{M}odel \textbf{G}uided \textbf{T}rade-offs (i.e., \textbf{LMGT}), a novel, sample-efficient framework that leverages the comprehensive prior knowledge embedded in Large Language Models (LLMs) and their adeptness at processing non-standard data forms, such as wiki tutorials. LMGT proficiently manages the exploration-exploitation trade-off by employing reward shifts guided by LLMs, which direct agents' exploration endeavors, thereby improving sample efficiency. We have thoroughly tested LMGT across various RL tasks and deployed it in industrial-grade RL recommendation systems, where it consistently outperforms baseline methods. The results indicate that our framework can significantly reduce the time cost required during the training phase in RL.

Scaling up deep learning models has been proven effective to improve intelligence of machine learning (ML) models, especially for industry recommendation models and large language models. The co-design of large distributed ML systems and algorithms (to maximize training performance) plays a pivotal role for its success. As it scales, the number of co-design hyper-parameters grows rapidly which brings challenges to feasibly find the optimal setup for system performance maximization. In this paper, we propose CubicML which uses ML to automatically optimize training performance of large distributed ML systems. In CubicML, we use an ML model as a proxy to predict the training performance for search efficiency and performance modeling flexibility. We proved that CubicML can effectively optimize training speed of in-house ads recommendation models with 73 billion parameters and large language models up to 405 billion parameters at Meta.

Periodic laser driving, known as Floquet engineering, is a powerful tool to manipulate the properties of quantum materials. Using circularly polarized light, artificial magnetic fields, called Berry curvature, can be created in the photon-dressed Floquet-Bloch states that form. This mechanism, when applied to 3D Dirac and Weyl systems, is predicted to lead to photon-dressed movement of Weyl nodes which should be detectable in the transport sector. The transport response of such a topological light-matter hybrid, however, remains experimentally unknown. Here, we report on the transport properties of the type-II Weyl semimetal T$\mathrm{_d}$-MoTe$_\mathrm{2}$ illuminated by a femtosecond pulse of circularly polarized light. Using an ultrafast optoelectronic device architecture, we observed injection currents and a helicity-dependent anomalous Hall effect whose scaling with laser field strongly deviate from the perturbative laws of nonlinear optics. We show using Floquet theory that this discovery corresponds to the formation of a magnetic Floquet-Weyl semimetal state. Numerical ab initio simulations support this interpretation, indicating that the light-induced motion of the Weyl nodes contributes substantially to the measured transport signals. This work demonstrates the ability to generate large effective magnetic fields ($>$ 30T) with light, which can be used to manipulate the magnetic and topological properties of a range of quantum materials.

Eating disorders are complex mental health conditions that affect millions of people around the world. Effective interventions on social media platforms are crucial, yet testing strategies in situ can be risky. We present a novel LLM-driven experimental testbed for simulating and assessing intervention strategies in ED-related discussions. Our framework generates synthetic conversations across multiple platforms, models, and ED-related topics, allowing for controlled experimentation with diverse intervention approaches. We analyze the impact of various intervention strategies on conversation dynamics across four dimensions: intervention type, generative model, social media platform, and ED-related community/topic. We employ cognitive domain analysis metrics, including sentiment, emotions, etc., to evaluate the effectiveness of interventions. Our findings reveal that civility-focused interventions consistently improve positive sentiment and emotional tone across all dimensions, while insight-resetting approaches tend to increase negative emotions. We also uncover significant biases in LLM-generated conversations, with cognitive metrics varying notably between models (Claude-3 Haiku $>$ Mistral $>$ GPT-3.5-turbo $>$ LLaMA3) and even between versions of the same model. These variations highlight the importance of model selection in simulating realistic discussions related to ED. Our work provides valuable information on the complex dynamics of ED-related discussions and the effectiveness of various intervention strategies., Comment: 9 pages, 5 figures

