A Survey of Foundation Models for Music Understanding

Music is essential in daily life, fulfilling emotional and entertainment needs, and connecting us personally, socially, and culturally. A better understanding of music can enhance our emotions, cognitive skills, and cultural connections. The rapid advancement of artificial intelligence (AI) has introduced new ways to analyze music, aiming to replicate human understanding of music and provide related services. While the traditional models focused on audio features and simple tasks, the recent development of large language models (LLMs) and foundation models (FMs), which excel in various fields by integrating semantic information and demonstrating strong reasoning abilities, could capture complex musical features and patterns, integrate music with language and incorporate rich musical, emotional and psychological knowledge. Therefore, they have the potential in handling complex music understanding tasks from a semantic perspective, producing outputs closer to human perception. This work, to our best knowledge, is one of the early reviews of the intersection of AI techniques and music understanding. We investigated, analyzed, and tested recent large-scale music foundation models in respect of their music comprehension abilities. We also discussed their limitations and proposed possible future directions, offering insights for researchers in this field.

Convergence of Unadjusted Langevin in High Dimensions: Delocalization of Bias

The unadjusted Langevin algorithm is commonly used to sample probability distributions in extremely high-dimensional settings. However, existing analyses of the algorithm for strongly log-concave distributions suggest that, as the dimension $d$ of the problem increases, the number of iterations required to ensure convergence within a desired error in the $W_2$ metric scales in proportion to $d$ or $\sqrt{d}$. In this paper, we argue that, despite this poor scaling of the $W_2$ error for the full set of variables, the behavior for a small number of variables can be significantly better: a number of iterations proportional to $K$, up to logarithmic terms in $d$, often suffices for the algorithm to converge to within a desired $W_2$ error for all $K$-marginals. We refer to this effect as delocalization of bias. We show that the delocalization effect does not hold universally and prove its validity for Gaussian distributions and strongly log-concave distributions with certain sparse interactions. Our analysis relies on a novel $W_{2,\ell^\infty}$ metric to measure convergence. A key technical challenge we address is the lack of a one-step contraction property in this metric. Finally, we use asymptotic arguments to explore potential generalizations of the delocalization effect beyond the Gaussian and sparse interactions setting.

ComKD-CLIP: Comprehensive Knowledge Distillation for Contrastive Language-Image Pre-traning Model

Contrastive Language-Image Pre-training (CLIP) excels in integrating semantic information between images and text through contrastive learning techniques. It has achieved remarkable performance in various multimodal tasks. However, the deployment of large CLIP models is hindered in resource-limited environments, while smaller models frequently fall short of meeting performance benchmarks necessary for practical applications. In this paper, we propose a novel approach, coined as ComKD-CLIP: Comprehensive Knowledge Distillation for Contrastive Language-Image Pre-traning Model, which aims to comprehensively distill the knowledge from a large teacher CLIP model into a smaller student model, ensuring comparable performance with significantly reduced parameters. ComKD-CLIP is composed of two key mechanisms: Image Feature Alignment (IFAlign) and Educational Attention (EduAttention). IFAlign makes the image features extracted by the student model closely match those extracted by the teacher model, enabling the student to learn teacher's knowledge of extracting image features. EduAttention explores the cross-relationships between text features extracted by the teacher model and image features extracted by the student model, enabling the student model to learn how the teacher model integrates text-image features. In addition, ComKD-CLIP can refine the knowledge distilled from IFAlign and EduAttention leveraging the results of text-image feature fusion by the teacher model, ensuring student model accurately absorbs the knowledge of teacher model. Extensive experiments conducted on 11 datasets have demonstrated the superiority of the proposed method.

