Yang Li

Techniques for Efficiently Handling Power Surges in Fuel Cell Powered Data Centers: Modeling, Analysis, Results

2018 · arXiv (Cornell University)

Fuel cells are a promising power source for future data centers, offering high energy efficiency, low greenhouse gas emissions, and high reliability. However, due to mechanical limitations related to fuel delivery, fuel cells are slow …

Weighted key enumeration for EM-based side-channel attacks

2018

Key enumeration algorithm is one of the useful post-analysis techniques for side-channel attacks to reduce the data complexity for successful key recovery. Normally, it is assumed that the merged key lists have similar quality since …

The Complexity of Morality: Checking Markov Blanket Consistency with DAGs via Morality

2019 · arXiv (Cornell University)

A family of Markov blankets in a faithful Bayesian network satisfies the symmetry and consistency properties. In this paper, we draw a bijection between families of consistent Markov blankets and moral graphs. We define the …

A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learning

2019 · arXiv (Cornell University)

In this paper, we proposed a general framework for data poisoning attacks to graph-based semi-supervised learning (G-SSL). In this framework, we first unify different tasks, goals, and constraints into a single formula for data poisoning …

Improved dolphin swarm optimization algorithm based on information entropy

2019 · Bulletin of the Polish Academy of Sciences Technical Sciences

In order to overcome the shortcomings of the dolphin algorithm, which is prone to falling into local optimum and premature convergence, an improved dolphin swarm algorithm, based on the standard dolphin algorithm, was proposed. As …

Computer-aided Detection of Squamous Carcinoma of the Cervix in Whole Slide Images

2019 · arXiv (Cornell University)

Goal: Squamous cell carcinoma of cervix is one of the most prevalent cancer worldwide in females. Traditionally, the most indispensable diagnosis of cervix squamous carcinoma is histopathological assessment which is achieved under microscope by pathologist. …

Feature Terms Prediction

2020

In Software Product Lines (SPL), feature extraction from software requirements specifications has been subject to intense research in order to assist domain analysis in a time-saving way. Although various approaches are proposed to extract features, …

SenticNet 6: Ensemble Application of Symbolic and Subsymbolic AI for Sentiment Analysis

2020

Deep learning has unlocked new paths towards the emulation of the peculiarly-human capability of learning from examples. While this kind of bottom-up learning works well for tasks such as image classification or object detection, it …

Privacy Protection in Deep Multi-modal Retrieval

2021

Deep learning techniques have ushered in significant progress in large-scale multi-modal retrieval. Nevertheless, the advanced techniques may be used nefariously to conduct a search that violates the privacy of individuals. In this paper, we propose …

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 …

Class-conditioned Domain Generalization via Wasserstein Distributional Robust Optimization

2021 · arXiv (Cornell University)

Given multiple source domains, domain generalization aims at learning a universal model that performs well on any unseen but related target domain. In this work, we focus on the domain generalization scenario where domain shifts …

Feature Extraction of National Physical Fitness Data Based on Data Mining

2022 · Mathematical Problems in Engineering

In order to better understand and optimize the national physical fitness, this paper puts forward the national physical fitness data change feature extraction method based on data mining, uses the decision tree and association rule …

ODNET: A Novel Personalized Origin-Destination Ranking Network for Flight Recommendation

2022 · 2022 IEEE 38th International Conference on Data Engineering (ICDE)

Origin-Destination recommendation that recom-mends personalized origin city (O) and destination city (D) of flight itinerary is of great value for both Online Travel Platforms (OTPs) and users. Existing studies on next location recommendation propose to …

Mamdani Fuzzy Inference System for Rating the Performance of Sponge City Programme

2022

China started Sponge City Programme (SCP) to manage urban floods and to improve the quality of water environment in 2015. So far, the first two batches of pilot cities of SCP have been finished construction …

Learning Representations from Local to Global for Fine-grained Patient Similarity Measuring in Intensive Care Unit

2022 · 2022 IEEE International Conference on Data Mining (ICDM)

Patient similarity measurement is an essential step in discovering clinically meaningful subgroups and building case retrieval systems. Most existing studies implement this procedure using similarity measurement algorithms on the multivariate clinical time-series (input space) or …

