Song Guo
YOU?
Author Swipe
View article: Prognostic Modeling of Thermal Runaway Risk in Lithium-Ion Power Batteries Based on Multivariate Degradation Data
Prognostic Modeling of Thermal Runaway Risk in Lithium-Ion Power Batteries Based on Multivariate Degradation Data Open
Lithium-ion batteries serve as critical energy storage units for electric vehicles, unmanned aerial vehicles, and other emerging transportation systems. Numerous real-world incidents have demonstrated that thermal runaway (TR) remains a pr…
View article: Adaptive Feature Regulation and Directional Consistency Optimization for Lightweight ORB-SLAM3 in Resource-Constrained Indoor Environments
Adaptive Feature Regulation and Directional Consistency Optimization for Lightweight ORB-SLAM3 in Resource-Constrained Indoor Environments Open
Visual Simultaneous Localization and Mapping (VSLAM) is a foundational technology widely applied in robotics, autonomous driving, and augmented reality, enabling devices to navigate and construct environmental models using visual sensors. …
View article: Climate science data can be compressed efficiently by dual-stage extreme compression with a variational auto-encoder transformer
Climate science data can be compressed efficiently by dual-stage extreme compression with a variational auto-encoder transformer Open
Climate change makes accurate weather prediction and large-scale data analysis increasingly crucial, but the sheer volume of weather data strains data storage and sharing. Here we introduce Aeolus, a deep learning framework with powerful V…
View article: Learning by Neighbor-Aware Semantics, Deciding by Open-form Flows: Towards Robust Zero-Shot Skeleton Action Recognition
Learning by Neighbor-Aware Semantics, Deciding by Open-form Flows: Towards Robust Zero-Shot Skeleton Action Recognition Open
Recognizing unseen skeleton action categories remains highly challenging due to the absence of corresponding skeletal priors. Existing approaches generally follow an "align-then-classify" paradigm but face two fundamental issues, i.e., (i)…
View article: Intelligent evaluation algorithm for Taekwondo poomsae quality and posture recognition teaching system
Intelligent evaluation algorithm for Taekwondo poomsae quality and posture recognition teaching system Open
View article: D2MoE: Dual Routing and Dynamic Scheduling for Efficient On-Device MoE-based LLM Serving
D2MoE: Dual Routing and Dynamic Scheduling for Efficient On-Device MoE-based LLM Serving Open
The mixture of experts (MoE) model is a sparse variant of large language models (LLMs), designed to hold a better balance between intelligent capability and computational overhead. Despite its benefits, MoE is still too expensive to deploy…
View article: Time Series Prediction for Monitoring Peatland and Wetland Conditions Using Remoteensing Data
Time Series Prediction for Monitoring Peatland and Wetland Conditions Using Remoteensing Data Open
Monitoring peatlands and wetlands is essential for assessing environmental health and managing ecosystems, yet traditional methods of monitoring these areas often face challenges due to the complexity and scale of the task. Remote sensing …
View article: Applications of Deep Learning in ArchitecturalFacade Parsing and 3D Reconstruction
Applications of Deep Learning in ArchitecturalFacade Parsing and 3D Reconstruction Open
The rapid advancements in deep learning have significantly transformed architectural facade parsing and 3D reconstruction,enabling precise and scalable analysis of urban environments. Traditional approaches, such as rule-based methods andh…
View article: Multi-Scenario Robust Distributed Permutation Flow Shop Scheduling Based on DDQN
Multi-Scenario Robust Distributed Permutation Flow Shop Scheduling Based on DDQN Open
In order to address the Distributed Displacement Flow Shop Scheduling Problem (DPFSP) with uncertain processing times in real production environments, Plant Simulation is employed to construct a simulation model for the MSRDPFSP. The model…
View article: United Minds or Isolated Agents? Exploring Coordination of LLMs under Cognitive Load Theory
United Minds or Isolated Agents? Exploring Coordination of LLMs under Cognitive Load Theory Open
