Pengcheng Wu
YOU?
Author Swipe
View article: A Survey on Vision-Language Models for Multimodal Federated Learning Tasks
A Survey on Vision-Language Models for Multimodal Federated Learning Tasks Open
View article: A Survey on Vision-Language Models for Multimodal Federated Learning Tasks
A Survey on Vision-Language Models for Multimodal Federated Learning Tasks Open
View article: Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexity
Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexity Open
Spiking Neural Networks (SNNs) often suffer from high time complexity $O(T)$ due to the sequential processing of $T$ spikes, making training computationally expensive. In this paper, we propose a novel Fixed-point Parallel Training (FPT) m…
View article: NTPP: Generative Speech Language Modeling for Dual-Channel Spoken Dialogue via Next-Token-Pair Prediction
NTPP: Generative Speech Language Modeling for Dual-Channel Spoken Dialogue via Next-Token-Pair Prediction Open
Inspired by the impressive capabilities of GPT-4o, there is growing interest in enabling speech language models (SLMs) to engage in natural, fluid spoken interactions with humans. Recent advancements have led to the development of several …
View article: HDT: Hierarchical Discrete Transformer for Multivariate Time Series Forecasting
HDT: Hierarchical Discrete Transformer for Multivariate Time Series Forecasting Open
Generative models have gained significant attention in multivariate time series forecasting (MTS), particularly due to their ability to generate high-fidelity samples. Forecasting the probability distribution of multivariate time series is…
View article: Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models
Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models Open
Recent advancements in multimodal reasoning have largely overlooked the audio modality. We introduce Audio-Reasoner, a large-scale audio language model for deep reasoning in audio tasks. We meticulously curated a large-scale and diverse mu…
View article: Evolutionary Reinforcement Learning: A Systematic Review and Future Directions
Evolutionary Reinforcement Learning: A Systematic Review and Future Directions Open
In response to the limitations of reinforcement learning and Evolutionary Algorithms (EAs) in complex problem-solving, Evolutionary Reinforcement Learning (EvoRL) has emerged as a synergistic solution. This systematic review aims to provid…
View article: HDT: Hierarchical Discrete Transformer for Multivariate Time Series Forecasting
HDT: Hierarchical Discrete Transformer for Multivariate Time Series Forecasting Open
Generative models have gained significant attention in multivariate time series forecasting (MTS), particularly due to their ability to generate high-fidelity samples. Forecasting the probability distribution of multivariate time series is…
View article: Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models
Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models Open
View article: Exploring New Paradigms in Time Series Prediction by Integrating Computer Simulations and Machine Learning
Exploring New Paradigms in Time Series Prediction by Integrating Computer Simulations and Machine Learning Open
Time series prediction is a challenging task that requires modeling complex temporal dependencies and structural priors. In this work, we propose a novel framework that fundamentally advances existing Transformer-based methods through the …
View article: Evolutionary Reinforcement Learning: A Systematic Review and Future Directions
Evolutionary Reinforcement Learning: A Systematic Review and Future Directions Open
In response to the limitations of reinforcement learning and evolutionary algorithms (EAs) in complex problem-solving, Evolutionary Reinforcement Learning (EvoRL) has emerged as a synergistic solution. EvoRL integrates EAs and reinforcemen…
View article: Research on Positioning Accuracy of Mobile Robot in Indoor Environment Based on Improved RTABMAP Algorithm
Research on Positioning Accuracy of Mobile Robot in Indoor Environment Based on Improved RTABMAP Algorithm Open
Visual simultaneous localization and mapping is a widely used technology for mobile robots to carry out precise positioning in the environment of GNSS technology failure. However, as the robot moves around indoors, its position accuracy wi…
View article: Smart Decision-Support System for Pig Farming
Smart Decision-Support System for Pig Farming Open
There are multiple participants, such as farmers, wholesalers, retailers, financial institutions, etc., involved in the modern food production process. All of these participants and stakeholders have a shared goal, which is to gather infor…
View article: A Survey on Reinforcement Learning for Recommender Systems
A Survey on Reinforcement Learning for Recommender Systems Open
Recommender systems have been widely applied in different real-life scenarios to help us find useful information. In particular, Reinforcement Learning (RL) based recommender systems have become an emerging research topic in recent years, …
View article: HyDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks
HyDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks Open
The behaviors of deep neural networks (DNNs) are notoriously resistant to human interpretations. In this paper, we propose Hypergradient Data Relevance Analysis, or HyDRA, which interprets the predictions made by DNNs as effects of their t…
View article: HYDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks
HYDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks Open
The behaviors of deep neural networks (DNNs) are notoriously resistant to human interpretations. In this paper, we propose Hypergradient Data Relevance Analysis, or HYDRA, which interprets the predictions made by DNNs as effects of their t…
View article: Prerequisite Relation Learning for Course Concepts Based on Hyperbolic Deep Representation
Prerequisite Relation Learning for Course Concepts Based on Hyperbolic Deep Representation Open
With the rapid development of MOOCs, more and more learners participate in online learning to improve their abilities. However, students from different educational backgrounds have different starting points, requirements and foundation. Ho…
View article: Face Detection using Deep Learning: An Improved Faster RCNN Approach
Face Detection using Deep Learning: An Improved Faster RCNN Approach Open
In this report, we present a new face detection scheme using deep learning and achieve the state-of-the-art detection performance on the well-known FDDB face detetion benchmark evaluation. In particular, we improve the state-of-the-art fas…
View article: HDIdx: High-dimensional indexing for efficient approximate nearest neighbor search
HDIdx: High-dimensional indexing for efficient approximate nearest neighbor search Open
View article: A Framework of Sparse Online Learning and Its Applications
A Framework of Sparse Online Learning and Its Applications Open
The amount of data in our society has been exploding in the era of big data today. In this paper, we address several open challenges of big data stream classification, including high volume, high velocity, high dimensionality, high sparsit…
View article: Virtual Instrumentation Design on Earthquake Simulation System
Virtual Instrumentation Design on Earthquake Simulation System Open
This research develops a virtual instrumentation on earthquake simulation system.The hardware part, an earthquake simulation platform, is constructed and installed with accelerometers.The software part, LabVIEW, is programmed to record, mo…