arXiv subjects

Lu Lu

Publications and source records attributed to Lu Lu.

At least 109 records · Page 6Linked to original sources

arXiv2024

Disk2Planet: A Robust and Automated Machine Learning Tool for Parameter Inference in Disk-Planet Systems

We introduce Disk2Planet, a machine learning-based tool to infer key parameters in disk-planet systems from observed protoplanetary disk structures. Disk2Planet takes as input the disk structures in the form of two-dimensional density and velocity maps, and outputs disk and planet properties, that is, the Shakura--Sunyaev viscosity, the disk aspect ratio, the planet--star mass ratio, and the planet's radius and azimuth. We integrate the Covariance Matrix Adaptation Evolution Strategy (CMA--ES), an evolutionary algorithm tailored for complex optimization problems, and the Protoplanetary Disk Operator Network (PPDONet), a neural network designed to predict solutions of disk--planet interactions. Our tool is fully automated and can retrieve parameters in one system in three minutes on an Nvidia A100 graphics processing unit. We empirically demonstrate that our tool achieves percent-level or higher accuracy, and is able to handle missing data and unknown levels of noise.

astro-ph.EP↗

arXiv2024

NEST-RQ: Next Token Prediction for Speech Self-Supervised Pre-Training

Speech self-supervised pre-training can effectively improve the performance of downstream tasks. However, previous self-supervised learning (SSL) methods for speech, such as HuBERT and BEST-RQ, focus on utilizing non-causal encoders with bidirectional context, and lack sufficient support for downstream streaming models. To address this issue, we introduce the next token prediction based speech pre-training method with random-projection quantizer (NEST-RQ). NEST-RQ employs causal encoders with only left context and uses next token prediction (NTP) as the training task. On the large-scale dataset, compared to BEST-RQ, the proposed NEST-RQ achieves comparable performance on non-streaming automatic speech recognition (ASR) and better performance on streaming ASR. We also conduct analytical experiments in terms of the future context size of streaming ASR, the codebook quality of SSL and the model size of the encoder. In summary, the paper demonstrates the feasibility of the NTP in speech SSL and provides empirical evidence and insights for speech SSL research.

eess.AS↗

arXiv2024

Mitigating Hallucination in Visual-Language Models via Re-Balancing Contrastive Decoding

Although Visual-Language Models (VLMs) have shown impressive capabilities in tasks like visual question answering and image captioning, they still struggle with hallucinations. Analysis of attention distribution in these models shows that VLMs tend to processing textual tokens rather than visual tokens. This imbalance of attention distribution causes VLMs to favor textual knowledge in the case of multimodal knowledge conflicts, resulting in differences from the image information. In this paper, we propose Re-Balancing Contrastive Decoding (RBD) method, which employs textual and visual branches to recalibrate attention distribution in VLMs. Specifically, the textual branch injects image noise to stimulate the model's dependency on text, thereby reducing textual bias. Concurrently, the visual branch focuses on the selection of significant tokens, refining the attention mechanism to highlight the primary subject. This dual-branch strategy enables the RBD method to diminish textual bias while enhancing visual information. Experimental results demonstrate that our method, RBD, outperforms the existing methods by the CHAIR and POPE metrics, mitigate hallucinations without reducing the model's general capabilities.

cs.CV↗

arXiv2024

Optical Integrated Sensing and Communication with Light-Emitting Diode

This paper presents a new optical integrated sensing and communication (O-ISAC) framework tailored for cost-effective Light-Emitting Diode (LED) for enhanced Internet of Things (IoT) applications. Unlike prior research on ISAC, which predominantly focused on radio frequency (RF) band, O-ISAC capitalizes on the inherent advantages of the optical spectrum, including the ultra-wide license-free bandwidth, immunity to RF interference, and energy efficiency -- attributes crucial for IoT communications. The communication and sensing in our O-ISAC system unfold in two phases: directionless O-ISAC and directional O-ISAC. In the first phase, distributed optical access points emit non-directional light for communication and leverage small-aperture imaging principles for sensing. In the second phase, we put forth the concept of optical beamforming, using collimating lenses to concentrate light, resulting in substantial performance enhancements in both communication and sensing. Numerical and simulation results demonstrate the feasibility and impressive performance of O-ISAC benchmarked against optical separate communication and sensing systems.

