Search Results for author:
Found 161 papers, 50 papers with code
SecFwT: Efficient Privacy-Preserving Fine-Tuning of Large Language Models Using Forward-Only Passes
Large language models (LLMs) have transformed numerous fields, yet their adaptation to specialized tasks in privacy-sensitive domains, such as healthcare and finance, is constrained by the scarcity of accessible training data due to stringent privacy requirements.
StreamMel: Real-Time Zero-shot Text-to-Speech via Interleaved Continuous Autoregressive Modeling
Recent advances in zero-shot text-to-speech (TTS) synthesis have achieved high-quality speech generation for unseen speakers, but most systems remain unsuitable for real-time applications because of their offline design.
OmniDRCA: Parallel Speech-Text Foundation Model via Dual-Resolution Speech Representations and Contrastive Alignment
This paper presents OmniDRCA, a parallel speech-text foundation model based on joint autoregressive modeling, featuring dual-resolution speech representations and contrastive cross-modal alignment.
STELLA: Towards Protein Function Prediction with Multimodal LLMs Integrating Sequence-Structure Representations
Since protein sequences determine tertiary structures, which in turn govern functions, integrating sequence and structure information is essential for accurate prediction of protein functions.
A survey of using EHR as real-world evidence for discovering and validating new drug indications
Electronic Health Records (EHRs) have been increasingly used as real-world evidence (RWE) to support the discovery and validation of new drug indications.
TC-GS: A Faster Gaussian Splatting Module Utilizing Tensor Cores
3D Gaussian Splatting (3DGS) renders pixels by rasterizing Gaussian primitives, where conditional alpha-blending dominates the time cost in the rendering pipeline.
Zero-Shot Streaming Text to Speech Synthesis with Transducer and Auto-Regressive Modeling
Zero-shot streaming text-to-speech is an important research topic in human-computer interaction.
Enhancing Generalization of Speech Large Language Models with Multi-Task Behavior Imitation and Speech-Text Interleaving
These speech LLMs (SLLMs) typically use supervised fine-tuning to align speech with text-based LLMs.
CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training
Despite these advancements, CosyVoice 2 exhibits limitations in language coverage, domain diversity, data volume, text formats, and post-training techniques.
Pushing the Frontiers of Self-Distillation Prototypes Network with Dimension Regularization and Score Normalization
Developing robust speaker verification (SV) systems without speaker labels has been a longstanding challenge.
Chinese-LiPS: A Chinese audio-visual speech recognition dataset with Lip-reading and Presentation Slides
Incorporating visual modalities to assist Automatic Speech Recognition (ASR) tasks has led to significant improvements.
Audio-Visual Speech Recognition
Automatic Speech Recognition
+4
From Large to Super-Tiny: End-to-End Optimization for Cost-Efficient LLMs
In this paper, we introduce a three-stage cost-efficient end-to-end LLM deployment pipeline, comprising prototyping, knowledge transfer, and model compression, to effectively tackle the cost-performance dilemma in LLM-based frameworks.
LightFormer: A lightweight and efficient decoder for remote sensing image segmentation
Deep learning techniques have achieved remarkable success in the semantic segmentation of remote sensing images and in land-use change detection.
Pseudo-Autoregressive Neural Codec Language Models for Efficient Zero-Shot Text-to-Speech Synthesis
Building on PAR, we propose PALLE, a two-stage TTS system that leverages PAR for initial generation followed by NAR refinement.
LLM-Gomoku: A Large Language Model-Based System for Strategic Gomoku with Self-Play and Reinforcement Learning
This study aims to develop a Gomoku AI system based on LLMs, simulating the human learning process of playing chess.
Deep Learning-Based Quantitative Assessment of Renal Chronicity Indices in Lupus Nephritis
Additionally, the DL pipeline enhanced prognostic accuracy, particularly in outcome prediction, when combined with clinical parameters and pathologist-assessed CIs Conclusions: The DL pipeline demonstrated accuracy and efficiency in assessing CI in LN, showing promise in improving interobserver agreement among pathologists.
RoCA: Robust Contrastive One-class Time Series Anomaly Detection with Contaminated Data
It fuses the separated assumptions of one-class classification and contrastive learning in a single training process to characterize a more complete so-called normality.
SeniorTalk: A Chinese Conversation Dataset with Rich Annotations for Super-Aged Seniors
While voice technologies increasingly serve aging populations, current systems exhibit significant performance gaps due to inadequate training data capturing elderly-specific vocal characteristics like presbyphonia and dialectal variations.
