Bohan Wu
YOU?
Author Swipe
Design and Implementation of Intelligent Shopping Recommendation System Based on AI Open
This paper presents the design and implementation of an Intelligent Shopping Recommendation System that addresses the increasing need for personalized product suggestions in modern e-commerce environments. The system combines a React-based…
The Efficient Degradation of Oxytetracycline in Wastewater Using Fe/Mn-Modified Magnetic Oak Biochar: Pathways and Mechanistic Investigation Open
Antibiotic resistance has been recognized as a global threat to human health. Therefore, it is urgent to develop effective strategies to address the contamination of water environments caused by antibiotics. In this study, Fe/Mn bimetallic…
View article: Plasmon Mediated Photocatalysis: Engineering Interfaces for Effective Hot Carrier Utilization
Plasmon Mediated Photocatalysis: Engineering Interfaces for Effective Hot Carrier Utilization Open
Plasmonic metal/semiconductor hetero-nanostructures have attracted tremendous research interests in optoelectronic devices, photocatalysis and photothermal therapy, and related fields. Among various mechanisms of localized surface plasmon …
View article: A Survey on Efficient Large Language Model Training: From Data-centric Perspectives
A Survey on Efficient Large Language Model Training: From Data-centric Perspectives Open
Post-training of Large Language Models (LLMs) is crucial for unlocking their task generalization potential and domain-specific capabilities. However, the current LLM post-training paradigm faces significant data challenges, including the h…
Integrated classification method of tight sandstone reservoir based on principal component analysis– simulated annealing genetic algorithm–fuzzy cluster means Open
In this research, a integrated classification method based on principal component analysis - simulated annealing genetic algorithm - fuzzy cluster means (PCA-SAGA-FCM) was proposed for the unsupervised classification of tight sandstone res…
Application of Speech on Stress Recognition with Neural Network in Nuclear Power Plant Open
Human failures occur in nuclear power plants when operators are under acute stress. Therefore, an automatic stressed recognition system should be developed for nuclear power work. Previous studies on the prediction of stress are limited be…
Example-Driven Model-Based Reinforcement Learning for Solving Long-Horizon Visuomotor Tasks Open
In this paper, we study the problem of learning a repertoire of low-level skills from raw images that can be sequenced to complete long-horizon visuomotor tasks. Reinforcement learning (RL) is a promising approach for acquiring short-horiz…
Preparation and Properties of Intrinsically Atomic-Oxygen Resistant Polyimide Films Containing Polyhedral Oligomeric Silsesquioxane (POSS) in the Side Chains Open
The relatively poor atomic-oxygen (AO) resistance of the standard polyimide (PI) films greatly limits the wide applications in low earth orbit (LEO) environments. The introduction of polyhedral oligomeric silsesquioxane (POSS) units into t…
SQUIRL: Robust and Efficient Learning from Video Demonstration of Long-Horizon Robotic Manipulation Tasks Open
Recent advances in deep reinforcement learning (RL) have demonstrated its potential to learn complex robotic manipulation tasks. However, RL still requires the robot to collect a large amount of real-world experience. To address this probl…
View article: MAT: Multi-Fingered Adaptive Tactile Grasping via Deep Reinforcement Learning
MAT: Multi-Fingered Adaptive Tactile Grasping via Deep Reinforcement Learning Open
Vision-based grasping systems typically adopt an open-loop execution of a planned grasp. This policy can fail due to many reasons, including ubiquitous calibration error. Recovery from a failed grasp is further complicated by visual occlus…
Pixel-Attentive Policy Gradient for Multi-Fingered Grasping in Cluttered Scenes Open
Recent advances in on-policy reinforcement learning (RL) methods enabled learning agents in virtual environments to master complex tasks with high-dimensional and continuous observation and action spaces. However, leveraging this family of…