cs.IT↗

arXiv2024

Fourier-MIONet: Fourier-enhanced multiple-input neural operators for multiphase modeling of geological carbon sequestration

Geologic carbon sequestration (GCS) is a safety-critical technology that aims to reduce the amount of carbon dioxide in the atmosphere, which also places high demands on reliability. Multiphase flow in porous media is essential to understand CO$_2$ migration and pressure fields in the subsurface associated with GCS. However, numerical simulation for such problems in 4D is computationally challenging and expensive, due to the multiphysics and multiscale nature of the highly nonlinear governing partial differential equations (PDEs). It prevents us from considering multiple subsurface scenarios and conducting real-time optimization. Here, we develop a Fourier-enhanced multiple-input neural operator (Fourier-MIONet) to learn the solution operator of the problem of multiphase flow in porous media. Fourier-MIONet utilizes the recently developed framework of the multiple-input deep neural operators (MIONet) and incorporates the Fourier neural operator (FNO) in the network architecture. Once Fourier-MIONet is trained, it can predict the evolution of saturation and pressure of the multiphase flow under various reservoir conditions, such as permeability and porosity heterogeneity, anisotropy, injection configurations, and multiphase flow properties. Compared to the enhanced FNO (U-FNO), the proposed Fourier-MIONet has 90% fewer unknown parameters, and it can be trained in significantly less time (about 3.5 times faster) with much lower CPU memory ($<$ 15%) and GPU memory ($<$ 35%) requirements, to achieve similar prediction accuracy. In addition to the lower computational cost, Fourier-MIONet can be trained with only 6 snapshots of time to predict the PDE solutions for 30 years. The excellent generalizability of Fourier-MIONet is enabled by its adherence to the physical principle that the solution to a PDE is continuous over time.

cs.LG↗

arXiv2024

Identifying heterogeneous micromechanical properties of biological tissues via physics-informed neural networks

The heterogeneous micromechanical properties of biological tissues have profound implications across diverse medical and engineering domains. However, identifying full-field heterogeneous elastic properties of soft materials using traditional engineering approaches is fundamentally challenging due to difficulties in estimating local stress fields. Recently, there has been a growing interest in using data-driven models to learn full-field mechanical responses such as displacement and strain from experimental or synthetic data. However, research studies on inferring full-field elastic properties of materials, a more challenging problem, are scarce, particularly for large deformation, hyperelastic materials. Here, we propose a physics-informed machine learning approach to identify the elasticity map in nonlinear, large deformation hyperelastic materials. We evaluate the prediction accuracies and computational efficiency of physics-informed neural networks (PINNs) by inferring the heterogeneous elasticity maps across three materials with structural complexity that closely resemble real tissue patterns, such as brain tissue and tricuspid valve tissue. We further applied our improved architecture to three additional examples of breast cancer tissue and extended our analysis to three hyperelastic constitutive models: Neo-Hookean, Mooney Rivlin, and Gent. Our selected network architecture consistently produced highly accurate estimations of heterogeneous elasticity maps, even when there was up to 10% noise present in the training data.

math.NA↗

arXiv2024

Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition

Modern automatic speech recognition (ASR) model is required to accurately transcribe diverse speech signals (from different domains, languages, accents, etc) given the specific contextual information in various application scenarios. Classic end-to-end models fused with extra language models perform well, but mainly in data matching scenarios and are gradually approaching a bottleneck. In this work, we introduce Seed-ASR, a large language model (LLM) based speech recognition model. Seed-ASR is developed based on the framework of audio conditioned LLM (AcLLM), leveraging the capabilities of LLMs by inputting continuous speech representations together with contextual information into the LLM. Through stage-wise large-scale training and the elicitation of context-aware capabilities in LLM, Seed-ASR demonstrates significant improvement over end-to-end models on comprehensive evaluation sets, including multiple domains, accents/dialects and languages. Additionally, Seed-ASR can be further deployed to support specific needs in various scenarios without requiring extra language models. Compared to recently released large ASR models, Seed-ASR achieves 10%-40% reduction in word (or character, for Chinese) error rates on Chinese and English public test sets, further demonstrating its powerful performance.

