Search Results for author:
Found 74 papers, 34 papers with code
Ignite Forecasting with SPARK: An Efficient Generative Framework for Refining LLMs in Temporal Knowledge Graph Forecasting
Temporal Knowledge Graph (TKG) forecasting is crucial for predicting future events using historical data.
Inductive Link Prediction on N-ary Relational Facts via Semantic Hypergraph Reasoning
The results highlight the superiority of the n-ary subgraph reasoning framework and the exceptional inductive ability of NS-HART.
A Language Vision Model Approach for Automated Tumor Contouring in Radiation Oncology
Conclusions: OCC represents a significant advance in oncology care, particularly through the use of the latest LVMs to improve contouring results by (1) streamlining oncology treatment workflows by optimizing tumor delineation, reducing manual processes; (2) offering a scalable and intuitive framework to reduce false positives in radiotherapy planning using LVMs; (3) introducing novel medical language vision prompt techniques to minimize LVMs hallucinations with ablation study, and (4) conducting a comparative analysis of LVMs, highlighting their potential in addressing medical language vision challenges.
MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization
In this paper, we propose a self-supervised music representation learning model for music understanding.
RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations
RecConv establishes a linear relationship between parameter growth and decomposing levels which determines the effective kernel size $k\times 2^\ell$ for a base kernel $k$ and $\ell$ levels of decomposition, while maintaining constant FLOPs regardless of the ERF expansion.
From Intention To Implementation: Automating Biomedical Research via LLMs
Conventional biomedical research is increasingly labor-intensive due to the exponential growth of scientific literature and datasets.
Infant Agent: A Tool-Integrated, Logic-Driven Agent with Cost-Effective API Usage
Despite the impressive capabilities of large language models (LLMs), they currently exhibit two primary limitations, \textbf{\uppercase\expandafter{\romannumeral 1}}: They struggle to \textbf{autonomously solve the real world engineering problem}.
Systematically Analyzing Prompt Injection Vulnerabilities in Diverse LLM Architectures
This study systematically analyzes the vulnerability of 36 large language models (LLMs) to various prompt injection attacks, a technique that leverages carefully crafted prompts to elicit malicious LLM behavior.
Apollo: Band-sequence Modeling for High-Quality Audio Restoration
Audio restoration has become increasingly significant in modern society, not only due to the demand for high-quality auditory experiences enabled by advanced playback devices, but also because the growing capabilities of generative audio models necessitate high-fidelity audio.
Revolutionizing Database Q&A with Large Language Models: Comprehensive Benchmark and Evaluation
However, there is still a lack of a comprehensive benchmark to evaluate the capabilities of different LLMs and their modular components in database QA.
Xinyu: An Efficient LLM-based System for Commentary Generation
To address the advanced requirements, we present an argument ranking model for arguments and establish a comprehensive evidence database that includes up-to-date events and classic books, thereby strengthening the substantiation of the evidence with retrieval augmented generation (RAG) technology.
RepNeXt: A Fast Multi-Scale CNN using Structural Reparameterization
In the realm of resource-constrained mobile vision tasks, the pursuit of efficiency and performance consistently drives innovation in lightweight Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs).
Semantic-Rearrangement-Based Multi-Level Alignment for Domain Generalized Segmentation
SRMA first incorporates a Semantic Rearrangement Module (SRM), which conducts semantic region randomization to enhance the diversity of the source domain sufficiently.
Reasoning on Efficient Knowledge Paths:Knowledge Graph Guides Large Language Model for Domain Question Answering
Especially for the question that require a multi-hop reasoning path, frequent calls to LLM will consume a lot of computing power.
Gull: A Generative Multifunctional Audio Codec
We introduce Gull, a generative multifunctional audio codec.
Ensuring Safe and High-Quality Outputs: A Guideline Library Approach for Language Models
Subsequently, the retrieval model correlates new inputs with relevant guidelines, which guide LLMs in response generation to ensure safe and high-quality outputs, thereby aligning with human values.
NewsBench: A Systematic Evaluation Framework for Assessing Editorial Capabilities of Large Language Models in Chinese Journalism
We present NewsBench, a novel evaluation framework to systematically assess the capabilities of Large Language Models (LLMs) for editorial capabilities in Chinese journalism.