Large Language Models (LLMs) exhibit a notable performance ceiling on complex, multi-faceted tasks, as they often fail to integrate diverse information or adhere to multiple constraints. We posit that such limitation arises when the demand…
View article: Facial Expression Analysis and Its Potentials in IoT Systems: A Contemporary Survey
Facial Expression Analysis and Its Potentials in IoT Systems: A Contemporary Survey Open
Facial expressions convey human emotions and can be categorized into macro-expressions (MaEs) and micro-expressions (MiEs) based on duration and intensity. While MaEs are voluntary and easily recognized, MiEs are involuntary, rapid, and ca…
View article: FreeMesh: Boosting Mesh Generation with Coordinates Merging
FreeMesh: Boosting Mesh Generation with Coordinates Merging Open
The next-coordinate prediction paradigm has emerged as the de facto standard in current auto-regressive mesh generation methods. Despite their effectiveness, there is no efficient measurement for the various tokenizers that serialize meshe…
View article: ELK1 inhibition alleviates amyloid pathology and memory decline by promoting the SYVN1-mediated ubiquitination and degradation of PS1 in Alzheimer’s disease
ELK1 inhibition alleviates amyloid pathology and memory decline by promoting the SYVN1-mediated ubiquitination and degradation of PS1 in Alzheimer’s disease Open
ELK1 is a member of the E-twenty-six transcription factor family and is usually activated by phosphorylation at Ser383 and Ser389 by extracellular signal-regulated kinase 1/2 (ERK1/2). Dysregulation of ERK1/2 is involved in Alzheimer’s dis…
View article: BoxSeg: Quality-Aware and Peer-Assisted Learning for Box-supervised Instance Segmentation
BoxSeg: Quality-Aware and Peer-Assisted Learning for Box-supervised Instance Segmentation Open
Box-supervised instance segmentation methods aim to achieve instance segmentation with only box annotations. Recent methods have demonstrated the effectiveness of acquiring high-quality pseudo masks under the teacher-student framework. Bui…
View article: Orchestrating Joint Offloading and Scheduling for Low-Latency Edge SLAM
Orchestrating Joint Offloading and Scheduling for Low-Latency Edge SLAM Open
Visual Simultaneous Localization and Mapping (vSLAM) is a prevailing technology for many emerging robotic applications. Achieving real-time SLAM on mobile robotic systems with limited computational resources is challenging because the comp…
View article: Analysis of research status and trends on nano-agricultural application: a bibliometric study
Analysis of research status and trends on nano-agricultural application: a bibliometric study Open
Introduction The rapid global population growth and limitations of traditional agricultural practices have resulted in inadequate nutrient supply. Nano-agricultural technology presents significant potential for enhancing crop growth and re…
View article: The MoE-Empowered Edge LLMs Deployment: Architecture, Challenges, and Opportunities
The MoE-Empowered Edge LLMs Deployment: Architecture, Challenges, and Opportunities Open
The powerfulness of LLMs indicates that deploying various LLMs with different scales and architectures on end, edge, and cloud to satisfy different requirements and adaptive heterogeneous hardware is the critical way to achieve ubiquitous …
View article: KIF9 Ameliorates Neuropathology and Cognitive Dysfunction by Promoting Macroautophagy in a Mouse Model of Alzheimer's Disease
KIF9 Ameliorates Neuropathology and Cognitive Dysfunction by Promoting Macroautophagy in a Mouse Model of Alzheimer's Disease Open
Alzheimer's disease (AD) is a prevalent neurodegenerative disorder affecting the elderly. The imbalance of protein production and degradation processes leads to the accumulation of misfolded and abnormally aggregated amyloid‐beta (Aβ) in t…
View article: Comparative analysis of methods for seasonal particulate organic nitrate estimation in urban areas
Comparative analysis of methods for seasonal particulate organic nitrate estimation in urban areas Open
Accurately estimating particulate organic nitrate under high NOx and oxidizing conditions is critical. This study compared the NOx + ratio, unconstrained Positive Matrix Factorization (PMF), and Multilinear Engine-2 (ME2) methods to estima…
View article: A Function-aware graph-based layout retrieval approach for public buildings
