Search Results for author:
Found 44 papers, 8 papers with code
An Evolved Universal Transformer Memory
Prior methods propose to offset the escalating costs of modern foundation models by dropping specific parts of their contexts with hand-designed rules, while attempting to preserve their original performance.
IntrinsicVoice: Empowering LLMs with Intrinsic Real-time Voice Interaction Abilities
Current methods of building LLMs with voice interaction capabilities rely heavily on explicit text autoregressive generation before or during speech response generation to maintain content quality, which unfortunately brings computational overhead and increases latency in multi-turn interactions.
Rapid Parameter Estimation for Extreme Mass Ratio Inspirals Using Machine Learning
Extreme-mass-ratio inspiral (EMRI) signals pose significant challenges in gravitational wave (GW) astronomy owing to their low-frequency nature and highly complex waveforms, which occupy a high-dimensional parameter space with numerous variables.
Enhancing Travel Choice Modeling with Large Language Models: A Prompt-Learning Approach
Travel choice analysis is crucial for understanding individual travel behavior to develop appropriate transport policies and recommendation systems in Intelligent Transportation Systems (ITS).
Release of Pre-Trained Models for the Japanese Language
AI democratization aims to create a world in which the average person can utilize AI techniques.
VmambaIR: Visual State Space Model for Image Restoration
To address these challenges, we propose VmambaIR, which introduces State Space Models (SSMs) with linear complexity into comprehensive image restoration tasks.
Large-Language-Model Empowered Dose Volume Histogram Prediction for Intensity Modulated Radiotherapy
A novel Dose Graph Neural Network (DoseGNN) model is developed for predicting DVHs from the structured graph.
Highly Accurate Disease Diagnosis and Highly Reproducible Biomarker Identification with PathFormer
However, we found two major limitations of existing GNNs in omics data analysis, i. e., limited-prediction (diagnosis) accuracy and limited-reproducible biomarker identification capacity across multiple datasets.
DoseGNN: Improving the Performance of Deep Learning Models in Adaptive Dose-Volume Histogram Prediction through Graph Neural Networks
Dose-Volume Histogram (DVH) prediction is fundamental in radiation therapy that facilitate treatment planning, dose evaluation, plan comparison and etc.
Enhancing Personality Recognition in Dialogue by Data Augmentation and Heterogeneous Conversational Graph Networks
Personality recognition is useful for enhancing robots' ability to tailor user-adaptive responses, thus fostering rich human-robot interactions.
Integrating Pre-Trained Speech and Language Models for End-to-End Speech Recognition
Advances in machine learning have made it possible to perform various text and speech processing tasks, such as automatic speech recognition (ASR), in an end-to-end (E2E) manner.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
SchurVINS: Schur Complement-Based Lightweight Visual Inertial Navigation System
To this end, we propose a novel filter-based VINS framework named SchurVINS, which could guarantee both high accuracy by building a complete residual model and low computational complexity with Schur complement.
Which Matters Most in Making Fund Investment Decisions? A Multi-granularity Graph Disentangled Learning Framework
In this paper, we highlight that both conformity and risk preference matter in making fund investment decisions beyond personal interest and seek to jointly characterize these aspects in a disentangled manner.
FinA: Fairness of Adverse Effects in Decision-Making of Human-Cyber-Physical-System
Ensuring fairness in decision-making systems within Human-Cyber-Physical-Systems (HCPS) is a pressing concern, particularly when diverse individuals, each with varying behaviors and expectations, coexist within the same application space, influenced by a shared set of control actions in the system.
Compact Binary Systems Waveform Generation with Generative Pre-trained Transformer
Space-based gravitational wave (GW) detection is one of the most anticipated GW detection projects in the next decade, which promises to detect abundant compact binary systems.
Rethinking the Power of Graph Canonization in Graph Representation Learning with Stability
We theoretically reveal the trade-off of expressivity and stability in graph-canonization-enhanced GNNs.
Dilated convolutional neural network for detecting extreme-mass-ratio inspirals
The detection of Extreme Mass Ratio Inspirals (EMRIs) is intricate due to their complex waveforms, extended duration, and low signal-to-noise ratio (SNR), making them more challenging to be identified compared to compact binary coalescences.
FAIRO: Fairness-aware Adaptation in Sequential-Decision Making for Human-in-the-Loop Systems
Furthermore, we recognize that fairness-aware policies can sometimes conflict with the application's utility.
Reinforcement Federated Learning Method Based on Adaptive OPTICS Clustering
The algorithm combines OPTICS clustering and adaptive learning technology, and can effective-ly deal with the problem of non-independent and identically distributed data across different user terminals.
Focused Prefix Tuning for Controllable Text Generation
In a controllable text generation dataset, there exist unannotated attributes that could provide irrelevant learning signals to models that use it for training and thus degrade their performance.
Space-based gravitational wave signal detection and extraction with deep neural network
Space-based gravitational wave (GW) detectors will be able to observe signals from sources that are otherwise nearly impossible from current ground-based detection.