Enhancing Non-English Capabilities of English-Centric Large Language Models through Deep Supervision Fine-Tuning
Large language models (LLMs) have demonstrated significant progress in multilingual language understanding and generation.
CS-Dialogue: A 104-Hour Dataset of Spontaneous Mandarin-English Code-Switching Dialogues for Speech Recognition
Code-switching (CS), the alternation between two or more languages within a single conversation, presents significant challenges for automatic speech recognition (ASR) systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
MA-GTS: A Multi-Agent Framework for Solving Complex Graph Problems in Real-World Applications
To address these challenges, we propose MA-GTS (Multi-Agent Graph Theory Solver), a multi-agent framework that decomposes these complex problems through agent collaboration.
NVR: Vector Runahead on NPUs for Sparse Memory Access
In this paper, we present NPU Vector Runahead (NVR), a prefetching mechanism tailored for NPUs to address cache miss problems in sparse DNN workloads.
SpeHeatal: A Cluster-Enhanced Segmentation Method for Sperm Morphology Analysis
The accurate assessment of sperm morphology is crucial in andrological diagnostics, where the segmentation of sperm images presents significant challenges.
One for All: A General Framework of LLMs-based Multi-Criteria Decision Making on Human Expert Level
The experimental results show that the accuracy rates for different applications improve significantly to around 95\%, and the performance difference is trivial between different models, indicating that LoRA-based fine-tuned LLMs exhibit significant and stable advantages in addressing MCDM tasks and can provide human-expert-level solutions to a wide range of MCDM challenges.
Planning of Heuristics: Strategic Planning on Large Language Models with Monte Carlo Tree Search for Automating Heuristic Optimization
Heuristics have achieved great success in solv- ing combinatorial optimization problems (COPs).
TSS GAZ PTP: Towards Improving Gumbel AlphaZero with Two-stage Self-play for Multi-constrained Electric Vehicle Routing Problems
Recently, Gumbel AlphaZero~(GAZ) was proposed to solve classic combinatorial optimization problems such as TSP and JSSP by creating a carefully designed competition model~(consisting of a learning player and a competitor player), which leverages the idea of self-play.
FELLE: Autoregressive Speech Synthesis with Token-Wise Coarse-to-Fine Flow Matching
To advance continuous-valued token modeling and temporal-coherence enforcement, we propose FELLE, an autoregressive model that integrates language modeling with token-wise flow matching.
Pushing the Limits of BFP on Narrow Precision LLM Inference
The substantial computational and memory demands of Large Language Models (LLMs) hinder their deployment.
Leveraging Chain of Thought towards Empathetic Spoken Dialogue without Corresponding Question-Answering Data
Empathetic dialogue is crucial for natural human-computer interaction, allowing the dialogue system to respond in a more personalized and emotionally aware manner, improving user satisfaction and engagement.
MinMo: A Multimodal Large Language Model for Seamless Voice Interaction
Previous models for voice interactions are categorized as native and aligned.
Planarian Neural Networks: Evolutionary Patterns from Basic Bilateria Shaping Modern Artificial Neural Network Architectures
This study examined the viability of enhancing the prediction accuracy of artificial neural networks (ANNs) in image classification tasks by developing ANNs with evolution patterns similar to those of biological neural networks.
Improving the Training of Data-Efficient GANs via Quality Aware Dynamic Discriminator Rejection Sampling
Specifically, QADDRS consists of two steps: (1) the sample quality aware step, which aims to obtain the sorted critic scores, i. e., the ordered discriminator outputs, on real/fake samples in the current training stage; (2) the dynamic rejection step that obtains dynamic rejection number N, where N is controlled by the overfitting degree of discriminator (D) during training.
Enhancing Multimodal Emotion Recognition through Multi-Granularity Cross-Modal Alignment
Multimodal emotion recognition (MER), leveraging speech and text, has emerged as a pivotal domain within human-computer interaction, demanding sophisticated methods for effective multimodal integration.
Ensuring Consistency for In-Image Translation
Subsequently, a diffusion model trained for style-consistent text-image generation ensures uniformity in text style within images and preserves background details.
Correcting Large Language Model Behavior via Influence Function
Recent advancements in AI alignment techniques have significantly improved the alignment of large language models (LLMs) with static human preferences.
Interleaved Speech-Text Language Models are Simple Streaming Text to Speech Synthesizers
This paper introduces Interleaved Speech-Text Language Model (IST-LM) for streaming zero-shot Text-to-Speech (TTS).