Research on Strategies to Improve Effective Teaching of English Listening in Rural Junior Middle Schools

2023 · Journal of Advanced Research in Education

Junior high school is a critical period of English learning. According to the English curriculum standards in China, junior high school English should not only pay attention to the imparting of language knowledge but also …

Multi-Granularity Information Interaction Framework for Incomplete Utterance Rewriting

2023 · arXiv (Cornell University)

Recent approaches in Incomplete Utterance Rewriting (IUR) fail to capture the source of important words, which is crucial to edit the incomplete utterance, and introduce words from irrelevant utterances. We propose a novel and effective …

Few-shot learning in intelligent agriculture: A review of methods and applications

2023 · Tarım Bilimleri Dergisi

Due to the high cost of data acquisition in many specific fields, such as intelligent agriculture, the available data is insufficient for the typical deep learning paradigm to show its superior performance. As an important …

Professional competency, professional identity, perceived organizational support of college teacher: Input to effective career management framework

2024 · International Journal of Research Studies in Management

With the increasing importance of technology, education and science, coupled with the competition for talents, human capital has becomes the most important capital for future social development. Vigorously improving the level of higher vocational education …

Causal-aware Graph Neural Architecture Search under Distribution Shifts

2024 · arXiv (Cornell University)

Graph NAS has emerged as a promising approach for autonomously designing GNN architectures by leveraging the correlations between graphs and architectures. Existing methods fail to generalize under distribution shifts that are ubiquitous in real-world graph …

A Quantum Automatic Tool for Finding Impossible Differentials

2024 · arXiv (Cornell University)

Due to the superiority of quantum computing, traditional cryptography is facing severe threat. This makes the security evaluation of cryptographic systems in quantum attack models significant and urgent. For symmetric ciphers, the security analysis heavily …

Scaling Parameter-Constrained Language Models with Quality Data

2024 · arXiv (Cornell University)

Scaling laws in language modeling traditionally quantify training loss as a function of dataset size and model parameters, providing compute-optimal estimates but often neglecting the impact of data quality on model generalization. In this paper, …

How customers respond to chatbot anthropomorphism: the mediating roles of perceived humanness and perceived persuasiveness

2024 · European Journal of Marketing

Purpose This study aims to investigate how chatbots’ warmth and competence affect customer behavioural expectation (i.e. purchase, recommendation) through perceived humanness and perceived persuasiveness. Moreover, prior knowledge of chatbot is considered the boundary condition of …

Integrated high-performance LDPC decoder for Continuous-Variable Quantum Key Distribution System

2025

The throughput of the error correction decoding is one of the major bottlenecks of high-speed continuous-variable quantum key distribution (CV-QKD) systems and an integrated decoder with Gbps decoding throughput is implemented in this work.

SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains

2025

Ran Xu, Hui Liu, Sreyashi Nag, Zhenwei Dai, Yaochen Xie, Xianfeng Tang, Chen Luo, Yang Li, Joyce C. Ho, Carl Yang, Qi He. Proceedings of the 2025 Conference of the Nations of the Americas Chapter …

Towards Monotonic Improvement in In-Context Reinforcement Learning

2025 · arXiv (Cornell University)

In-Context Reinforcement Learning (ICRL) has emerged as a promising paradigm for developing agents that can rapidly adapt to new tasks by leveraging past experiences as context, without updating their parameters. Recent approaches train large sequence …

On learning denoisable student logits

2026 · Pattern Recognition

Knowledge Distillation (KD) aims to train a student model to mimic the behavior of a more powerful teacher model. In this paper, we reveal that through the lens of diffusion processes, student logits can be …

Cluster-GCN

2019

Graph convolutional network (GCN) has been successfully applied to many graph-based applications; however, training a large-scale GCN remains challenging. Current SGD-based algorithms suffer from either a high computational cost that exponentially grows with number of …

Big Bird: Transformers for Longer Sequences

2020 · arXiv (Cornell University)

Transformers-based models, such as BERT, have been one of the most successful deep learning models for NLP. Unfortunately, one of their core limitations is the quadratic dependency (mainly in terms of memory) on the sequence …