Aspect-Based Sentiment Analysis using Local Context Focus Mechanism with DeBERTa
Aspect-Based Sentiment Analysis (ABSA) is a fine-grained task in the field of sentiment analysis, which aims to predict the polarity of aspects.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+4
End-to-End Text-to-Speech Based on Latent Representation of Speaking Styles Using Spontaneous Dialogue
A style encoder that extracts a latent speaking style representation from speech is trained jointly with TTS.
Space4HGNN: A Novel, Modularized and Reproducible Platform to Evaluate Heterogeneous Graph Neural Network
Heterogeneous Graph Neural Network (HGNN) has been successfully employed in various tasks, but we cannot accurately know the importance of different design dimensions of HGNNs due to diverse architectures and applied scenarios.
Ensuring DNN Solution Feasibility for Optimization Problems with Convex Constraints and Its Application to DC Optimal Power Flow Problems
We systematically calibrate inequality constraints used in DNN training, thereby anticipating prediction errors and ensuring the resulting solutions remain feasible.
Weaving Attention U-net: A Novel Hybrid CNN and Attention-based Method for Organs-at-risk Segmentation in Head and Neck CT Images
Our results of the new Weaving Attention U-net demonstrate superior or similar performance on the segmentation of head and neck CT images.
CORSAIR: Convolutional Object Retrieval and Symmetry-AIded Registration
This paper considers online object-level mapping using partial point-cloud observations obtained online in an unknown environment.
Topic-relevant Response Generation using Optimal Transport for an Open-domain Dialog System
The semantic constraint, which encourages a response to be semantically related to its context by regularizing the decoding objective function with semantic distance, is proposed.
Semi-supervised Semantic Segmentation of Prostate and Organs-at-Risk on 3D Pelvic CT Images
We developed a novel semi-supervised adversarial deep learning approach for 3D pelvic CT image semantic segmentation.
Multi-Referenced Training for Dialogue Response Generation
In this work, we first analyze the training objective of dialogue models from the view of Kullback-Leibler divergence (KLD) and show that the gap between the real world probability distribution and the single-referenced data's probability distribution prevents the model from learning the one-to-many relations efficiently.
ARPM-net: A novel CNN-based adversarial method with Markov Random Field enhancement for prostate and organs at risk segmentation in pelvic CT images
A segmentation network and a discriminator network were trained jointly, and only the segmentation network was used for prediction.
DeepOPF: A Feasibility-Optimized Deep Neural Network Approach for AC Optimal Power Flow Problems
High percentage penetrations of renewable energy generations introduce significant uncertainty into power systems.
End-to-end speech-to-dialog-act recognition
In the proposed model, the dialog act recognition network is conjunct with an acoustic-to-word ASR model at its latent layer before the softmax layer, which provides a distributed representation of word-level ASR decoding information.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
An adaptive neuro-fuzzy model for attitude estimation and 2 control a 3 DOF system
To evaluate the performance of the AN-FIS controller in closed-loop simulation, an ANFIS observer is used to estimate the attitude and angular velocities of the satellite using magnetometer, sun sensor and data gyro data.
Designing Precise and Robust Dialogue Response Evaluators
Automatic dialogue response evaluator has been proposed as an alternative to automated metrics and human evaluation.
DeepOPF: A Deep Neural Network Approach for Security-Constrained DC Optimal Power Flow
We then directly reconstruct the phase angles from the generations and loads by using the power flow equations.
Efficient and Robust Equilibrium Strategies of Utilities in Day-ahead Market with Load Uncertainty
We consider the scenario where $N$ utilities strategically bid for electricity in the day-ahead market and balance the mismatch between the committed supply and actual demand in the real-time market, with uncertainty in demand and local renewable generation in consideration.
Effective Incorporation of Speaker Information in Utterance Encoding in Dialog
In dialog studies, we often encode a dialog using a hierarchical encoder where each utterance is converted into an utterance vector, and then a sequence of utterance vectors is converted into a dialog vector.
Content Word-based Sentence Decoding and Evaluating for Open-domain Neural Response Generation
Various encoder-decoder models have been applied to response generation in open-domain dialogs, but a majority of conventional models directly learn a mapping from lexical input to lexical output without explicitly modeling intermediate representations.
DeepOPF: Deep Neural Network for DC Optimal Power Flow
DeepOPF is inspired by the observation that solving DC-OPF for a given power network is equivalent to characterizing a high-dimensional mapping between the load inputs and the dispatch and transmission decisions.
Systems and Control
Unsupervised Degradation Learning for Single Image Super-Resolution
Specifically, we propose a degradation network to model the real-world degradation process from HR to LR via generative adversarial networks, and these generated realistic LR images paired with real-world HR images are exploited for training the SR reconstruction network, forming the first cycle.
A Unified Neural Architecture for Joint Dialog Act Segmentation and Recognition in Spoken Dialog System
We propose a unified architecture based on neural networks, which consists of a sequence tagger for segmentation and a classifier for recognition.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Joint Learning of Dialog Act Segmentation and Recognition in Spoken Dialog Using Neural Networks
Dialog act segmentation and recognition are basic natural language understanding tasks in spoken dialog systems.
Automatic Speech Recognition (ASR)
Natural Language Understanding
+2
