Search

Symbolic Music, akin to language, can be encoded in discrete symbols. Recent research has extended the application of large language models (LLMs) such as GPT-4 and Llama2 to the symbolic music domain including understanding and generation. Yet scant research explores the details of how these LLMs perform on advanced music understanding and conditioned generation, especially from the multi-step reasoning perspective, which is a critical aspect in the conditioned, editable, and interactive human-computer co-creation process. This study conducts a thorough investigation of LLMs' capability and limitations in symbolic music processing. We identify that current LLMs exhibit poor performance in song-level multi-step music reasoning, and typically fail to leverage learned music knowledge when addressing complex musical tasks. An analysis of LLMs' responses highlights distinctly their pros and cons. Our findings suggest achieving advanced musical capability is not intrinsically obtained by LLMs, and future research should focus more on bridging the gap between music knowledge and reasoning, to improve the co-creation experience for musicians., Comment: Accepted by ISMIR2024

To overcome these obstacles and improve computational accuracy and efficiency, this paper presents the Randomized Radial Basis Function Neural Network (RRNN), an innovative approach explicitly crafted for solving multiscale elliptic equations. The RRNN method commences by decomposing the computational domain into non-overlapping subdomains. Within each subdomain, the solution to the localized subproblem is approximated by a randomized radial basis function neural network with a Gaussian kernel. This network is distinguished by the random assignment of width and center coefficients for its activation functions, thereby rendering the training process focused solely on determining the weight coefficients of the output layer. For each subproblem, similar to the Petrov-Galerkin finite element method, a linear system will be formulated on the foundation of a weak formulation. Subsequently, a selection of collocation points is stochastically sampled at the boundaries of the subdomain, ensuring satisfying $C^0$ and $C^1$ continuity and boundary conditions to couple these localized solutions. The network is ultimately trained using the least squares method to ascertain the output layer weights. To validate the RRNN method's effectiveness, an extensive array of numerical experiments has been executed and the results demonstrate that the proposed method can improve the accuracy and efficiency well., Comment: 33 pages

The issue of hallucinations is a prevalent concern in existing Large Vision-Language Models (LVLMs). Previous efforts have primarily focused on investigating object hallucinations, which can be easily alleviated by introducing object detectors. However, these efforts neglect hallucinations in inter-object relationships, which is essential for visual comprehension. In this work, we introduce R-Bench, a novel benchmark for evaluating Vision Relationship Hallucination. R-Bench features image-level questions that focus on the existence of relationships and instance-level questions that assess local visual comprehension. We identify three types of relationship co-occurrences that lead to hallucinations: relationship-relationship, subject-relationship, and relationship-object. The visual instruction tuning dataset's long-tail distribution significantly impacts LVLMs' understanding of visual relationships. Furthermore, our analysis reveals that current LVLMs tend to disregard visual content and overly rely on the common sense knowledge of Large Language Models. They also struggle with reasoning about spatial relationships based on contextual information., Comment: ICML2024; Project Page:https://github.com/mrwu-mac/R-Bench

Evaluating the alignment capabilities of large Vision-Language Models (VLMs) is essential for determining their effectiveness as helpful assistants. However, existing benchmarks primarily focus on basic abilities using nonverbal methods, such as yes-no and multiple-choice questions. In this paper, we address this gap by introducing AlignMMBench, a comprehensive alignment benchmark specifically designed for emerging Chinese VLMs. This benchmark is meticulously curated from real-world scenarios and Chinese Internet sources, encompassing thirteen specific tasks across three categories, and includes both single-turn and multi-turn dialogue scenarios. Incorporating a prompt rewrite strategy, AlignMMBench encompasses 1,054 images and 4,978 question-answer pairs. To facilitate the evaluation pipeline, we propose CritiqueVLM, a rule-calibrated evaluator that exceeds GPT-4's evaluation ability. Finally, we report the performance of representative VLMs on AlignMMBench, offering insights into the capabilities and limitations of different VLM architectures. All evaluation codes and data are available on https://alignmmbench.github.io.

Pre-trained large language models (LLM) have emerged as a powerful tool for simulating various scenarios and generating output given specific instructions and multimodal input. In this work, we analyze the specific use of LLM to enhance a classical supervised machine learning method for classification problems. We propose a few approaches to integrate LLM into a classical machine learning estimator to further enhance the prediction performance. We examine the performance of the proposed approaches through both standard supervised learning binary classification tasks, and a transfer learning task where the test data observe distribution changes compared to the training data. Numerical experiments using four publicly available datasets are conducted and suggest that using LLM to enhance classical machine learning estimators can provide significant improvement on prediction performance.