Split Knowledge Distillation for Large Models in IoT: Architecture, Challenges, and Solutions
Large models (LMs) have immense potential in Internet of Things (IoT) systems, enabling applications such as intelligent voice assistants, predictive maintenance, and healthcare monitoring.
CENTAUR: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference
With the growing deployment of pre-trained models like Transformers on cloud platforms, privacy concerns about model parameters and inference data are intensifying.
CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models
By training on a large-scale multilingual dataset, CosyVoice 2 achieves human-parity naturalness, minimal response latency, and virtually lossless synthesis quality in the streaming mode.
Addressing bias in Recommender Systems: A Case Study on Data Debiasing Techniques in Mobile Games
This case study aims to identify and categorize potential bias within datasets specific to model-based recommendations in mobile games, review debiasing techniques in the existing literature, and assess their effectiveness on real-world data gathered through implicit feedback.
Transcending Language Boundaries: Harnessing LLMs for Low-Resource Language Translation
Our comparison with the zero-shot performance of GPT-4o and LLaMA 3. 1 405B, highlights the significant challenges these models face when translating into low-resource languages.
Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent
To bridge the dataset gap, we first construct Dyn-VQA dataset, consisting of three types of "dynamic" questions, which require complex knowledge retrieval strategies variable in query, tool, and time: (1) Questions with rapidly changing answers.
Innovative Thinking, Infinite Humor: Humor Research of Large Language Models through Structured Thought Leaps
Humor is a culturally nuanced aspect of human language that presents challenges for understanding and generation, requiring participants to possess good creativity and strong associative thinking.
A Systematic Assessment of OpenAI o1-Preview for Higher Order Thinking in Education
This study evaluates OpenAI o1-preview's ability to perform higher-order cognitive tasks across 14 dimensions, including critical thinking, systems thinking, computational thinking, design thinking, metacognition, data literacy, creative thinking, abstract reasoning, quantitative reasoning, logical reasoning, analogical reasoning, and scientific reasoning.
Chip-Tuning: Classify Before Language Models Say
After selecting a chip for classification, all layers subsequent to the attached layer could be removed with marginal performance loss.
Open-Nav: Exploring Zero-Shot Vision-and-Language Navigation in Continuous Environment with Open-Source LLMs
Vision-and-Language Navigation (VLN) tasks require an agent to follow textual instructions to navigate through 3D environments.
Evaluation of OpenAI o1: Opportunities and Challenges of AGI
-Impressive performance in chip design tasks, outperforming specialized models in areas such as EDA script generation and bug analysis.
IRSC: A Zero-shot Evaluation Benchmark for Information Retrieval through Semantic Comprehension in Retrieval-Augmented Generation Scenarios
In Retrieval-Augmented Generation (RAG) tasks using Large Language Models (LLMs), the quality of retrieved information is critical to the final output.
Trustworthy Hate Speech Detection Through Visual Augmentation
The surge of hate speech on social media platforms poses a significant challenge, with hate speech detection~(HSD) becoming increasingly critical.
Exploring Text-Queried Sound Event Detection with Audio Source Separation
To address this issue, we propose the text-queried SED (TQ-SED) framework.
Video-CCAM: Enhancing Video-Language Understanding with Causal Cross-Attention Masks for Short and Long Videos
To address these limitations, we apply cross-attention layers in the intermediate projector between the visual encoder and the large language model (LLM).
Uncertainty-Aware Mean Opinion Score Prediction
Mean Opinion Score (MOS) prediction has made significant progress in specific domains.
Dynamics of Meta-learning Representation in the Teacher-student Scenario
Gradient-based meta-learning algorithms have gained popularity for their ability to train models on new tasks using limited data.
Integrating Audio, Visual, and Semantic Information for Enhanced Multimodal Speaker Diarization
Then we introduce a joint pairwise constraint propagation algorithm to cluster speakers based on these visual and semantic constraints.
Blind Image Deconvolution by Generative-based Kernel Prior and Initializer via Latent Encoding
To alleviate this issue and further improve their performance, we propose a new framework for BID that better considers the prior modeling and the initialization for blur kernels, leveraging a deep generative model.
MetaTool: Facilitating Large Language Models to Master Tools with Meta-task Augmentation
Training on solution paths is also hindered by the high cost of expert annotations and generalizing to new tools.
CS3: Cascade SAM for Sperm Segmentation
Automated sperm morphology analysis plays a crucial role in the assessment of male fertility, yet its efficacy is often compromised by the challenges in accurately segmenting sperm images.