eess.AS↗

arXiv2024

Solving forward and inverse PDE problems on unknown manifolds via physics-informed neural operators

In this paper, we evaluate the effectiveness of deep operator networks (DeepONets) in solving both forward and inverse problems of partial differential equations (PDEs) on unknown manifolds. By unknown manifolds, we identify the manifold by a set of randomly sampled data point clouds that are assumed to lie on or close to the manifold. When the loss function incorporates the physics, resulting in the so-called physics-informed DeepONets (PI-DeepONets), we approximate the differentiation terms in the PDE by an appropriate operator approximation scheme. For the second-order elliptic PDE with a nontrivial diffusion coefficient, we approximate the differentiation term with one of these methods: the Diffusion Maps (DM), the Radial Basis Functions (RBF), and the Generalized Moving Least Squares (GMLS) methods. For the GMLS approximation, which is more flexible for problems with boundary conditions, we derive the theoretical error bound induced by the approximate differentiation. Numerically, we found that DeepONet is accurate for various types of diffusion coefficients, including linear, exponential, piecewise linear, and quadratic functions, for linear and semi-linear PDEs with/without boundaries. When the number of observations is small, PI-DeepONet trained with sufficiently large samples of PDE constraints produces more accurate approximations than DeepONet. For the inverse problem, we incorporate PI-DeepONet in a Bayesian Markov Chain Monte Carlo (MCMC) framework to estimate the diffusion coefficient from noisy solutions of the PDEs measured at a finite number of point cloud data. Numerically, we found that PI-DeepONet provides accurate approximations comparable to those obtained by a more expensive method that directly solves the PDE on the proposed diffusion coefficient in each MCMC iteration.

math.NA↗

arXiv2024

A Comprehensive Solution to Connect Speech Encoder and Large Language Model for ASR

Recent works have shown promising results in connecting speech encoders to large language models (LLMs) for speech recognition. However, several limitations persist, including limited fine-tuning options, a lack of mechanisms to enforce speech-text alignment, and high insertion errors especially in domain mismatch conditions. This paper presents a comprehensive solution to address these issues. We begin by investigating more thoughtful fine-tuning schemes. Next, we propose a matching loss to enhance alignment between modalities. Finally, we explore training and inference methods to mitigate high insertion errors. Experimental results on the Librispeech corpus demonstrate that partially fine-tuning the encoder and LLM using parameter-efficient methods, such as LoRA, is the most cost-effective approach. Additionally, the matching loss improves modality alignment, enhancing performance. The proposed training and inference methods significantly reduce insertion errors.

cs.LG↗

arXiv2024

video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models

Speech understanding as an element of the more generic video understanding using audio-visual large language models (av-LLMs) is a crucial yet understudied aspect. This paper proposes video-SALMONN, a single end-to-end av-LLM for video processing, which can understand not only visual frame sequences, audio events and music, but speech as well. To obtain fine-grained temporal information required by speech understanding, while keeping efficient for other video elements, this paper proposes a novel multi-resolution causal Q-Former (MRC Q-Former) structure to connect pre-trained audio-visual encoders and the backbone large language model. Moreover, dedicated training approaches including the diversity loss and the unpaired audio-visual mixed training scheme are proposed to avoid frames or modality dominance. On the introduced speech-audio-visual evaluation benchmark, video-SALMONN achieves more than 25\% absolute accuracy improvements on the video-QA task and over 30\% absolute accuracy improvements on audio-visual QA tasks with human speech. In addition, video-SALMONN demonstrates remarkable video comprehension and reasoning abilities on tasks that are unprecedented by other av-LLMs. Our training code and model checkpoints are available at \texttt{\url{https://github.com/bytedance/SALMONN/}}.

cs.CV↗

arXiv2024

Can Large Language Models Understand Spatial Audio?

