Jiaxu Wang
YOU?
Author Swipe
View article: The interplay of estrogen, gut microbiome, and bone immunity in osteoporosis
The interplay of estrogen, gut microbiome, and bone immunity in osteoporosis Open
Osteoporosis is a global health concern arising from estrogen deficiency, intestinal dysbiosis, and dysregulation of the bone immune system. The absence of estrogen after menopause created environmental changes within the gut, where the mi…
View article: Study on Electrochemical Performance and Magnesium Storage Mechanism of Na3V2(PO4)3@C Cathode in Mg(TFSI)2/DME Electrolyte
Study on Electrochemical Performance and Magnesium Storage Mechanism of Na3V2(PO4)3@C Cathode in Mg(TFSI)2/DME Electrolyte Open
Magnesium metal boasts a high theoretical volumetric specific capacity and abundant reserves. Magnesium batteries offer high safety and environmental friendliness. In recent years, magnesium-ion batteries (MIBs) with Mg or Mg alloys as ano…
View article: DEGS: Deformable Event-based 3D Gaussian Splatting from RGB and Event Stream
DEGS: Deformable Event-based 3D Gaussian Splatting from RGB and Event Stream Open
Reconstructing Dynamic 3D Gaussian Splatting (3DGS) from low-framerate RGB videos is challenging. This is because large inter-frame motions will increase the uncertainty of the solution space. For example, one pixel in the first frame migh…
View article: DPL: Depth-only Perceptive Humanoid Locomotion via Realistic Depth Synthesis and Cross-Attention Terrain Reconstruction
DPL: Depth-only Perceptive Humanoid Locomotion via Realistic Depth Synthesis and Cross-Attention Terrain Reconstruction Open
Recent advancements in legged robot perceptive locomotion have shown promising progress. However, terrain-aware humanoid locomotion remains largely constrained to two paradigms: depth image-based end-to-end learning and elevation map-based…
View article: Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition
Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition Open
Diffusion-based models for robotic control, including vision-language-action (VLA) and vision-action (VA) policies, have demonstrated significant capabilities. Yet their advancement is constrained by the high cost of acquiring large-scale …
View article: Humanoid Occupancy: Enabling A Generalized Multimodal Occupancy Perception System on Humanoid Robots
Humanoid Occupancy: Enabling A Generalized Multimodal Occupancy Perception System on Humanoid Robots Open
Humanoid robot technology is advancing rapidly, with manufacturers introducing diverse heterogeneous visual perception modules tailored to specific scenarios. Among various perception paradigms, occupancy-based representation has become wi…
View article: Learning Null Geodesics for Gravitational Lensing Rendering in General Relativity
Learning Null Geodesics for Gravitational Lensing Rendering in General Relativity Open
We present GravLensX, an innovative method for rendering black holes with gravitational lensing effects using neural networks. The methodology involves training neural networks to fit the spacetime around black holes and then employing the…
View article: Research on the Development Path of Green Buildings based on the Integrated Model of Structural Equation and System Dynamics
Research on the Development Path of Green Buildings based on the Integrated Model of Structural Equation and System Dynamics Open
Driven by China's "dual carbon" goals, the green transformation of the construction industry has become a crucial path to achieve low-carbon development. This study focuses on the development of green buildings in Shandong Province. By app…
View article: Improving Electrochemical Performance of Cobalt Hexacyanoferrate as Magnesium Ion Battery Cathode Material by Nickel Doping
Improving Electrochemical Performance of Cobalt Hexacyanoferrate as Magnesium Ion Battery Cathode Material by Nickel Doping Open
Magnesium metal has a high theoretical volume capacity and abundant reserves. Magnesium ion battery is theoretically secure and eco-friendly. In recent years, magnesium ion battery has attracted wide attention and is expected to become a c…
View article: EmbodiedVSR: Dynamic Scene Graph-Guided Chain-of-Thought Reasoning for Visual Spatial Tasks
EmbodiedVSR: Dynamic Scene Graph-Guided Chain-of-Thought Reasoning for Visual Spatial Tasks Open
While multimodal large language models (MLLMs) have made groundbreaking progress in embodied intelligence, they still face significant challenges in spatial reasoning for complex long-horizon tasks. To address this gap, we propose Embodied…
View article: HumanoidPano: Hybrid Spherical Panoramic-LiDAR Cross-Modal Perception for Humanoid Robots
HumanoidPano: Hybrid Spherical Panoramic-LiDAR Cross-Modal Perception for Humanoid Robots Open
The perceptual system design for humanoid robots poses unique challenges due to inherent structural constraints that cause severe self-occlusion and limited field-of-view (FOV). We present HumanoidPano, a novel hybrid cross-modal perceptio…
View article: Distillation-PPO: A Novel Two-Stage Reinforcement Learning Framework for Humanoid Robot Perceptive Locomotion
Distillation-PPO: A Novel Two-Stage Reinforcement Learning Framework for Humanoid Robot Perceptive Locomotion Open
In recent years, humanoid robots have garnered significant attention from both academia and industry due to their high adaptability to environments and human-like characteristics. With the rapid advancement of reinforcement learning, subst…
View article: LiPS: Large-Scale Humanoid Robot Reinforcement Learning with Parallel-Series Structures
LiPS: Large-Scale Humanoid Robot Reinforcement Learning with Parallel-Series Structures Open
In recent years, research on humanoid robots has garnered significant attention, particularly in reinforcement learning based control algorithms, which have achieved major breakthroughs. Compared to traditional model-based control algorith…
View article: Trinity: A Modular Humanoid Robot AI System
Trinity: A Modular Humanoid Robot AI System Open
In recent years, research on humanoid robots has garnered increasing attention. With breakthroughs in various types of artificial intelligence algorithms, embodied intelligence, exemplified by humanoid robots, has been highly anticipated. …
View article: Assessing the viral enrichment methods and their roles in indicating wastewater-associated pollution in aquatic environments