The geographic flow of bank funding and access to credit: Branch networks, local synergies and competition
Geographic dispersion of depositors, borrowers, and banks may prevent funding from flowing to high loan demand areas, limiting credit access.
GraCoRe: Benchmarking Graph Comprehension and Complex Reasoning in Large Language Models
Evaluating the graph comprehension and reasoning abilities of Large Language Models (LLMs) is challenging and often incomplete.
Neurovascular Segmentation in sOCT with Deep Learning and Synthetic Training Data
Microvascular anatomy is known to be involved in various neurological disorders.
SMLT-MUGC: Small, Medium, and Large Texts -- Machine versus User-Generated Content Detection and Comparison
This paper analyzes datasets of varying text lengths: small, medium, and large.
Self-Distillation Prototypes Network: Learning Robust Speaker Representations without Supervision
SDPN assigns the representation of the augmented views of an utterance to the same prototypes as the representation of the original view, thereby enabling effective knowledge transfer between the views.
Hacking Encrypted Wireless Power: Cyber-Security of Dynamic Charging
To stimulate the progress of energy encryption technology and point out security holes, this paper proposes a decryption method for the fundamental principle of encrypted frequency-varying wireless power transfer.
LAFMA: A Latent Flow Matching Model for Text-to-Audio Generation
And the effectiveness of the method is accompanied by the extensive number of sampling steps, leading to an extended synthesis time necessary for generating high-quality audio.
Improving Zero-Shot Chinese-English Code-Switching ASR with kNN-CTC and Gated Monolingual Datastores
To address this, we propose a novel kNN-CTC-based code-switching ASR (CS-ASR) framework that employs dual monolingual datastores and a gated datastore selection mechanism to reduce noise interference.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
ERes2NetV2: Boosting Short-Duration Speaker Verification Performance with Computational Efficiency
Speaker verification systems experience significant performance degradation when tasked with short-duration trial recordings.
Deep Reinforcement Learning for 5*5 Multiplayer Go
In recent years, much progress has been made in computer Go and most of the results have been obtained thanks to search algorithms (Monte Carlo Tree Search) and Deep Reinforcement Learning (DRL).
A label-free and data-free training strategy for vasculature segmentation in serial sectioning OCT data
Serial sectioning Optical Coherence Tomography (sOCT) is a high-throughput, label free microscopic imaging technique that is becoming increasingly popular to study post-mortem neurovasculature.
Relay Decoding: Concatenating Large Language Models for Machine Translation
Leveraging large language models for machine translation has demonstrated promising results.
Ensemble Learning for Heterogeneous Large Language Models with Deep Parallel Collaboration
To address this challenge, DeePEn maps the probability distribution of each model from its own probability space to a universal relative space based on the relative representation theory, and performs aggregation.
3D-Speaker-Toolkit: An Open-Source Toolkit for Multimodal Speaker Verification and Diarization
With 3D-Speaker-Toolkit, we establish a new benchmark for multimodal speaker analysis.
UltraWiki: Ultra-fine-grained Entity Set Expansion with Negative Seed Entities
To solve this issue, we first introduce negative seed entities in the inputs, which belong to the same fine-grained semantic class as the positive seed entities but differ in certain attributes.
Mitigating Biases of Large Language Models in Stance Detection with Counterfactual Augmented Calibration
Therefore, in this paper, we propose a Counterfactual Augmented Calibration Network (FACTUAL), which a novel calibration network is devised to calibrate potential bias in the stance prediction of LLMs.
COPR: Continual Human Preference Learning via Optimal Policy Regularization
Reinforcement Learning from Human Feedback (RLHF) is commonly utilized to improve the alignment of Large Language Models (LLMs) with human preferences.
Small Object Detection by DETR via Information Augmentation and Adaptive Feature Fusion
This allows the model to adaptively fuse feature maps from different levels and effectively integrate feature information from different scales.
CPPO: Continual Learning for Reinforcement Learning with Human Feedback
The approach of Reinforcement Learning from Human Feedback (RLHF) is widely used for enhancing pre-trained Language Models (LM), enabling them to better align with human preferences.
Training and Serving System of Foundation Models: A Comprehensive Survey
Additionally, the paper summarizes the challenges and presents a perspective on the future development direction of foundation model systems.
SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC
With the growing use of Transformer models hosted on cloud platforms to offer inference services, privacy concerns are escalating, especially concerning sensitive data like investment plans and bank account details.