Entire Chain Uplift Modeling with Context-Enhanced Learning for Intelligent Marketing
ECUP consists of two primary components: 1) the Entire Chain-Enhanced Network, which utilizes user behavior patterns to estimate ITE throughout the entire chain space, models the various impacts of treatments on each task, and integrates task prior information to enhance context awareness across all stages, capturing the impact of treatment on different tasks, and 2) the Treatment-Enhanced Network, which facilitates fine-grained treatment modeling through bit-level feature interactions, thereby enabling adaptive feature adjustment.
Subnetwork-to-go: Elastic Neural Network with Dynamic Training and Customizable Inference
Deploying neural networks to different devices or platforms is in general challenging, especially when the model size is large or model complexity is high.
AutoPrep: An Automatic Preprocessing Framework for In-the-Wild Speech Data
To address this issue, we introduce an automatic in-the-wild speech data preprocessing framework (AutoPrep) in this paper, which is designed to enhance speech quality, generate speaker labels, and produce transcriptions automatically.
ReZero: Region-customizable Sound Extraction
Being a solution to the R-SE task, the proposed ReZero framework includes (1) definitions of different types of spatial regions, (2) methods for region feature extraction and aggregation, and (3) a multi-channel extension of the band-split RNN (BSRNN) model specified for the R-SE task.
Ultra Dual-Path Compression For Joint Echo Cancellation And Noise Suppression
Echo cancellation and noise reduction are essential for full-duplex communication, yet most existing neural networks have high computational costs and are inflexible in tuning model complexity.
The Sound Demixing Challenge 2023 $\unicode{x2013}$ Music Demixing Track
We propose a formalization of the errors that can occur in the design of a training dataset for MSS systems and introduce two new datasets that simulate such errors: SDXDB23_LabelNoise and SDXDB23_Bleeding.
The Sound Demixing Challenge 2023 $\unicode{x2013}$ Cinematic Demixing Track
A significant source of this improvement was making the simulated data better match real cinematic audio, which we further investigate in detail.
LAW-Diffusion: Complex Scene Generation by Diffusion with Layouts
Thanks to the rapid development of diffusion models, unprecedented progress has been witnessed in image synthesis.
Graph Entropy Minimization for Semi-supervised Node Classification
Node classifiers are required to comprehensively reduce prediction errors, training resources, and inference latency in the industry.
Enhancing Chain-of-Thoughts Prompting with Iterative Bootstrapping in Large Language Models
By utilizing iterative bootstrapping, our approach enables LLMs to autonomously rectify errors, resulting in more precise and comprehensive reasoning chains.
High Fidelity Speech Enhancement with Band-split RNN
Despite the rapid progress in speech enhancement (SE) research, enhancing the quality of desired speech in environments with strong noise and interfering speakers remains challenging.
Ranked #3 on
Speech Enhancement
on Deep Noise Suppression (DNS) Challenge
(SI-SDR-WB metric)
Unifying Label-inputted Graph Neural Networks with Deep Equilibrium Models
The unification facilitates the exchange between the two subdomains and inspires more studies.
3D Matting: A Benchmark Study on Soft Segmentation Method for Pulmonary Nodules Applied in Computed Tomography
In this work, we introduce the image matting into the 3D scenes and use the alpha matte, i. e., a soft mask, to describe lesions in a 3D medical image.
Music Source Separation with Band-split RNN
The performance of music source separation (MSS) models has been greatly improved in recent years thanks to the development of novel neural network architectures and training pipelines.
Ranked #3 on
Music Source Separation
on MUSDB18
(using extra training data)
Virtual impactor-based label-free bio-aerosol detection using holography and deep learning
To address this need, we present a mobile and cost-effective label-free bio-aerosol sensor that takes holographic images of flowing particulate matter concentrated by a virtual impactor, which selectively slows down and guides particles larger than ~6 microns to fly through an imaging window.
Massively Parallel Universal Linear Transformations using a Wavelength-Multiplexed Diffractive Optical Network
We report deep learning-based design of a massively parallel broadband diffractive neural network for all-optically performing a large group of arbitrarily-selected, complex-valued linear transformations between an input and output field-of-view, each with N_i and N_o pixels, respectively.
FRA-RIR: Fast Random Approximation of the Image-source Method
The training of modern speech processing systems often requires a large amount of simulated room impulse response (RIR) data in order to allow the systems to generalize well in real-world, reverberant environments.
All-optical image classification through unknown random diffusers using a single-pixel diffractive network
Classification of an object behind a random and unknown scattering medium sets a challenging task for computational imaging and machine vision fields.