Autonomous indoor navigation of UAVs presents numerous challenges, primarily due to the limited precision of GPS in enclosed environments. Additionally, UAVs' limited capacity to carry heavy or power-intensive sensors, such as overheight packages, exacerbates the difficulty of achieving autonomous navigation indoors. This paper introduces an advanced system in which a drone autonomously navigates indoor spaces to locate a specific target, such as an unknown Amazon package, using only a single camera. Employing a deep learning approach, a deep reinforcement adaptive learning algorithm is trained to develop a control strategy that emulates the decision-making process of an expert pilot. We demonstrate the efficacy of our system through real-time simulations conducted in various indoor settings. We apply multiple visualization techniques to gain deeper insights into our trained network. Furthermore, we extend our approach to include an adaptive control algorithm for coordinating multiple drones to lift an object in an indoor environment collaboratively. Integrating our DRAL algorithm enables multiple UAVs to learn optimal control strategies that adapt to dynamic conditions and uncertainties. This innovation enhances the robustness and flexibility of indoor navigation and opens new possibilities for complex multi-drone operations in confined spaces. The proposed framework highlights significant advancements in adaptive control and deep reinforcement learning, offering robust solutions for complex multi-agent systems in real-world applications.

Cognitive psychology investigates perception, attention, memory, language, problem-solving, decision-making, and reasoning. Kahneman's dual-system theory elucidates the human decision-making process, distinguishing between the rapid, intuitive System 1 and the deliberative, rational System 2. Recent advancements have positioned large language Models (LLMs) as formidable tools nearing human-level proficiency in various cognitive tasks. Nonetheless, the presence of a dual-system framework analogous to human cognition in LLMs remains unexplored. This study introduces the \textbf{CogniDual Framework for LLMs} (CFLLMs), designed to assess whether LLMs can, through self-training, evolve from deliberate deduction to intuitive responses, thereby emulating the human process of acquiring and mastering new information. Our findings reveal the cognitive mechanisms behind LLMs' response generation, enhancing our understanding of their capabilities in cognitive psychology. Practically, self-trained models can provide faster responses to certain queries, reducing computational demands during inference.

Large multimodal foundation models have been extensively utilized for image recognition tasks guided by instructions, yet there remains a scarcity of domain expertise in industrial vibration signal analysis. This paper presents a pipeline named VSLLaVA that leverages a large language model to integrate expert knowledge for identification of signal parameters and diagnosis of faults. Within this pipeline, we first introduce an expert rule-assisted signal generator. The generator merges signal provided by vibration analysis experts with domain-specific parameter identification and fault diagnosis question-answer pairs to build signal-question-answer triplets. Then we use these triplets to apply low-rank adaptation methods for fine-tuning the linear layers of the Contrastive Language-Image Pretraining (CLIP) and large language model, injecting multimodal signal processing knowledge. Finally, the fine-tuned model is assessed through the combined efforts of large language model and expert rules to evaluate answer accuracy and relevance, which showcases enhanced performance in identifying, analyzing various signal parameters, and diagnosing faults. These enhancements indicate the potential of this pipeline to build a foundational model for future industrial signal analysis and monitoring.

Understanding surface collective dynamics in quantum materials is crucial for advancing quantum technologies. For example, surface phonon modes in quantum paraelectrics are thought to play an essential role in facilitating interfacial superconductivity. However, detecting these modes, especially below 1 terahertz (THz), is challenging due to limited sampling volumes and the need for high spectroscopic resolution. Here, we report surface soft transverse optical (TO1) phonon dynamics in KTaO3 and SrTiO3 by developing surface-sensitive spintronic THz spectroscopy that can sense the collective modes only a few nanometers deep from the surface. In KTaO3, the TO1 mode softens and sharpens with decreasing temperature, leveling off at 0.7 THz. In contrast, this mode in SrTiO3 broadens significantly below the quantum paraelectric crossover and coincides with the hardening of a sub-meV phonon mode related to the antiferrodistortive transition. These observations that deviate from their bulk properties may have implications for interfacial superconductivity and ferroelectricity. The developed technique opens opportunities for sensing low-energy surface excitations., Comment: The main text consists of 24 pages and includes 4 figures. Supplementary Information is also provided. Science Advances accepted

Micro-ring resonators (MRRs) "trap" incoming light, and therefore, have been shown to achieve extremely high local intensities of light. Thus, they can be used to facilitate highly non-linear optical signals. By embedding materials that host non-linear optical processes inside the MRR, we expect to observe an enhancement in the strength of the non-linear optical signal. This concept is demonstrated here by extracting the Raman signature of graphene that is placed inside a MRR. A highly doped silica MRR which features an optical bus waveguide coupled to a loop (ring) tuned to near-infrared wavelengths is used. Raman signal with an excitation wavelength of 522 nm via third harmonic generation inside the MRR is observed. Higher order Raman signal of the embedded graphene at the 1597.6 nm excitation wavelength is also observed. This work demonstrates the feasibility of the MRR as a non-linear signal enhancer using novel MRR device setups., Comment: Main text 6 pages with 3 figures. Supplementary text 4 pages with 3 figures and 1 table

