Mingxi Cheng
YOU?
Author Swipe
View article: ERMoE: Eigen-Reparameterized Mixture-of-Experts for Stable Routing and Interpretable Specialization
ERMoE: Eigen-Reparameterized Mixture-of-Experts for Stable Routing and Interpretable Specialization Open
Mixture-of-Experts (MoE) architectures expand model capacity by sparsely activating experts but face two core challenges: misalignment between router logits and each expert's internal structure leads to unstable routing and expert underuti…
View article: Eigen Neural Network: Unlocking Generalizable Vision with Eigenbasis
Eigen Neural Network: Unlocking Generalizable Vision with Eigenbasis Open
The remarkable success of Deep Neural Networks(DNN) is driven by gradient-based optimization, yet this process is often undermined by its tendency to produce disordered weight structures, which harms feature clarity and degrades learning d…
View article: Machine learning‐based identification of general transcriptional predictors for plant disease
Machine learning‐based identification of general transcriptional predictors for plant disease Open
Summary This study investigated the generalizability of Arabidopsis thaliana immune responses across diverse pathogens, including Botrytis cinerea , Sclerotinia sclerotiorum , and Pseudomonas syringae , using a data‐driven, machine learnin…
View article: Neuro-Inspired Information-Theoretic Hierarchical Perception for Multimodal Learning
Neuro-Inspired Information-Theoretic Hierarchical Perception for Multimodal Learning Open
Integrating and processing information from various sources or modalities are critical for obtaining a comprehensive and accurate perception of the real world in autonomous systems and cyber-physical systems. Drawing inspiration from neuro…
View article: Unlocking Deep Learning: A BP-Free Approach for Parallel Block-Wise Training of Neural Networks
Unlocking Deep Learning: A BP-Free Approach for Parallel Block-Wise Training of Neural Networks Open
Backpropagation (BP) has been a successful optimization technique for deep learning models. However, its limitations, such as backward- and update-locking, and its biological implausibility, hinder the concurrent updating of layers and do …
View article: Discovering Malicious Signatures in Software from Structural Interactions
Discovering Malicious Signatures in Software from Structural Interactions Open
Malware represents a significant security concern in today's digital landscape, as it can destroy or disable operating systems, steal sensitive user information, and occupy valuable disk space. However, current malware detection methods, s…
View article: Leader-Follower Neural Networks with Local Error Signals Inspired by Complex Collectives
Leader-Follower Neural Networks with Local Error Signals Inspired by Complex Collectives Open
The collective behavior of a network with heterogeneous, resource-limited information processing units (e.g., group of fish, flock of birds, or network of neurons) demonstrates high self-organization and complexity. These emergent properti…
View article: Neuro-Inspired Hierarchical Multimodal Learning
Neuro-Inspired Hierarchical Multimodal Learning Open
Integrating and processing information from various sources or modalities are critical for obtaining a comprehensive and accurate perception of the real world. Drawing inspiration from neuroscience, we develop the Information-Theoretic Hie…
View article: Machine learning general transcriptional predictors of plant disease
Machine learning general transcriptional predictors of plant disease Open
Plants utilize an innate immune system to defend against all classes of microbial invaders. While we understand specific genetic determinants of host-pathogen interactions, it remains less clear how generalized the immune response is to di…
View article: Fractional Dynamics Foster Deep Learning of COPD Stage Prediction (Adv. Sci. 12/2023)
Fractional Dynamics Foster Deep Learning of COPD Stage Prediction (Adv. Sci. 12/2023) Open
Deep Learning Analyzing physiological signals with fractional dynamics reduces the learning complexity for automated diagnosis with deep learning. In article number 2203485, Mihai Udrescu, Paul Bogdan, and co‐workers show that fractional‐o…
View article: Fractional dynamics foster deep learning of COPD stage prediction
Fractional dynamics foster deep learning of COPD stage prediction Open
Chronic obstructive pulmonary disease (COPD) is one of the leading causes of death worldwide. Current COPD diagnosis (i.e., spirometry) could be unreliable because the test depends on an adequate effort from the tester and testee. Moreover…
View article: Fractional Dynamics Foster Deep Learning of COPD Stage Prediction
Fractional Dynamics Foster Deep Learning of COPD Stage Prediction Open
Chronic obstructive pulmonary disease (COPD) is one of the leading causes of death worldwide. Current COPD diagnosis (i.e., spirometry) could be unreliable because the test depends on an adequate effort from the tester and testee. Moreover…
View article: Anatomically interpretable deep learning of brain age captures domain-specific cognitive impairment