Image Super-resolution Reconstruction Network based on Enhanced Swin Transformer via Alternating Aggregation of Local-Global Features
In the local feature aggregation stage, we introduce a shift convolution to realize the interaction between local spatial information and channel information.
EncryIP: A Practical Encryption-Based Framework for Model Intellectual Property Protection
In the rapidly growing digital economy, protecting intellectual property (IP) associated with digital products has become increasingly important.
Multimodality of AI for Education: Towards Artificial General Intelligence
This paper presents a comprehensive examination of how multimodal artificial intelligence (AI) approaches are paving the way towards the realization of Artificial General Intelligence (AGI) in educational contexts.
Generative AI in Higher Education: Seeing ChatGPT Through Universities' Policies, Resources, and Guidelines
In order to respond to higher educators' needs, this study aims to explore how universities and educators respond and adapt to the development of GenAI in their academic contexts by analyzing academic policies and guidelines established by top-ranked U. S. universities regarding the use of GenAI, especially ChatGPT.
COPR: Continual Learning Human Preference through Optimal Policy Regularization
The technique of Reinforcement Learning from Human Feedback (RLHF) is a commonly employed method to improve pre-trained Language Models (LM), enhancing their ability to conform to human preferences.
Improving Speaker Diarization using Semantic Information: Joint Pairwise Constraints Propagation
Speaker diarization has gained considerable attention within speech processing research community.
SHAPE: A Sample-adaptive Hierarchical Prediction Network for Medication Recommendation
Effectively medication recommendation with complex multimorbidity conditions is a critical task in healthcare.
Intelligence-Endogenous Management Platform for Computing and Network Convergence
Therefore, in this article, we present the concept of an intelligence-endogenous management platform for CNCs called \emph{CNC brain} based on artificial intelligence technologies.
Self-Distillation Prototypes Network: Learning Robust Speaker Representations without Supervision
To mitigate this problem, we introduce a diversity regularization term to embeddings in SDPN.
Model Provenance via Model DNA
Understanding the life cycle of the machine learning (ML) model is an intriguing area of research (e. g., understanding where the model comes from, how it is trained, and how it is used).
Personalized Federated Learning via Amortized Bayesian Meta-Learning
Federated learning is a decentralized and privacy-preserving technique that enables multiple clients to collaborate with a server to learn a global model without exposing their private data.
3D-Speaker: A Large-Scale Multi-Device, Multi-Distance, and Multi-Dialect Corpus for Speech Representation Disentanglement
Disentangling uncorrelated information in speech utterances is a crucial research topic within speech community.
AOG-LSTM: An adaptive attention neural network for visual storytelling
Moreover, the existing method of alleviating error accumulation based on replacing reference words does not take into account the different effects of each word.
Ranked #20 on
Visual Storytelling
on VIST
Practical Privacy-Preserving Gaussian Process Regression via Secret Sharing
In contrast to existing studies that protect the data privacy of GPR via homomorphic encryption, differential privacy, or federated learning, our proposed method is more practical and can be used to preserve the data privacy of both the model inputs and outputs for various data-sharing scenarios (e. g., horizontally/vertically-partitioned data).
An Enhanced Res2Net with Local and Global Feature Fusion for Speaker Verification
This paper proposes a novel architecture called Enhanced Res2Net (ERes2Net), which incorporates both local and global feature fusion techniques to improve the performance.
Exploring Speaker-Related Information in Spoken Language Understanding for Better Speaker Diarization
In this paper, we propose methods to extract speaker-related information from semantic content in multi-party meetings, which, as we will show, can further benefit speaker diarization.
A novel parameter decoupling approach of personalized federated learning for image analysis
To address the problem of the statistical heterogeneity in image analysis, PCCFED, a personalised federated learning method utilizing the strategy of parameter decoupling is proposed.
Towards Tackling MaxSAT by Combining Nested Monte Carlo with Local Search
First, a nesting of the tree search inspired by the Nested Monte Carlo Search algorithm is effective on most instance types in the benchmark.
The most probable dynamics of receptor-ligand binding on cell membrane
We consider the dynamics of a receptor binding to a ligand on the cell membrane, where the receptor and ligand perform different motions and are thus modeled by stochastic differential equations with Gaussian noise or non-Gaussian noise.
Semantic Feature Integration network for Fine-grained Visual Classification
By eliminating unnecessary features and reconstructing the semantic relations among discriminative features, our SFI-Net has achieved satisfying performance.