SentenceVAE: Enable Next-sentence Prediction for Large Language Models with Faster Speed, Higher Accuracy and Longer Context

Current large language models (LLMs) primarily utilize next-token prediction method for inference, which significantly impedes their processing speed. In this paper, we introduce a novel inference methodology termed next-sentence prediction, aimed at enhancing the inference efficiency of LLMs. We present Sentence Variational Autoencoder (SentenceVAE), a tiny model consisting of a Sentence Encoder and a Sentence Decoder. The Sentence Encoder can effectively condense the information within a sentence into a singular token, while the Sentence Decoder can reconstruct this compressed token back into sentence. By integrating SentenceVAE into the input and output layers of LLMs, we develop Sentence-level LLMs (SLLMs) that employ a sentence-by-sentence inference method. In addition, the SentenceVAE module of SLLMS can maintain the integrity of the original semantic content by segmenting the context into sentences, thereby improving accuracy while boosting inference speed. Moreover, compared to previous LLMs, SLLMs process fewer tokens over equivalent context length, significantly reducing memory demands for self-attention computation and facilitating the handling of longer context. Extensive experiments on Wanjuan dataset have reveal that the proposed method can accelerate inference speed by 204~365%, reduce perplexity (PPL) to 46~75% of its original metric, and decrease memory overhead by 86~91% for the equivalent context length, compared to the token-by-token method.

CGB-DM: Content and Graphic Balance Layout Generation with Transformer-based Diffusion Model

Layout generation is the foundation task of intelligent design, which requires the integration of visual aesthetics and harmonious expression of content delivery. However, existing methods still face challenges in generating precise and visually appealing layouts, including blocking, overlap, or spatial misalignment between layouts, which are closely related to the spatial structure of graphic layouts. We find that these methods overly focus on content information and lack constraints on layout spatial structure, resulting in an imbalance of learning content-aware and graphic-aware features. To tackle this issue, we propose Content and Graphic Balance Layout Generation with Transformer-based Diffusion Model (CGB-DM). Specifically, we first design a regulator that balances the predicted content and graphic weight, overcoming the tendency of paying more attention to the content on canvas. Secondly, we introduce a graphic constraint of saliency bounding box to further enhance the alignment of geometric features between layout representations and images. In addition, we adapt a transformer-based diffusion model as the backbone, whose powerful generation capability ensures the quality in layout generation. Extensive experimental results indicate that our method has achieved state-of-the-art performance in both quantitative and qualitative evaluations. Our model framework can also be expanded to other graphic design fields.

Fisher-Rao Gradient Flow: Geodesic Convexity and Functional Inequalities

The dynamics of probability density functions has been extensively studied in science and engineering to understand physical phenomena and facilitate algorithmic design. Of particular interest are dynamics that can be formulated as gradient flows of energy functionals under the Wasserstein metric. The development of functional inequalities, such as the log-Sobolev inequality, plays a pivotal role in analyzing the convergence of these dynamics. The goal of this paper is to parallel the success of techniques using functional inequalities, for dynamics that are gradient flows under the Fisher-Rao metric, with various $f$-divergences as energy functionals. Such dynamics take the form of a nonlocal differential equation, for which existing analysis critically relies on using the explicit solution formula in special cases. We provide a comprehensive study on functional inequalities and the relevant geodesic convexity for Fisher-Rao gradient flows under minimal assumptions. A notable feature of the obtained functional inequalities is that they do not depend on the log-concavity or log-Sobolev constants of the target distribution. Consequently, the convergence rate of the dynamics (assuming well-posed) is uniform across general target distributions, making them potentially desirable dynamics for posterior sampling applications in Bayesian inference.

Efficient, Multimodal, and Derivative-Free Bayesian Inference With Fisher-Rao Gradient Flows

