5 citations · 14 across the 12 of their papers we have counts for
12 papers
EMoE: Eigenbasis-Guided Routing for Mixture-of-Experts
Anzhe Cheng, Shukai Duan, Shixuan Li +5
The relentless scaling of deep learning models has led to unsustainable computational demands, positioning Mixture-of-Experts (MoE) architectures as a promising path towards greate…
ERMoE: Eigen-Reparameterized Mixture-of-Experts for Stable Routing and Interpretable Specialization
Anzhe Cheng, Shukai Duan, Shixuan Li +8
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 inter…
Eigen Neural Network: Unlocking Generalizable Vision with Eigenbasis
Anzhe Cheng, Chenzhong Yin, Mingxi Cheng +3
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 stru…
Neuro-Inspired Information-Theoretic Hierarchical Perception for Multimodal Learning
Xiongye Xiao, Gengshuo Liu, Gaurav Gupta +6
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…
Unlocking Deep Learning: A BP-Free Approach for Parallel Block-Wise Training of Neural Networks
Anzhe Cheng, Zhenkun Wang, Chenzhong Yin +5
Backpropagation (BP) has been a successful optimization technique for deep learning models. However, its limitations, such as backward- and update-locking, and its biological impla…
Discovering Malicious Signatures in Software from Structural Interactions
Chenzhong Yin, Hantang Zhang, Mingxi Cheng +4
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 valuabl…
Leader-Follower Neural Networks with Local Error Signals Inspired by Complex Collectives
Chenzhong Yin, Mingxi Cheng, Xiongye Xiao +4
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 hig…
Neuro-Inspired Hierarchical Multimodal Learning
Xiongye Xiao, Gengshuo Liu, Gaurav Gupta +6
Integrating and processing information from various sources or modalities are critical for obtaining a comprehensive and accurate perception of the real world. Drawing inspiration…
Fractional dynamics foster deep learning of COPD stage prediction
Chenzhong Yin, Mihai Udrescu, Gaurav Gupta +6
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…
Trust-aware Control for Intelligent Transportation Systems
Mingxi Cheng, Junyao Zhang, Shahin Nazarian +2
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 i…
VRoC: Variational Autoencoder-aided Multi-task Rumor Classifier Based on Text
Mingxi Cheng, Shahin Nazarian, Paul Bogdan
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 o…
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
Mingxi Cheng, Ji Li, Paul Bogdan +1
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 server…