Super-resolution image display using diffractive decoders
We report a deep learning-enabled diffractive display design that is based on a jointly-trained pair of an electronic encoder and a diffractive optical decoder to synthesize/project super-resolved images using low-resolution wavefront modulators.
To image, or not to image: Class-specific diffractive cameras with all-optical erasure of undesired objects
Here, we demonstrate a camera design that performs class-specific imaging of target objects with instantaneous all-optical erasure of other classes of objects.
Analysis of Diffractive Neural Networks for Seeing Through Random Diffusers
During its training, random diffusers with a range of correlation lengths were used to improve the diffractive network's generalization performance.
Inferring from References with Differences for Semi-Supervised Node Classification on Graphs
Following the application of Deep Learning to graphic data, Graph Neural Networks (GNNs) have become the dominant method for Node Classification on graphs in recent years.
Ranked #4 on
Node Classification
on Coauthor CS
Node Representation Learning in Graph via Node-to-Neighbourhood Mutual Information Maximization
In this work, we present a simple-yet-effective self-supervised node representation learning strategy via directly maximizing the mutual information between the hidden representations of nodes and their neighbourhood, which can be theoretically justified by its link to graph smoothing.
A Time-domain Real-valued Generalized Wiener Filter for Multi-channel Neural Separation Systems
Frequency-domain beamformers have been successful in a wide range of multi-channel neural separation systems in the past years.
Cascadable all-optical NAND gates using diffractive networks
Based on this architecture, we numerically optimized the design of a diffractive neural network composed of 4 passive layers to all-optically perform NAND operation using the diffraction of light, and cascaded these diffractive NAND gates to perform complex logical functions by successively feeding the output of one diffractive NAND gate into another.
Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
Nowadays, Graph Neural Networks (GNNs) following the Message Passing paradigm become the dominant way to learn on graphic data.
Ranked #1 on
Node Classification
on Cora Full with Public Split
Dynamic imaging and characterization of volatile aerosols in e-cigarette emissions using deep learning-based holographic microscopy
To evaluate the effects of e-liquid composition on aerosol dynamics, we measured the volatility of the particles generated by flavorless, nicotine-free e-liquids with various PG/VG volumetric ratios, revealing a negative correlation between the particles' volatility and the volumetric ratio of VG in the e-liquid.
Dual-Path Modeling for Long Recording Speech Separation in Meetings
A transformer-based dual-path system is proposed, which integrates transform layers for global modeling.
Holographic image reconstruction with phase recovery and autofocusing using recurrent neural networks
Digital holography is one of the most widely used label-free microscopy techniques in biomedical imaging.
Memory-Associated Differential Learning
Conventional Supervised Learning approaches focus on the mapping from input features to output labels.
Ranked #1 on
Link Property Prediction
on ogbl-ddi
Continuous Speech Separation Using Speaker Inventory for Long Multi-talker Recording
Leveraging additional speaker information to facilitate speech separation has received increasing attention in recent years.
Group Communication with Context Codec for Lightweight Source Separation
A context codec module, containing a context encoder and a context decoder, is designed as a learnable downsampling and upsampling module to decrease the length of a sequential feature processed by the separation module.
Drone LAMS: A Drone-based Face Detection Dataset with Large Angles and Many Scenarios
This work presented a new drone-based face detection dataset Drone LAMS in order to solve issues of low performance of drone-based face detection in scenarios such as large angles which was a predominant working condition when a drone flies high.
Integration of speech separation, diarization, and recognition for multi-speaker meetings: System description, comparison, and analysis
Multi-speaker speech recognition of unsegmented recordings has diverse applications such as meeting transcription and automatic subtitle generation.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Integrated Gallium Nitride Nonlinear Photonics
Thanks to its high nonlinearity and high refractive index contrast, GaN-on-insulator (GaNOI) is also a promising platform for nonlinear optical applications.
Optics Applied Physics
An End-to-end Architecture of Online Multi-channel Speech Separation
Previously, we introduced a sys-tem, calledunmixing, fixed-beamformerandextraction(UFE), that was shown to be effective in addressing the speech over-lap problem in conversation transcription.
Deep learning-based holographic polarization microscopy
Our analysis shows that a trained deep neural network can extract the birefringence information using both the sample specific morphological features as well as the holographic amplitude and phase distribution.
Terahertz Pulse Shaping Using Diffractive Surfaces
Recent advances in deep learning have been providing non-intuitive solutions to various inverse problems in optics.