Robust Split Federated Learning for U-shaped Medical Image Networks
To achieve this goal, in this paper, we propose Robust Split Federated Learning (RoS-FL) for U-shaped medical image networks, which is a novel hybrid learning paradigm of FL and SL.
Integrated optimization of train timetables rescheduling and response vehicles on a disrupted metro line
Numerical cases of Beijing Metro Line 9 verify the efficiency and effectiveness of our proposed model, and results show that: (1) when occurring a disruption event during peak hours, the impact on the normal timetable is greater, and passengers in the direction with fewer train services are more affected; (2) if passengers stranded at the terminal stations of disruption area are not transported in time, they will rapidly increase at a speed of more than 300 passengers per minute; (3) compared with the fixed shortest path, using the response vehicles reduces the total travel time about 7%.
Pushing the limits of self-supervised speaker verification using regularized distillation framework
A range of experiments conducted on the VoxCeleb datasets demonstrate the superiority of the regularized DINO framework in speaker verification.
A Secure and Efficient Multi-Object Grasping Detection Approach for Robotic Arms
However, with wide applications of deep learning in robotic arms, there are new challenges such as the allocation of grasping computing power and the growing demand for security.
Entropy-driven Sampling and Training Scheme for Conditional Diffusion Generation
Denoising Diffusion Probabilistic Model (DDPM) is able to make flexible conditional image generation from prior noise to real data, by introducing an independent noise-aware classifier to provide conditional gradient guidance at each time step of denoising process.
Ranked #2 on
Conditional Image Generation
on ImageNet 128x128
Motion Gait: Gait Recognition via Motion Excitation
Gait recognition, which can realize long-distance and contactless identification, is an important biometric technology.
Exploring evolution-aware & -free protein language models as protein function predictors
Large-scale Protein Language Models (PLMs) have improved performance in protein prediction tasks, ranging from 3D structure prediction to various function predictions.
Feature-aware Diversified Re-ranking with Disentangled Representations for Relevant Recommendation
Relevant recommendation is a special recommendation scenario which provides relevant items when users express interests on one target item (e. g., click, like and purchase).
Encoded Gradients Aggregation against Gradient Leakage in Federated Learning
However, privacy information could be leaked from uploaded gradients and be exposed to malicious attackers or an honest-but-curious server.
Cross-Enhancement Transformer for Action Segmentation
Temporal convolutions have been the paradigm of choice in action segmentation, which enhances long-term receptive fields by increasing convolution layers.
Ranked #7 on
Action Segmentation
on Breakfast
CATNet: Cross-event Attention-based Time-aware Network for Medical Event Prediction
It is a time-aware, event-aware and task-adaptive method with the following advantages: 1) modeling heterogeneous information and temporal information in a unified way and considering temporal irregular characteristics locally and globally respectively, 2) taking full advantage of correlations among different types of events via cross-event attention.
Unsupervised Quantized Prosody Representation for Controllable Speech Synthesis
In this paper, we propose a novel prosody disentangle method for prosodic Text-to-Speech (TTS) model, which introduces the vector quantization (VQ) method to the auxiliary prosody encoder to obtain the decomposed prosody representations in an unsupervised manner.
Graph-based Approximate NN Search: A Revisit
For the graph construction, a two-stage graph diversification scheme is proposed, which makes a good trade-off between the efficiency and reachability for the search procedure that builds upon it.
Multimodal data matters: language model pre-training over structured and unstructured electronic health records
As two important textual modalities in electronic health records (EHR), both structured data (clinical codes) and unstructured data (clinical narratives) have recently been increasingly applied to the healthcare domain.
PowerGear: Early-Stage Power Estimation in FPGA HLS via Heterogeneous Edge-Centric GNNs
Specifically, in the graph construction flow, we introduce buffer insertion, datapath merging, graph trimming and feature annotation techniques to transform HLS designs into graph-structured data, which encode both intra-operation micro-architectures and inter-operation interconnects annotated with switching activities.
A Survey on Neural-symbolic Learning Systems
In recent years, neural systems have demonstrated highly effective learning ability and superior perception intelligence.
Fast k-NN Graph Construction by GPU based NN-Descent
In this paper, NN-Descent has been redesigned to adapt to the GPU architecture.
Meter-Range Wireless Motor Drive for Pipeline Transportation
This paper proposes and implements a meter-range wireless motor drive (WMD) system for promising applications of underground pipeline transportations or in-pipe robots.
Dual-branch Attention-In-Attention Transformer for single-channel speech enhancement
Curriculum learning begins to thrive in the speech enhancement area, which decouples the original spectrum estimation task into multiple easier sub-tasks to achieve better performance.