In this paper, we study efficient approximate sampling for probability distributions known up to normalization constants. We specifically focus on a problem class arising in Bayesian inference for large-scale inverse problems in science and engineering applications. The computational challenges we address with the proposed methodology are: (i) the need for repeated evaluations of expensive forward models; (ii) the potential existence of multiple modes; and (iii) the fact that gradient of, or adjoint solver for, the forward model might not be feasible. While existing Bayesian inference methods meet some of these challenges individually, we propose a framework that tackles all three systematically. Our approach builds upon the Fisher-Rao gradient flow in probability space, yielding a dynamical system for probability densities that converges towards the target distribution at a uniform exponential rate. This rapid convergence is advantageous for the computational burden outlined in (i). We apply Gaussian mixture approximations with operator splitting techniques to simulate the flow numerically; the resulting approximation can capture multiple modes thus addressing (ii). Furthermore, we employ the Kalman methodology to facilitate a derivative-free update of these Gaussian components and their respective weights, addressing the issue in (iii). The proposed methodology results in an efficient derivative-free sampler flexible enough to handle multi-modal distributions: Gaussian Mixture Kalman Inversion (GMKI). The effectiveness of GMKI is demonstrated both theoretically and numerically in several experiments with multimodal target distributions, including proof-of-concept and two-dimensional examples, as well as a large-scale application: recovering the Navier-Stokes initial condition from solution data at positive times.

Common and Rare Fundus Diseases Identification Using Vision-Language Foundation Model with Knowledge of Over 400 Diseases

The current retinal artificial intelligence models were trained using data with a limited category of diseases and limited knowledge. In this paper, we present a retinal vision-language foundation model (RetiZero) with knowledge of over 400 fundus diseases. Specifically, we collected 341,896 fundus images paired with text descriptions from 29 publicly available datasets, 180 ophthalmic books, and online resources, encompassing over 400 fundus diseases across multiple countries and ethnicities. RetiZero achieved outstanding performance across various downstream tasks, including zero-shot retinal disease recognition, image-to-image retrieval, internal domain and cross-domain retinal disease classification, and few-shot fine-tuning. Specially, in the zero-shot scenario, RetiZero achieved a Top5 score of 0.8430 and 0.7561 on 15 and 52 fundus diseases respectively. In the image-retrieval task, RetiZero achieved a Top5 score of 0.9500 and 0.8860 on 15 and 52 retinal diseases respectively. Furthermore, clinical evaluations by ophthalmology experts from different countries demonstrate that RetiZero can achieve performance comparable to experienced ophthalmologists using zero-shot and image retrieval methods without requiring model retraining. These capabilities of retinal disease identification strengthen our RetiZero foundation model in clinical implementation.

Unraveling and Mitigating Retriever Inconsistencies in Retrieval-Augmented Large Language Models

Although Retrieval-Augmented Large Language Models (RALMs) demonstrate their superiority in terms of factuality, they do not consistently outperform the original retrieval-free Language Models (LMs). Our experiments reveal that this example-level performance inconsistency exists not only between retrieval-augmented and retrieval-free LM but also among different retrievers. To understand this phenomenon, we investigate the degeneration behavior of RALMs and theoretically decompose it into four categories. Further analysis based on our decomposition reveals that the innate difference in knowledge sources and the unpredictable degeneration of the reader model contribute most to the inconsistency. Drawing from our analysis, we introduce Ensemble of Retrievers (EoR), a trainable framework that can adaptively retrieve from different knowledge sources and effectively decrease unpredictable reader errors. Our experiments on Open Domain Question Answering show that EoR substantially improves performance over the RALM with a single retriever by considerably reducing inconsistent behaviors.

Principled Probabilistic Imaging using Diffusion Models as Plug-and-Play Priors

Diffusion models (DMs) have recently shown outstanding capability in modeling complex image distributions, making them expressive image priors for solving Bayesian inverse problems. However, most existing DM-based methods rely on approximations in the generative process to be generic to different inverse problems, leading to inaccurate sample distributions that deviate from the target posterior defined within the Bayesian framework. To harness the generative power of DMs while avoiding such approximations, we propose a Markov chain Monte Carlo algorithm that performs posterior sampling for general inverse problems by reducing it to sampling the posterior of a Gaussian denoising problem. Crucially, we leverage a general DM formulation as a unified interface that allows for rigorously solving the denoising problem with a range of state-of-the-art DMs. We demonstrate the effectiveness of the proposed method on six inverse problems (three linear and three nonlinear), including a real-world black hole imaging problem. Experimental results indicate that our proposed method offers more accurate reconstructions and posterior estimation compared to existing DM-based imaging inverse methods.