We provide a preliminary study on utilizing GPU (Graphics Processing Unit) to accelerate computation for three simulation optimization tasks with either first-order or second-order algorithms. Compared to the implementation using only CPU (Central Processing Unit), the GPU implementation benefits from computational advantages of parallel processing for large-scale matrices and vectors operations. Numerical experiments demonstrate computational advantages of utilizing GPU implementation in simulation optimization problems, and show that such advantage comparatively further increase as the problem scale increases.

In this paper, the large time behavior of the solutions for the Cauchy problem to the one-dimensional compressible Navier-Stokes system with the motion of a viscous heat-conducting perfect polytropic gas is investigated.Our result shows that the combination of a viscous contact wave with rarefaction waves is asymptotically stable, when the large initial disturbance of the density, velocity and temperature belong to $H^{1}(\mathbb{R})$, $L^{2}(\mathbb{R})\cap L^{4}(\mathbb{R})$ and $L^{2}(\mathbb{R})$, provided the strength of the combination waves is suitably small. In addition, the initial disturbance on the derivation of velocity and temperature belong to $L^{2}(\mathbb{R})$ can be arbitrarily large., Comment: 38 pages. arXiv admin note: text overlap with arXiv:1502.00211 by other authors

This technical report presents our solution, "occTransformer" for the 3D occupancy prediction track in the autonomous driving challenge at CVPR 2023. Our method builds upon the strong baseline BEVFormer and improves its performance through several simple yet effective techniques. Firstly, we employed data augmentation to increase the diversity of the training data and improve the model's generalization ability. Secondly, we used a strong image backbone to extract more informative features from the input data. Thirdly, we incorporated a 3D unet head to better capture the spatial information of the scene. Fourthly, we added more loss functions to better optimize the model. Additionally, we used an ensemble approach with the occ model BevDet and SurroundOcc to further improve the performance. Most importantly, we integrated 3D detection model StreamPETR to enhance the model's ability to detect objects in the scene. Using these methods, our solution achieved 49.23 miou on the 3D occupancy prediction track in the autonomous driving challenge., Comment: Innovation Award in the 3D Occupancy Prediction Challenge (CVPR23)

While Large Language Models (LLMs) demonstrate impressive capabilities in text generation, we find that their ability has yet to be generalized to music, humanity's creative language. We introduce ChatMusician, an open-source LLM that integrates intrinsic musical abilities. It is based on continual pre-training and finetuning LLaMA2 on a text-compatible music representation, ABC notation, and the music is treated as a second language. ChatMusician can understand and generate music with a pure text tokenizer without any external multi-modal neural structures or tokenizers. Interestingly, endowing musical abilities does not harm language abilities, even achieving a slightly higher MMLU score. Our model is capable of composing well-structured, full-length music, conditioned on texts, chords, melodies, motifs, musical forms, etc, surpassing GPT-4 baseline. On our meticulously curated college-level music understanding benchmark, MusicTheoryBench, ChatMusician surpasses LLaMA2 and GPT-3.5 on zero-shot setting by a noticeable margin. Our work reveals that LLMs can be an excellent compressor for music, but there remains significant territory to be conquered. We release our 4B token music-language corpora MusicPile, the collected MusicTheoryBench, code, model and demo in GitHub., Comment: GitHub: https://shanghaicannon.github.io/ChatMusician/

Most existing personalized federated learning approaches are based on intricate designs, which often require complex implementation and tuning. In order to address this limitation, we propose a simple yet effective personalized federated learning framework. Specifically, during each communication round, we group clients into multiple clusters based on their model training status and data distribution on the server side. We then consider each cluster center as a node equipped with model parameters and construct a graph that connects these nodes using weighted edges. Additionally, we update the model parameters at each node by propagating information across the entire graph. Subsequently, we design a precise personalized model distribution strategy to allow clients to obtain the most suitable model from the server side. We conduct experiments on three image benchmark datasets and create synthetic structured datasets with three types of typologies. Experimental results demonstrate the effectiveness of the proposed work., Comment: This paper has been accepted by PAKDD 2024 as an oral presentation

Neural operators have been validated as promising deep surrogate models for solving partial differential equations (PDEs). Despite the critical role of boundary conditions in PDEs, however, only a limited number of neural operators robustly enforce these conditions. In this paper we introduce semi-periodic Fourier neural operator (SPFNO), a novel spectral operator learning method, to learn the target operators of PDEs with non-periodic BCs. This method extends our previous work (arXiv:2206.12698), which showed significant improvements by employing enhanced neural operators that precisely satisfy the boundary conditions. However, the previous work is associated with Gaussian grids, restricting comprehensive comparisons across most public datasets. Additionally, we present numerical results for various PDEs such as the viscous Burgers' equation, Darcy flow, incompressible pipe flow, and coupled reactiondiffusion equations. These results demonstrate the computational efficiency, resolution invariant property, and BC-satisfaction behavior of proposed model. An accuracy improvement of approximately 1.7X-4.7X over the non-BC-satisfying baselines is also achieved. Furthermore, our studies on SOL underscore the significance of satisfying BCs as a criterion for deep surrogate models of PDEs.