A Two-stage Complex Network using Cycle-consistent Generative Adversarial Networks for Speech Enhancement
After that, the second stage is applied to further suppress the residual noise components and estimate the clean phase by a complex spectral mapping network, which is a pure complex-valued network composed of complex 2D convolution/deconvolution and complex temporal-frequency attention blocks.
FedLab: A Flexible Federated Learning Framework
Federated learning (FL) is a machine learning field in which researchers try to facilitate model learning process among multiparty without violating privacy protection regulations.
Progressive Class-based Expansion Learning For Image Classification
In this paper, we propose a novel image process scheme called class-based expansion learning for image classification, which aims at improving the supervision-stimulation frequency for the samples of the confusing classes.
Curriculum Pre-Training Heterogeneous Subgraph Transformer for Top-$N$ Recommendation
Due to the flexibility in modelling data heterogeneity, heterogeneous information network (HIN) has been adopted to characterize complex and heterogeneous auxiliary data in top-$N$ recommender systems, called \emph{HIN-based recommendation}.
A Deep Variational Bayesian Framework for Blind Image Deblurring
Under this framework, the posterior of the latent clean image and blur kernel can be jointly estimated in an amortized inference fashion with DNNs, and the involved inference DNNs can be trained by fully considering the physical blur model, together with the supervision of data driven priors for the clean image and blur kernel, which is naturally led to by the evidence lower bound objective.
Adaptive Warm-Start MCTS in AlphaZero-like Deep Reinforcement Learning
AlphaZero has achieved impressive performance in deep reinforcement learning by utilizing an architecture that combines search and training of a neural network in self-play.
Blockchain-Based Decentralized Energy Management Platform for Residential Distributed Energy Resources in A Virtual Power Plant
In this paper, we develop a blockchain-based VPP energy management platform to facilitate a rich set of transactive energy activities among residential users with renewables, energy storage, and flexible loads in a VPP.
PanGu-$α$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation
To enhance the generalization ability of PanGu-$\alpha$, we collect 1. 1TB high-quality Chinese data from a wide range of domains to pretrain the model.
Ranked #1 on
Reading Comprehension (One-Shot)
on DuReader
Cloze (multi-choices) (Few-Shot)
Cloze (multi-choices) (One-Shot)
+19
Large-Scale Approximate k-NN Graph Construction on GPU
NN-Descent was proposed as an effective solution for the graph construction problem.
Unsupervised Domain Adaptation for Image Classification via Structure-Conditioned Adversarial Learning
Unsupervised domain adaptation (UDA) typically carries out knowledge transfer from a label-rich source domain to an unlabeled target domain by adversarial learning.
RecBole: Towards a Unified, Comprehensive and Efficient Framework for Recommendation Algorithms
In this library, we implement 73 recommendation models on 28 benchmark datasets, covering the categories of general recommendation, sequential recommendation, context-aware recommendation and knowledge-based recommendation.
Lyapunov-guided Deep Reinforcement Learning for Stable Online Computation Offloading in Mobile-Edge Computing Networks
In particular, we aim to design an online computation offloading algorithm to maximize the network data processing capability subject to the long-term data queue stability and average power constraints.
Edge-computing
Networking and Internet Architecture
Leveraging Historical Interaction Data for Improving Conversational Recommender System
Most of the existing CRS methods focus on learning effective preference representations for users from conversation data alone.
S^3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization
To tackle this problem, we propose the model S^3-Rec, which stands for Self-Supervised learning for Sequential Recommendation, based on the self-attentive neural architecture.
Memory Efficient Class-Incremental Learning for Image Classification
To cope with the forgetting problem, many CIL methods transfer the knowledge of old classes by preserving some exemplar samples into the size-constrained memory buffer.
What and Where: Learn to Plug Adapters via NAS for Multi-Domain Learning
As an important and challenging problem, multi-domain learning (MDL) typically seeks for a set of effective lightweight domain-specific adapter modules plugged into a common domain-agnostic network.
Tackling Morpion Solitaire with AlphaZero-likeRanked Reward Reinforcement Learning
A later algorithm, Nested Rollout Policy Adaptation, was able to find a new record of 82 steps, albeit with large computational resources.
Sequential Recommendation with Self-Attentive Multi-Adversarial Network
Recently, deep learning has made significant progress in the task of sequential recommendation.
Warm-Start AlphaZero Self-Play Search Enhancements
Recently, AlphaZero has achieved landmark results in deep reinforcement learning, by providing a single self-play architecture that learned three different games at super human level.