Deriving health indicators of rotating machines is crucial for their maintenance. However, this process is challenging for the prevalent adopted intelligent methods since they may take the whole data distributions, not only introducing noise interference but also lacking the explainability. To address these issues, we propose a diffusion-based weakly-supervised approach for deriving health indicators of rotating machines, enabling early fault detection and continuous monitoring of condition evolution. This approach relies on a classifier-free diffusion model trained using healthy samples and a few anomalies. This model generates healthy samples. and by comparing the differences between the original samples and the generated ones in the envelope spectrum, we construct an anomaly map that clearly identifies faults. Health indicators are then derived, which can explain the fault types and mitigate noise interference. Comparative studies on two cases demonstrate that the proposed method offers superior health monitoring effectiveness and robustness compared to baseline models.

Circularly polarized light (CPL) sources are essential for chiroptics, spintronics, quantum optics, and asymmetric photochemistry. However, conventional approaches fail to simultaneously realize a large luminescence dissymmetry factor (glum) and wide-range tuning of glum in a compact device. Chiral luminophores usually suffer from low glum due to their small molecular sizes. Although chiral metasurfaces can enable a large glum, they lack post-fabrication tunability. Here, we demonstrate that it is possible to achieve high-purity circularly polarized luminescence using achiral metasurfaces. These metasurfaces enable optical tuning and even reversal of luminescence chirality by uncovering and utilizing giant near-field chirality. We validate our concept with upconversion nanoparticles and downshifting dye molecules, experimentally achieving a large glum of up to 1.65, which can be actively and continuously tuned between 1.65 and -1.58. Our approach promises important applications in next-generation CPL sources and detectors, and tunable quantum devices.

Current quantum generative adversarial networks (QGANs) still struggle with practical-sized data. First, many QGANs use principal component analysis (PCA) for dimension reduction, which, as our studies reveal, can diminish the QGAN's effectiveness. Second, methods that segment inputs into smaller patches processed by multiple generators face scalability issues. In this work, we propose LSTM-QGAN, a QGAN architecture that eliminates PCA preprocessing and integrates quantum long short-term memory (QLSTM) to ensure scalable performance. Our experiments show that LSTM-QGAN significantly enhances both performance and scalability over state-of-the-art QGAN models, with visual data improvements, reduced Frechet Inception Distance scores, and reductions of 5x in qubit counts, 5x in single-qubit gates, and 12x in two-qubit gates.

We introduce SAM4MLLM, an innovative approach which integrates the Segment Anything Model (SAM) with Multi-Modal Large Language Models (MLLMs) for pixel-aware tasks. Our method enables MLLMs to learn pixel-level location information without requiring excessive modifications to the existing model architecture or adding specialized tokens. We introduce an inquiry-based approach that can effectively find prompt points for SAM to perform segmentation based on MLLM. It combines detailed visual information with the powerful expressive capabilities of large language models in a unified language-based manner without additional computational overhead in learning. Experimental results on pubic benchmarks demonstrate the effectiveness of our approach., Comment: ECCV 2024

Modern artificial intelligence (AI) systems are powered by foundation models. This paper presents a new set of foundation models, called Llama 3. It is a herd of language models that natively support multilinguality, coding, reasoning, and tool usage. Our largest model is a dense Transformer with 405B parameters and a context window of up to 128K tokens. This paper presents an extensive empirical evaluation of Llama 3. We find that Llama 3 delivers comparable quality to leading language models such as GPT-4 on a plethora of tasks. We publicly release Llama 3, including pre-trained and post-trained versions of the 405B parameter language model and our Llama Guard 3 model for input and output safety. The paper also presents the results of experiments in which we integrate image, video, and speech capabilities into Llama 3 via a compositional approach. We observe this approach performs competitively with the state-of-the-art on image, video, and speech recognition tasks. The resulting models are not yet being broadly released as they are still under development.