This paper explores enabling large language models (LLMs) to understand spatial information from multichannel audio, a skill currently lacking in auditory LLMs. By leveraging LLMs' advanced cognitive and inferential abilities, the aim is to enhance understanding of 3D environments via audio. We study 3 spatial audio tasks: sound source localization (SSL), far-field speech recognition (FSR), and localisation-informed speech extraction (LSE), achieving notable progress in each task. For SSL, our approach achieves an MAE of $2.70^{\circ}$ on the Spatial LibriSpeech dataset, substantially surpassing the prior benchmark of about $6.60^{\circ}$. Moreover, our model can employ spatial cues to improve FSR accuracy and execute LSE by selectively attending to sounds originating from a specified direction via text prompts, even amidst overlapping speech. These findings highlight the potential of adapting LLMs to grasp physical audio concepts, paving the way for LLM-based agents in 3D environments.

cs.SD↗

arXiv2024

MINT: Boosting Audio-Language Model via Multi-Target Pre-Training and Instruction Tuning

In the realm of audio-language pre-training (ALP), the challenge of achieving cross-modal alignment is significant. Moreover, the integration of audio inputs with diverse distributions and task variations poses challenges in developing generic audio-language models. In this study, we present MINT, a novel ALP framework boosting audio-language models through multi-target pre-training and instruction tuning. MINT leverages the strength of frozen pre-trained audio encoders and large language models (LLM) to improve audio-language pre-training, enabling effective transferablility to both audio-text understanding and generation tasks. To address the modality gap, we introduce Bridge-Net, a trainable module that enhances cross-modality alignment and the model's ability to follow instructions for a variety of audio-text tasks. Bridge-Net is pivotal within MINT, initially enhancing audio-language representation learning through a multi-target pre-training approach. Subsequently, Bridge-Net further boosts audio-to-language generative learning by integrating a frozen language model with instruction tuning. This integration empowers MINT to extract features in a flexible and effective manner, specifically tailored to the provided instructions for diverse tasks. Experimental results demonstrate that MINT attains superior performance across various audio-language understanding and generation tasks, highlighting its robust generalization capabilities even in zero-shot scenarios.

cs.SD↗

arXiv2024

Dual-Pipeline with Low-Rank Adaptation for New Language Integration in Multilingual ASR

This paper addresses challenges in integrating new languages into a pre-trained multilingual automatic speech recognition (mASR) system, particularly in scenarios where training data for existing languages is limited or unavailable. The proposed method employs a dual-pipeline with low-rank adaptation (LoRA). It maintains two data flow pipelines-one for existing languages and another for new languages. The primary pipeline follows the standard flow through the pre-trained parameters of mASR, while the secondary pipeline additionally utilizes language-specific parameters represented by LoRA and a separate output decoder module. Importantly, the proposed approach minimizes the performance degradation of existing languages and enables a language-agnostic operation mode, facilitated by a decoder selection strategy. We validate the effectiveness of the proposed method by extending the pre-trained Whisper model to 19 new languages from the FLEURS dataset

eess.AS↗

arXiv2024

A spectral Erdős-Rademacher theorem

A classical result of Erdős and Rademacher (1955) indicates a supersaturation phenomenon. It says that if $G$ is a graph on $n$ vertices with at least $\lfloor {n^2}/{4} \rfloor +1$ edges, then $G$ contains at least $\lfloor {n}/{2}\rfloor$ triangles. We prove a spectral version of Erdős--Rademacher's theorem. Moreover, Mubayi [Adv. Math. 225 (2010)] extends the result of Erdős and Rademacher from a triangle to any color-critical graph. It is interesting to study the extension of Mubayi from a spectral perspective. However, it is not apparent to measure the increment on the spectral radius of a graph comparing to the traditional edge version (Mubayi's result). In this paper, we provide a way to measure the increment on the spectral radius of a graph and propose a spectral version on the counting problems for color-critical graphs.

math.CO↗

arXiv2024

One-shot learning for solution operators of partial differential equations

Learning and solving governing equations of a physical system, represented by partial differential equations (PDEs), from data is a central challenge in a variety of areas of science and engineering. Traditional numerical methods for solving PDEs can be computationally expensive for complex systems and require the complete PDEs of the physical system. On the other hand, current data-driven machine learning methods require a large amount of data to learn a surrogate model of the PDE solution operator, which could be impractical. Here, we propose the first solution operator learning method that only requires one PDE solution, i.e., one-shot learning. By leveraging the principle of locality of PDEs, we consider small local domains instead of the entire computational domain and define a local solution operator. The local solution operator is then trained using a neural network, and utilized to predict the solution of a new input function via mesh-based fixed-point iteration (FPI), meshfree local-solution-operator informed neural network (LOINN) or local-solution-operator informed neural network with correction (cLOINN). We test our method on diverse PDEs, including linear or nonlinear PDEs, PDEs defined on complex geometries, and PDE systems, demonstrating the effectiveness and generalization capabilities of our method across these varied scenarios.

