Search Results for author:
Found 18 papers, 3 papers with code
WAE_RN: Integrating Wasserstein Autoencoder and Relational Network for Text Sequence
In spite of the success of pre-trained language model in many NLP tasks, the learned text representation only contains the correlation among the words in the sentence itself and ignores the implicit relationship between arbitrary tokens in the sequence.
Enhancing Reset Control Phase with Lead Shaping Filters: Applications to Precision Motion Systems
{The design achieves either an increased phase margin while maintaining gain properties or improved gain without sacrificing phase margin, compared to reset control without the shaping filter.}
Higher-Order Sinusoidal Input Describing Functions for Open-Loop and Closed-Loop Reset Control with Application to Mechatronics Systems
Finally, the utility of the proposed methods is demonstrated through case studies that analyze and compare the performance of three controllers: a PID controller, a reset controller, and a shaped reset controller on a precision motion stage.
Using Large Language Models for Parametric Shape Optimization
Recent advanced large language models (LLMs) have showcased their emergent capability of in-context learning, facilitating intelligent decision-making through natural language prompts without retraining.
Enhancing the Reliability of Closed-Loop Describing Function Analysis for Reset Control Applied to Precision Motion Systems
To address this, a shaped reset control strategy is proposed, which incorporates a shaping filter to tune reset actions and reduce high-order harmonics.
Unified Embedding Alignment for Open-Vocabulary Video Instance Segmentation
We discover that the domain gap between the VLM features (e. g., CLIP) and the instance queries and the underutilization of temporal consistency are two central causes.
The Analysis and the Performance of the Parallel-Partial Reset Control System
We develop frequency response analysis methods for both the open-loop and closed-loop parallel-partial reset systems.
Fine-Grained Urban Flow Inference with Multi-scale Representation Learning
In order to effectively learn multi-scale information across time and space, we propose an effective fine-grained urban flow inference model called UrbanMSR, which uses self-supervised contrastive learning to obtain dynamic multi-scale representations of neighborhood-level and city-level geographic information, and fuses multi-scale representations to improve fine-grained accuracy.
RedCore: Relative Advantage Aware Cross-modal Representation Learning for Missing Modalities with Imbalanced Missing Rates
Multimodal learning is susceptible to modality missing, which poses a major obstacle for its practical applications and, thus, invigorates increasing research interest.
Rapid online solution of inverse heat transfer problem by ANN-based extended Kalman smoothing algorithm
Digital twin is a modern technology for many advanced applications.
A Reinforcement Learning Framework for Online Speaker Diarization
Our approach considers speaker diarization as a fully online learning problem of the speaker recognition task, where the agent receives no pretraining from any training set before deployment, and learns to detect speaker identity on the fly through reward feedbacks.
RTN: Reinforced Transformer Network for Coronary CT Angiography Vessel-level Image Quality Assessment
Therefore, we propose a Progressive Reinforcement learning based Instance Discarding module (termed as PRID) to progressively remove quality-irrelevant/negative instances for CCTA VIQA.
Steady-state nonlinearity of open-loop reset systems
In this paper, we introduce a new representation for open-loop reset systems.
Frequency Response Analysis for Reset Control Systems: Application to Predict Precision of Motion Systems
These methods decompose the frequency responses of reset systems into base-linear and nonlinear components.
Geodesic Paths for Image Segmentation with Implicit Region-based Homogeneity Enhancement
Minimal paths are regarded as a powerful and efficient tool for boundary detection and image segmentation due to its global optimality and the well-established numerical solutions such as fast marching method.
Speaker Diarization as a Fully Online Learning Problem in MiniVox
We proposed a novel machine learning framework to conduct real-time multi-speaker diarization and recognition without prior registration and pretraining in a fully online learning setting.
Hierarchical Optimization Time Integration for CFL-rate MPM Stepping
We propose Hierarchical Optimization Time Integration (HOT) for efficient implicit time-stepping of the Material Point Method (MPM) irrespective of simulated materials and conditions.
Graphics
Tree Recognition APP of Mount Tai Based on CNN
Mount Tai has abundant sunshine, abundant rainfall and favorable climatic conditions, forming dense vegetation with various kinds of trees.