In the rapidly evolving landscape of artificial intelligence, ChatGPT has been widely used in various applications. The new feature - customization of ChatGPT models by users to cater to specific needs has opened new frontiers in AI utility. However, this study reveals a significant security vulnerability inherent in these user-customized GPTs: prompt injection attacks. Through comprehensive testing of over 200 user-designed GPT models via adversarial prompts, we demonstrate that these systems are susceptible to prompt injections. Through prompt injection, an adversary can not only extract the customized system prompts but also access the uploaded files. This paper provides a first-hand analysis of the prompt injection, alongside the evaluation of the possible mitigation of such attacks. Our findings underscore the urgent need for robust security frameworks in the design and deployment of customizable GPT models. The intent of this paper is to raise awareness and prompt action in the AI community, ensuring that the benefits of GPT customization do not come at the cost of compromised security and privacy., Comment: Accepted in ICLR 2024 Workshop on Secure and Trustworthy Large Language Models

Utilizing covariate information has been a powerful approach to improve the efficiency and accuracy for causal inference, which support massive amount of randomized experiments run on data-driven enterprises. However, state-of-art approaches can become practically unreliable when the dimension of covariate increases to just 50, whereas experiments on large platforms can observe even higher dimension of covariate. We propose a machine-learning-assisted covariate representation approach that can effectively make use of historical experiment or observational data that are run on the same platform to understand which lower dimensions can effectively represent the higher-dimensional covariate. We then propose design and estimation methods with the covariate representation. We prove statistically reliability and performance guarantees for the proposed methods. The empirical performance is demonstrated using numerical experiments.

One of the main goals of financial institutions (FIs) today is combating fraud and financial crime. To this end, FIs use sophisticated machine-learning models trained using data collected from their customers. The output of machine learning models may be manually reviewed for critical use cases, e.g., determining the likelihood of a transaction being anomalous and the subsequent course of action. While advanced machine learning models greatly aid an FI in anomaly detection, model performance could be significantly improved using additional customer data from other FIs. In practice, however, an FI may not have appropriate consent from customers to share their data with other FIs. Additionally, data privacy regulations may prohibit FIs from sharing clients' sensitive data in certain geographies. Combining customer data to jointly train highly accurate anomaly detection models is therefore challenging for FIs in operational settings. In this paper, we describe a privacy-preserving framework that allows FIs to jointly train highly accurate anomaly detection models. The framework combines the concept of federated learning with efficient multi-party computation and noisy aggregates inspired by differential privacy. The presented framework was submitted as a winning entry to the financial crime detection track of the US/UK PETs Challenge. The challenge considered an architecture where banks hold customer data and execute transactions through a central network. We show that our solution enables the network to train a highly accurate anomaly detection model while preserving privacy of customer data. Experimental results demonstrate that use of additional customer data using the proposed approach results in improvement of our anomaly detection model's AUPRC from 0.6 to 0.7. We discuss how our framework, can be generalized to other similar scenarios., Comment: 12 pages

We report the generation of multimode solitons in step-index fiber. The solitons are superpositions of 5-10 temporally-aligned transverse modes, they exhibit speckled beam profiles, and the spatio-spectral variation across the soliton can be complex. Greater understanding of multimode solitons should create a foundation for further research into complex multimode nonlinear phenomena in step-index fibers. With energies of tens of nanojoules and durations around 100 fs, the multimode solitons are speckled fields with peak powers that can exceeed 300 kW, parameters which may be valuable in applications.

We formulate, analyze and solve the problem of best arm identification with fairness constraints on subpopulations (BAICS). Standard best arm identification problems aim at selecting an arm that has the largest expected reward where the expectation is taken over the entire population. The BAICS problem requires that an selected arm must be fair to all subpopulations (e.g., different ethnic groups, age groups, or customer types) by satisfying constraints that the expected reward conditional on every subpopulation needs to be larger than some thresholds. The BAICS problem aims at correctly identify, with high confidence, the arm with the largest expected reward from all arms that satisfy subpopulation constraints. We analyze the complexity of the BAICS problem by proving a best achievable lower bound on the sample complexity with closed-form representation. We then design an algorithm and prove that the algorithm's sample complexity matches with the lower bound in terms of order. A brief account of numerical experiments are conducted to illustrate the theoretical findings.