cs.LG↗

arXiv2024

Seed-TTS: A Family of High-Quality Versatile Speech Generation Models

We introduce Seed-TTS, a family of large-scale autoregressive text-to-speech (TTS) models capable of generating speech that is virtually indistinguishable from human speech. Seed-TTS serves as a foundation model for speech generation and excels in speech in-context learning, achieving performance in speaker similarity and naturalness that matches ground truth human speech in both objective and subjective evaluations. With fine-tuning, we achieve even higher subjective scores across these metrics. Seed-TTS offers superior controllability over various speech attributes such as emotion and is capable of generating highly expressive and diverse speech for speakers in the wild. Furthermore, we propose a self-distillation method for speech factorization, as well as a reinforcement learning approach to enhance model robustness, speaker similarity, and controllability. We additionally present a non-autoregressive (NAR) variant of the Seed-TTS model, named $\text{Seed-TTS}_\text{DiT}$, which utilizes a fully diffusion-based architecture. Unlike previous NAR-based TTS systems, $\text{Seed-TTS}_\text{DiT}$ does not depend on pre-estimated phoneme durations and performs speech generation through end-to-end processing. We demonstrate that this variant achieves comparable performance to the language model-based variant and showcase its effectiveness in speech editing. We encourage readers to listen to demos at \url{https://bytedancespeech.github.io/seedtts_tech_report}.

eess.AS↗

arXiv2024

Challenges in Training PINNs: A Loss Landscape Perspective

This paper explores challenges in training Physics-Informed Neural Networks (PINNs), emphasizing the role of the loss landscape in the training process. We examine difficulties in minimizing the PINN loss function, particularly due to ill-conditioning caused by differential operators in the residual term. We compare gradient-based optimizers Adam, L-BFGS, and their combination Adam+L-BFGS, showing the superiority of Adam+L-BFGS, and introduce a novel second-order optimizer, NysNewton-CG (NNCG), which significantly improves PINN performance. Theoretically, our work elucidates the connection between ill-conditioned differential operators and ill-conditioning in the PINN loss and shows the benefits of combining first- and second-order optimization methods. Our work presents valuable insights and more powerful optimization strategies for training PINNs, which could improve the utility of PINNs for solving difficult partial differential equations.

cs.LG↗

arXiv2024

Promoting AI Equity in Science: Generalized Domain Prompt Learning for Accessible VLM Research

Large-scale Vision-Language Models (VLMs) have demonstrated exceptional performance in natural vision tasks, motivating researchers across domains to explore domain-specific VLMs. However, the construction of powerful domain-specific VLMs demands vast amounts of annotated data, substantial electrical energy, and computing resources, primarily accessible to industry, yet hindering VLM research in academia. To address this challenge and foster sustainable and equitable VLM research, we present the Generalized Domain Prompt Learning (GDPL) framework. GDPL facilitates the transfer of VLMs' robust recognition capabilities from natural vision to specialized domains, without the need for extensive data or resources. By leveraging small-scale domain-specific foundation models and minimal prompt samples, GDPL empowers the language branch with domain knowledge through quaternion networks, uncovering cross-modal relationships between domain-specific vision features and natural vision-based contextual embeddings. Simultaneously, GDPL guides the vision branch into specific domains through hierarchical propagation of generated vision prompt features, grounded in well-matched vision-language relations. Furthermore, to fully harness the domain adaptation potential of VLMs, we introduce a novel low-rank adaptation approach. Extensive experiments across diverse domains like remote sensing, medical imaging, geology, Synthetic Aperture Radar, and fluid dynamics, validate the efficacy of GDPL, demonstrating its ability to achieve state-of-the-art domain recognition performance in a prompt learning paradigm. Our framework paves the way for sustainable and inclusive VLM research, transcending the barriers between academia and industry.

cs.CV↗