Anatomically interpretable deep learning of brain age captures domain-specific cognitive impairment Open
The gap between chronological age (CA) and biological brain age, as estimated from magnetic resonance images (MRIs), reflects how individual patterns of neuroanatomic aging deviate from their typical trajectories. MRI-derived brain age (BA…
View article: Generation-Based Data Augmentation Pipeline for Real-Time Automatic Gesture Recognition
Generation-Based Data Augmentation Pipeline for Real-Time Automatic Gesture Recognition Open
View article: ClipCrop: Conditioned Cropping Driven by Vision-Language Model
ClipCrop: Conditioned Cropping Driven by Vision-Language Model Open
Image cropping has progressed tremendously under the data-driven paradigm. However, current approaches do not account for the intentions of the user, which is an issue especially when the composition of the input image is complex. Moreover…
View article: Polyphenic risk score shows robust predictive ability for long-term future suicidality
Polyphenic risk score shows robust predictive ability for long-term future suicidality Open
View article: Polyphenic Risk Score Shows Robust Predictive Ability For Long-Term Future Suicidality
Polyphenic Risk Score Shows Robust Predictive Ability For Long-Term Future Suicidality Open
Suicides are preventable tragedies, if risk factors are tracked and mitigated. We had previously developed a new quantitative suicidality risk assessment instrument (Convergent Functional Information for Suicidality, CFI-S), which is in es…
View article: Trust-aware Control for Intelligent Transportation Systems
Trust-aware Control for Intelligent Transportation Systems Open
Many intelligent transportation systems are multi-agent systems, i.e., both the traffic participants and the subsystems within the transportation infrastructure can be modeled as interacting agents. The use of AI-based methods to achieve c…
View article: A COVID-19 Rumor Dataset
A COVID-19 Rumor Dataset Open
DATA REPORT article Front. Psychol., 31 May 2021Sec. Personality and Social Psychology Volume 12 - 2021 | https://doi.org/10.3389/fpsyg.2021.644801
View article: Deciphering the laws of social network-transcendent COVID-19 misinformation dynamics and implications for combating misinformation phenomena
Deciphering the laws of social network-transcendent COVID-19 misinformation dynamics and implications for combating misinformation phenomena Open
View article: From rumor to genetic mutation detection with explanations: a GAN approach
From rumor to genetic mutation detection with explanations: a GAN approach Open
View article: VRoC: Variational Autoencoder-aided Multi-task Rumor Classifier Based on Text
VRoC: Variational Autoencoder-aided Multi-task Rumor Classifier Based on Text Open
Social media became popular and percolated almost all aspects of our daily lives. While online posting proves very convenient for individual users, it also fosters fast-spreading of various rumors. The rapid and wide percolation of rumors …
View article: There Is Hope After All: Quantifying Opinion and Trustworthiness in Neural Networks
There Is Hope After All: Quantifying Opinion and Trustworthiness in Neural Networks Open
Artificial Intelligence (AI) plays a fundamental role in the modern world, especially when used as an autonomous decision maker. One common concern nowadays is "how trustworthy the AIs are." Human operators follow a strict educational curr…
View article: VRoC: Variational Autoencoder-aided Multi-task Rumor Classifier Based on Text
VRoC: Variational Autoencoder-aided Multi-task Rumor Classifier Based on Text Open
Social media became popular and percolated almost all aspects of our daily lives. While online posting proves very convenient for individual users, it also fosters fast-spreading of various rumors. The rapid and wide percolation of rumors …
View article: H2O-Cloud: A Resource and Quality of Service-Aware Task Scheduling Framework for Warehouse-Scale Data Centers
H2O-Cloud: A Resource and Quality of Service-Aware Task Scheduling Framework for Warehouse-Scale Data Centers Open
View article: H2O-Cloud: A Resource and Quality of Service-Aware Task Scheduling Framework for Warehouse-Scale Data Centers -- A Hierarchical Hybrid DRL (Deep Reinforcement Learning) based Approach
H2O-Cloud: A Resource and Quality of Service-Aware Task Scheduling Framework for Warehouse-Scale Data Centers -- A Hierarchical Hybrid DRL (Deep Reinforcement Learning) based Approach Open
Cloud computing has attracted both end-users and Cloud Service Providers (CSPs) in recent years. Improving resource utilization rate (RUtR), such as CPU and memory usages on servers, while maintaining Quality-of-Service (QoS) is one key ch…
View article: A WiFi-based Positioning Parking Guidance System
A WiFi-based Positioning Parking Guidance System Open
With the development of economic and the growth of the city, the number of vehicles has also increased rapidly, parking problems continue testing the ability of the city's public services. To solve this problem, we hope to find a more accu…