Spectrally-Encoded Single-Pixel Machine Vision Using Diffractive Networks
3D engineering of matter has opened up new avenues for designing systems that can perform various computational tasks through light-matter interaction.
Separating Varying Numbers of Sources with Auxiliary Autoencoding Loss
Many recent source separation systems are designed to separate a fixed number of sources out of a mixture.
Continuous speech separation: dataset and analysis
In this paper, we define continuous speech separation (CSS) as a task of generating a set of non-overlapped speech signals from a \textit{continuous} audio stream that contains multiple utterances that are \emph{partially} overlapped by a varying degree.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
End-to-end Microphone Permutation and Number Invariant Multi-channel Speech Separation
An important problem in ad-hoc microphone speech separation is how to guarantee the robustness of a system with respect to the locations and numbers of microphones.
Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation
Recent studies in deep learning-based speech separation have proven the superiority of time-domain approaches to conventional time-frequency-based methods.
Ranked #29 on
Speech Separation
on WSJ0-2mix
FaSNet: Low-latency Adaptive Beamforming for Multi-microphone Audio Processing
Beamforming has been extensively investigated for multi-channel audio processing tasks.
Design of Task-Specific Optical Systems Using Broadband Diffractive Neural Networks
We report a broadband diffractive optical neural network design that simultaneously processes a continuum of wavelengths generated by a temporally-incoherent broadband source to all-optically perform a specific task learned using deep learning.
Class-specific Differential Detection in Diffractive Optical Neural Networks Improves Inference Accuracy
Similar to ensemble methods practiced in machine learning, we also independently-optimized multiple differential diffractive networks that optically project their light onto a common detector plane, and achieved testing accuracies of 98. 59%, 91. 06% and 51. 44% for MNIST, Fashion-MNIST and grayscale CIFAR-10, respectively.
Demand Prediction for Electric Vehicle Sharing
Electric Vehicle (EV) sharing systems have recently experienced unprecedented growth across the globe.
Adversarial Defense of Image Classification Using a Variational Auto-Encoder
Deep neural networks are known to be vulnerable to adversarial attacks.
Response to Comment on "All-optical machine learning using diffractive deep neural networks"
In their Comment, Wei et al. (arXiv:1809. 08360v1 [cs. LG]) claim that our original interpretation of Diffractive Deep Neural Networks (D2NN) represent a mischaracterization of the system due to linearity and passivity.
Analysis of Diffractive Optical Neural Networks and Their Integration with Electronic Neural Networks
Furthermore, we report the integration of D2NNs with electronic neural networks to create hybrid-classifiers that significantly reduce the number of input pixels into an electronic network using an ultra-compact front-end D2NN with a layer-to-layer distance of a few wavelengths, also reducing the complexity of the successive electronic network.
Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
The majority of the previous methods have formulated the separation problem through the time-frequency representation of the mixed signal, which has several drawbacks, including the decoupling of the phase and magnitude of the signal, the suboptimality of time-frequency representation for speech separation, and the long latency in calculating the spectrograms.
Ranked #2 on
Multi-task Audio Source Seperation
on MTASS
Multi-task Audio Source Seperation
Music Source Separation
+3
Real-time Single-channel Dereverberation and Separation with Time-domainAudio Separation Network
We investigate the recently proposed Time-domain Audio Sep-aration Network (TasNet) in the task of real-time single-channel speech dereverberation.
Ranked #37 on
Speech Separation
on WSJ0-2mix
TasNet: time-domain audio separation network for real-time, single-channel speech separation
We directly model the signal in the time-domain using an encoder-decoder framework and perform the source separation on nonnegative encoder outputs.
Ranked #39 on
Speech Separation
on WSJ0-2mix
Point Set Registration With Global-Local Correspondence and Transformation Estimation
We present a new point set registration method with global-local correspondence and transformation estimation (GL-CATE).
Speaker-independent Speech Separation with Deep Attractor Network
A reference point attractor is created in the embedding space to represent each speaker which is defined as the centroid of the speaker in the embedding space.
Deep attractor network for single-microphone speaker separation
We propose a novel deep learning framework for single channel speech separation by creating attractor points in high dimensional embedding space of the acoustic signals which pull together the time-frequency bins corresponding to each source.
Deep Clustering and Conventional Networks for Music Separation: Stronger Together
Deep clustering is the first method to handle general audio separation scenarios with multiple sources of the same type and an arbitrary number of sources, performing impressively in speaker-independent speech separation tasks.