Graph neural networks have achieved significant success in representation learning. However, the performance gains come at a cost; acquiring comprehensive labeled data for training can be prohibitively expensive. Active learning mitigates this issue by searching the unexplored data space and prioritizing the selection of data to maximize model's performance gain. In this paper, we propose a novel method SMARTQUERY, a framework to learn a graph neural network with very few labeled nodes using a hybrid uncertainty reduction function. This is achieved using two key steps: (a) design a multi-stage active graph learning framework by exploiting diverse explicit graph information and (b) introduce label propagation to efficiently exploit known labels to assess the implicit embedding information. Using a comprehensive set of experiments on three network datasets, we demonstrate the competitive performance of our method against state-of-the-arts on very few labeled data (up to 5 labeled nodes per class).

We study the problem of multi-task non-smooth optimization that arises ubiquitously in statistical learning, decision-making and risk management. We develop a data fusion approach that adaptively leverages commonalities among a large number of objectives to improve sample efficiency while tackling their unknown heterogeneities. We provide sharp statistical guarantees for our approach. Numerical experiments on both synthetic and real data demonstrate significant advantages of our approach over benchmarks., Comment: 25 pages

Constructing asymptotically valid confidence intervals through a valid central limit theorem is crucial for A/B tests, where a classical goal is to statistically assert whether a treatment plan is significantly better than a control plan. In some emerging applications for online platforms, the treatment plan is not a single plan, but instead encompasses an infinite continuum of plans indexed by a continuous treatment parameter. As such, the experimenter not only needs to provide valid statistical inference, but also desires to effectively and adaptively find the optimal choice of value for the treatment parameter to use for the treatment plan. However, we find that classical optimization algorithms, despite of their fast convergence rates under convexity assumptions, do not come with a central limit theorem that can be used to construct asymptotically valid confidence intervals. We fix this issue by providing a new optimization algorithm that on one hand maintains the same fast convergence rate and on the other hand permits the establishment of a valid central limit theorem. We discuss practical implementations of the proposed algorithm and conduct numerical experiments to illustrate the theoretical findings.

Spatiotemporal mode-locking in a laser with anomalous dispersion is investigated. Mode-locked states with varying modal content can be observed, but we find it difficult to observe highly multimode states. We describe the properties of these mode-locked states and compare them to the results of numerical simulations. Prospects for the generation of highly-multimode states and lasers based on multimode soliton formation are discussed.

Today's cyber-world is vastly multivariate. Metrics collected at extreme varieties demand multivariate algorithms to properly detect anomalies. However, forecast-based algorithms, as widely proven approaches, often perform sub-optimally or inconsistently across datasets. A key common issue is they strive to be one-size-fits-all but anomalies are distinctive in nature. We propose a method that tailors to such distinction. Presenting FMUAD - a Forecast-based, Multi-aspect, Unsupervised Anomaly Detection framework. FMUAD explicitly and separately captures the signature traits of anomaly types - spatial change, temporal change and correlation change - with independent modules. The modules then jointly learn an optimal feature representation, which is highly flexible and intuitive, unlike most other models in the category. Extensive experiments show our FMUAD framework consistently outperforms other state-of-the-art forecast-based anomaly detectors., Comment: Published at IEEE BigData 2021

Recently, many approaches tackle the Unsupervised Domain Adaptive person re-identification (UDA re-ID) problem through pseudo-label-based contrastive learning. During training, a uni-centroid representation is obtained by simply averaging all the instance features from a cluster with the same pseudo label. However, a cluster may contain images with different identities (label noises) due to the imperfect clustering results, which makes the uni-centroid representation inappropriate. In this paper, we present a novel Multi-Centroid Memory (MCM) to adaptively capture different identity information within the cluster. MCM can effectively alleviate the issue of label noises by selecting proper positive/negative centroids for the query image. Moreover, we further propose two strategies to improve the contrastive learning process. First, we present a Domain-Specific Contrastive Learning (DSCL) mechanism to fully explore intradomain information by comparing samples only from the same domain. Second, we propose Second-Order Nearest Interpolation (SONI) to obtain abundant and informative negative samples. We integrate MCM, DSCL, and SONI into a unified framework named Multi-Centroid Representation Network (MCRN). Extensive experiments demonstrate the superiority of MCRN over state-of-the-art approaches on multiple UDA re-ID tasks and fully unsupervised re-ID tasks., Comment: Accepted by AAAI2022