Cheng Yi
YOU?
Author Swipe
View article: RAR$^2$: Retrieval-Augmented Medical Reasoning via Thought-Driven Retrieval
RAR$^2$: Retrieval-Augmented Medical Reasoning via Thought-Driven Retrieval Open
Large Language Models (LLMs) have shown promising performance on diverse medical benchmarks, highlighting their potential in supporting real-world clinical tasks. Retrieval-Augmented Generation (RAG) has emerged as a key approach for mitig…
View article: Efficient Hg(Ii) Removal Using Recyclable Poly(Thioctic Acid)/Sh-Uio-66 Functionalized Polyacrylonitrile Fiber: Multifunctional Binding Strategy
Efficient Hg(Ii) Removal Using Recyclable Poly(Thioctic Acid)/Sh-Uio-66 Functionalized Polyacrylonitrile Fiber: Multifunctional Binding Strategy Open
View article: Significantly Enhanced Hydrogen Sensing in Rare-Earth Doped Indium Oxide Nanofibers Via Metal Orbital Hybridization
Significantly Enhanced Hydrogen Sensing in Rare-Earth Doped Indium Oxide Nanofibers Via Metal Orbital Hybridization Open
View article: Fl-Sdgin: A Federated Graph Learning Approach for Schizophrenia Diagnosis Integrating Static and Dynamic Brain Functional Networks
Fl-Sdgin: A Federated Graph Learning Approach for Schizophrenia Diagnosis Integrating Static and Dynamic Brain Functional Networks Open
View article: Mechanistic Insight into Humidity Resistance Enhancement in Metal Oxide Semiconductor Hydrogen Sensors Via Crystalline Ceria Decoration
Mechanistic Insight into Humidity Resistance Enhancement in Metal Oxide Semiconductor Hydrogen Sensors Via Crystalline Ceria Decoration Open
View article: RAR2: Retrieval-Augmented Medical Reasoning via Thought-Driven Retrieval
RAR2: Retrieval-Augmented Medical Reasoning via Thought-Driven Retrieval Open
View article: Double-Threshold Spiking Reinforcement Learning for Computation-Efficient Robotic Arm Furniture Assembly
Double-Threshold Spiking Reinforcement Learning for Computation-Efficient Robotic Arm Furniture Assembly Open
View article: Global Prevalence of Overweight and Obesity in Children and Adolescents
Global Prevalence of Overweight and Obesity in Children and Adolescents Open
Importance Overweight and obesity in childhood and adolescence is a global health issue associated with adverse outcomes throughout the life course. Objective To estimate worldwide prevalence of overweight and obesity in children and adole…
View article: Deep Learning Based Framework for Productivity Prediction and Optimization of Muti-Stage Horizontal Shale Gas Well
Deep Learning Based Framework for Productivity Prediction and Optimization of Muti-Stage Horizontal Shale Gas Well Open
View article: Partial Nitriding in Bimetallic Catalyst for High-Efficiency Polysulfide Conversion in Lithium-Sulfur Batteries
Partial Nitriding in Bimetallic Catalyst for High-Efficiency Polysulfide Conversion in Lithium-Sulfur Batteries Open
View article: AI-Powered Waste Classification Using Convolutional Neural Networks (CNNs)
AI-Powered Waste Classification Using Convolutional Neural Networks (CNNs) Open
View article: Accurate diagnosis of colorectal cancer based on histopathology images using artificial intelligence
Accurate diagnosis of colorectal cancer based on histopathology images using artificial intelligence Open
View article: Fusing Wav2vec2.0 and BERT into End-to-end Model for Low-resource Speech Recognition
Fusing Wav2vec2.0 and BERT into End-to-end Model for Low-resource Speech Recognition Open
Self-supervised acoustic pre-training has achieved impressive results on low-resource speech recognition tasks. It indicates that the pretrain-and-finetune paradigm is a promising direction. In this work, we propose an end-to-end model for…
View article: Applying Wav2vec2.0 to Speech Recognition in Various Low-resource Languages
Applying Wav2vec2.0 to Speech Recognition in Various Low-resource Languages Open
There are several domains that own corresponding widely used feature extractors, such as ResNet, BERT, and GPT-x. These models are usually pre-trained on large amounts of unlabeled data by self-supervision and can be effectively applied to…
View article: A Comparison of Label-Synchronous and Frame-Synchronous End-to-End Models for Speech Recognition
A Comparison of Label-Synchronous and Frame-Synchronous End-to-End Models for Speech Recognition Open
End-to-end models are gaining wider attention in the field of automatic speech recognition (ASR). One of their advantages is the simplicity of building that directly recognizes the speech frame sequence into the text label sequence by neur…
View article: WHAT’S OLD IS NEW: USING ARTIFICIAL INTELLIGENCE TO ACCELERATE DISCOVERY OF NEW TREATMENTS
WHAT’S OLD IS NEW: USING ARTIFICIAL INTELLIGENCE TO ACCELERATE DISCOVERY OF NEW TREATMENTS Open
Given the high cost of drug development and low success rates, repurposing drugs already proven safe provides a promising avenue for identifying effective therapies with additional indications. The IBM Watson artificial intelligence system…
View article: Dual shear wave induced laser speckle contrast signal and the improvement in shear wave speed measurement
Dual shear wave induced laser speckle contrast signal and the improvement in shear wave speed measurement Open
Shear wave speed is quantitatively related to tissue viscoelasticity. Previously we reported shear wave tracking at centimetre depths in a turbid optical medium using laser speckle contrast detection. Shear wave progression modulates displ…
View article: Quantifying Activation of Perfluorocarbon-Based Phase-Change Contrast Agents Using Simultaneous Acoustic and Optical Observation
Quantifying Activation of Perfluorocarbon-Based Phase-Change Contrast Agents Using Simultaneous Acoustic and Optical Observation Open