Iterative Context-Aware Graph Inference for Visual Dialog
Visual dialog is a challenging task that requires the comprehension of the semantic dependencies among implicit visual and textual contexts.
Ranked #12 on
Visual Dialog
on VisDial v0.9 val
Analysis of Hyper-Parameters for Small Games: Iterations or Epochs in Self-Play?
A secondary result of our experiments concerns the choice of optimization goals, for which we also provide recommendations.
A Group Norm Regularized Factorization Model for Subspace Segmentation
Subspace segmentation assumes that data comes from the union of different subspaces and the purpose of segmentation is to partition the data into the corresponding subspace.
Residual Block-based Multi-Label Classification and Localization Network with Integral Regression for Vertebrae Labeling
Accurate identification and localization of the vertebrae in CT scans is a critical and standard preprocessing step for clinical spinal diagnosis and treatment.
Composing Knowledge Graph Embeddings via Word Embeddings
As $(\mathbf{h},\mathbf{r},\mathbf{t})$ is learned from the existing facts within a knowledge graph, these representations can not be used to detect unknown facts (if the entities or relations never occur in the knowledge graph).
On the Merge of k-NN Graph
Unfortunately, a closely related issue of how to merge two existing k-NN graphs has been overlooked.
Neural Machine Reading Comprehension: Methods and Trends
Machine reading comprehension (MRC), which requires a machine to answer questions based on a given context, has attracted increasing attention with the incorporation of various deep-learning techniques over the past few years.
Quantifying consensus of rankings based on q-support patterns
Existing studies are insufficient in assessing the overall consensus of a ranking set.
Hyper-Parameter Sweep on AlphaZero General
Therefore, in this paper, we choose 12 parameters in AlphaZero and evaluate how these parameters contribute to training.
Democratisation of Usable Machine Learning in Computer Vision
Many industries are now investing heavily in data science and automation to replace manual tasks and/or to help with decision making, especially in the realm of leveraging computer vision to automate many monitoring, inspection, and surveillance tasks.
Assessing the Potential of Classical Q-learning in General Game Playing
For small games, simple classical table-based Q-learning might still be the algorithm of choice.
Most Probable Evolution Trajectories in a Genetic Regulatory System Excited by Stable Lévy Noise
We especially examine those most probable trajectories from low concentration state to high concentration state (i. e., the likely transcription regime) for certain parameters, in order to gain insights into the transcription processes and the tipping time for the transcription likely to occur.
A Study of Deep Feature Fusion based Methods for Classifying Multi-lead ECG
An automatic classification method has been studied to effectively detect and recognize Electrocardiogram (ECG).
Approximation by filter functions
In this exploratory article, we draw attention to the common formal ground among various estimators such as the belief functions of evidence theory and their relatives, approximation quality of rough set theory, and contextual probability.
Minimum Margin Loss for Deep Face Recognition
Face recognition has achieved great progress owing to the fast development of the deep neural network in the past a few years.
Approximate k-NN Graph Construction: a Generic Online Approach
On the one hand, the approximate k-nearest neighbor graph construction is treated as a search task.
Monte Carlo Q-learning for General Game Playing
GGP problems can be solved by reinforcement learning.
Aspect-level Sentiment Classification with HEAT (HiErarchical ATtention) Network
However, the prior work only attends to the sentiment information and ignores the aspect-related information in the text, which may cause mismatching between the sentiment words and the aspects when an unrelated sentiment word is semantically meaningful for the given aspect.
FuRongWang at SemEval-2017 Task 3: Deep Neural Networks for Selecting Relevant Answers in Community Question Answering
We describes deep neural networks frameworks in this paper to address the community question answering (cQA) ranking task (SemEval-2017 task 3).
Prediction of Sea Surface Temperature using Long Short-Term Memory
We formulate the SST prediction problem as a time series regression problem.
Concordance and the Smallest Covering Set of Preference Orderings
Preference orderings are orderings of a set of items according to the preferences (of judges).
A machine learning method for the large-scale evaluation of urban visual environment
Given the size of modern cities in the urbanising age, it is beyond the perceptual capacity of most people to develop a good knowledge about the beauty and ugliness of the city at every street corner.
BIG-bench Machine Learning
Cultural Vocal Bursts Intensity Prediction
Information-theoretic Interestingness Measures for Cross-Ontology Data Mining
Development of efficient data mining methods and metrics to mine and assess the quality of the mined relationships has not kept pace with the growth of annotation data.