A Function-aware graph-based layout retrieval approach for public buildings Open
View article: RORem: Training a Robust Object Remover with Human-in-the-Loop
RORem: Training a Robust Object Remover with Human-in-the-Loop Open
Despite the significant advancements, existing object removal methods struggle with incomplete removal, incorrect content synthesis and blurry synthesized regions, resulting in low success rates. Such issues are mainly caused by the lack o…
View article: Compact single-shot multispectral polarization imager through joint spectral-polarization encoding
Compact single-shot multispectral polarization imager through joint spectral-polarization encoding Open
The technique of spectral polarization imaging (SPI) is a potent detection tool in various fields due to its ability to capture multi-dimensional information. However, existing SPI systems usually face challenges associated with architectu…
View article: BrokerChain: A Blockchain Sharding Protocol by Exploiting Broker Accounts
BrokerChain: A Blockchain Sharding Protocol by Exploiting Broker Accounts Open
State-of-the-art blockchain sharding solutions such as Monoxide, can cause severely imbalanced distribution of transaction (TX) workloads across all blockchain shards due to the deployment policy of their accounts. Imbalanced TX distributi…
View article: Structure-Adaptive and Power-Aware Broadcast Scheduling for Multihop Wireless-Powered IoT Networks
Structure-Adaptive and Power-Aware Broadcast Scheduling for Multihop Wireless-Powered IoT Networks Open
Wireless Power Transfer technology, which can charge IoT devices over the air, has become a promising technology for IoT networks. In wireless-powered IoT networks, broadcasting is a fundamental networking service for disseminating message…
View article: Random Sampling for Diffusion-based Adversarial Purification
Random Sampling for Diffusion-based Adversarial Purification Open
Denoising Diffusion Probabilistic Models (DDPMs) have gained great attention in adversarial purification. Current diffusion-based works focus on designing effective condition-guided mechanisms while ignoring a fundamental problem, i.e., th…
View article: QuickDrop: Efficient Federated Unlearning via Synthetic Data Generation
QuickDrop: Efficient Federated Unlearning via Synthetic Data Generation Open
Federated Unlearning (FU) aims to delete specific training data from an ML model trained using Federated Learning (FL). However, existing FU methods suffer from inefficiencies due to the high costs associated with gradient recomputation an…
View article: Communication-Efficient Sparsely-Activated Model Training via Sequence Migration and Token Condensation
Communication-Efficient Sparsely-Activated Model Training via Sequence Migration and Token Condensation Open
Mixture-of-Experts (MoE) is an emerging technique for scaling large models with sparse activation. MoE models are typically trained in a distributed manner with an expert parallelism scheme, where experts in each MoE layer are distributed …
View article: Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition
Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition Open
Zero-shot skeleton action recognition is a non-trivial task that requires robust unseen generalization with prior knowledge from only seen classes and shared semantics. Existing methods typically build the skeleton-semantics interactions b…
View article: DeepZoning: Re-accelerate CNN Inference with Zoning Graph for Heterogeneous Edge Cluster
DeepZoning: Re-accelerate CNN Inference with Zoning Graph for Heterogeneous Edge Cluster Open
Parallelizing CNN inference on heterogeneous edge clusters with data parallelism has gained popularity as a way to meet real-time requirements without sacrificing model accuracy. However, existing algorithms struggle to find optimal parall…
View article: SFP: Spurious Feature-Targeted Pruning for Out-of-Distribution Generalization
SFP: Spurious Feature-Targeted Pruning for Out-of-Distribution Generalization Open
Recent studies reveal that even highly biased dense networks can contain an invariant substructure with superior out-of-distribution (OOD) generalization. While existing works commonly seek these substructures using global sparsity constra…