Assessing the viral enrichment methods and their roles in indicating wastewater-associated pollution in aquatic environments Open
With the increasing need for monitoring viral contamination in aquatic environments, research has increasingly focused on utilizing viruses as indicators for microbial contamination assessment. However, studies on enrichment techniques for…
View article: Optimal Brain Apoptosis
Optimal Brain Apoptosis Open
The increasing complexity and parameter count of Convolutional Neural Networks (CNNs) and Transformers pose challenges in terms of computational efficiency and resource demands. Pruning has been identified as an effective strategy to addre…
View article: The correlation of starch composition, physicochemical and structural properties of different sorghum grains
The correlation of starch composition, physicochemical and structural properties of different sorghum grains Open
The composition, structure, and physicochemical properties of starch in sorghum grains greatly influence the processing and quality of the final products. In this study, 19 sorghum lines were examined to analyze various starch-related char…
View article: Identification of hub biomarkers and immune cell infiltrations participating in the pathogenesis of endometriosis
Identification of hub biomarkers and immune cell infiltrations participating in the pathogenesis of endometriosis Open
Endometriosis (EM) is a chronic disease that can cause pain and infertility in patients. As is well known, immune cell infiltrations (ICIs) play important roles in the pathogenesis of EM. However, the pathogenesis and biomarkers of EM that…
View article: Event Masked Autoencoder: Point-wise Action Recognition with Event-Based Cameras
Event Masked Autoencoder: Point-wise Action Recognition with Event-Based Cameras Open
Dynamic vision sensors (DVS) are bio-inspired devices that capture visual information in the form of asynchronous events, which encode changes in pixel intensity with high temporal resolution and low latency. These events provide rich moti…
View article: Analysis and Prediction of Transmission Error of Harmonic Reducer for Space Robot
Analysis and Prediction of Transmission Error of Harmonic Reducer for Space Robot Open
During operation of the space robot joint, there are periodic changes in the load and speed of the harmonic reducer. Because the flexspline is a flexible mechanism, the transmission error of the harmonic reducer is related not only to manu…
View article: Cluster-directed ionic framework supramolecular hydrogel with high-temperature tolerability and enhanced water evaporation
Cluster-directed ionic framework supramolecular hydrogel with high-temperature tolerability and enhanced water evaporation Open
Ionic supramolecular frameworks made of polyoxometalates and cationic pseudo-rotaxane can form hydrogels with a stable, hierarchical porous structure that remains stable at temperatures above water's boiling point, reducing the evaporation…
View article: First principles study of electronic structure, mechanical properties and possible martensitic transformation in Ni<sub>2</sub>Cu-based Heusler alloys
First principles study of electronic structure, mechanical properties and possible martensitic transformation in Ni<sub>2</sub>Cu-based Heusler alloys Open
Ni2-based Heusler alloys have received increasing attention due to their shape memory effects and the relevant application properties. It is interesting to explore new Ni2-based shape memory alloys with novel properties. In this work, the …
View article: Robust SG-NeRF: Robust Scene Graph Aided Neural Surface Reconstruction
Robust SG-NeRF: Robust Scene Graph Aided Neural Surface Reconstruction Open
Neural surface reconstruction relies heavily on accurate camera poses as input. Despite utilizing advanced pose estimators like COLMAP or ARKit, camera poses can still be noisy. Existing pose-NeRF joint optimization methods handle poses wi…
View article: On dynamic responses of gear transmission system during rough tooth surface worn
On dynamic responses of gear transmission system during rough tooth surface worn Open
This study investigates the dynamic responses of gear systems while considering the morphology of worn gear tooth surfaces after different working times. Specifically, the anisotropic three-dimensional micro-morphology of the rough tooth s…
View article: Distributed Autonomous Economic Control Strategy for the AC/DC Interconnected Microgrid Considering the Regulation Boundary of the Consensus Variable
Distributed Autonomous Economic Control Strategy for the AC/DC Interconnected Microgrid Considering the Regulation Boundary of the Consensus Variable Open
The autonomous economic control for the islanded AC/DC interconnected microgrid has various modes due to the restriction of the feasible regions of inner and inter‐microgrid resources. To properly handle the cooperative relationship betwee…
View article: DEL: Discrete Element Learner for Learning 3D Particle Dynamics with Neural Rendering
DEL: Discrete Element Learner for Learning 3D Particle Dynamics with Neural Rendering Open
Learning-based simulators show great potential for simulating particle dynamics when 3D groundtruth is available, but per-particle correspondences are not always accessible. The development of neural rendering presents a new solution to th…
View article: E2H: A Two-Stage Non-Invasive Neural Signal Driven Humanoid Robotic Whole-Body Control Framework
E2H: A Two-Stage Non-Invasive Neural Signal Driven Humanoid Robotic Whole-Body Control Framework Open
Recent advancements in humanoid robotics, including the integration of hierarchical reinforcement learning-based control and the utilization of LLM planning, have significantly enhanced the ability of robots to perform complex tasks. In co…
View article: Manipulation Facing Threats: Evaluating Physical Vulnerabilities in End-to-End Vision Language Action Models
Manipulation Facing Threats: Evaluating Physical Vulnerabilities in End-to-End Vision Language Action Models Open
Recently, driven by advancements in Multimodal Large Language Models (MLLMs), Vision Language Action Models (VLAMs) are being proposed to achieve better performance in open-vocabulary scenarios for robotic manipulation tasks. Since manipul…