Tao Shen

Exploration of offering photoelectric experimental general elective courses for college students of science and technology

2017 · 14th Conference on Education and Training in Optics and Photonics: ETOP 2017

The necessity of offering photoelectric experiment general elective courses, such as the experiments of modern optical and innovational photoelectric design for non optic-electric’s science and engineering students were discussed based on the analysis of the …

Multi-Task Learning for Conversational Question Answering over a Large-Scale Knowledge Base

2019 · arXiv (Cornell University)

We consider the problem of conversational question answering over a large-scale knowledge base. To handle huge entity vocabulary of a large-scale knowledge base, recent neural semantic parsing based approaches usually decompose the task into several …

Realizing downstream access network using continuous-variable quantum key distribution

2021 · arXiv (Cornell University)

Quantum key distribution (QKD) which enables the secure distribution of symmetric keys between two legitimate parties is of great importance in future network security. Access network that connects multiple end-users with one network backbone can …

Dynamic Prediction Model for NOx Emission of SCR System Based on Hybrid Data-driven Algorithms

2021 · arXiv (Cornell University)

Aiming at the problem that delay time is difficult to determine and prediction accuracy is low in building prediction model of SCR system, a dynamic modeling scheme based on a hybrid of multiple data-driven algorithms …

FedGuCci: Making Local Models More Connected in Landscape for Federated Learning

2024 · arXiv (Cornell University)

Federated learning (FL) involves multiple heterogeneous clients collaboratively training a global model via iterative local updates and model fusion. The generalization of FL's global model has a large gap compared with centralized training, which is …

FlowerTune: A Cross-Domain Benchmark for Federated Fine-Tuning of Large Language Models

2025

Large Language Models (LLMs) have achieved state-of-the-art results across diverse domains, yet their development remains reliant on vast amounts of publicly available data, raising concerns about data scarcity and the lack of access to domain-specific, …

A review of reinforcement learning: A tripartite framework of environment design, algorithmic innovation, and application scenarios

2026 · Array

Reinforcement learning is gradually shifting from a research paradigm dominated by games and simulations toward real complex scenarios with high safety requirements and high costs, such as energy systems, industrial control, robotics, medical decision-making, and …

DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding

2018 · Proceedings of the AAAI Conference on Artificial Intelligence

Recurrent neural nets (RNN) and convolutional neural nets (CNN) are widely used on NLP tasks to capture the long-term and local dependencies, respectively. Attention mechanisms have recently attracted enormous interest due to their highly parallelizable …

Structure-Augmented Text Representation Learning for Efficient Knowledge Graph Completion

2021

Human-curated knowledge graphs provide critical supportive information to various natural language processing tasks, but these graphs are usually incomplete, urging auto-completion of them (a.k.a. knowledge graph completion). Prevalent graph embedding approaches, e.g., TransE, learn structured …

Multi-center federated learning: clients clustering for better personalization

2022 · World Wide Web

Abstract Personalized decision-making can be implemented in a Federated learning (FL) framework that can collaboratively train a decision model by extracting knowledge across intelligent clients, e.g. smartphones or enterprises. FL can mitigate the data privacy …