Chao Li

BAAT: Towards Dynamically Managing Battery Aging in Green Datacenters

2015

Energy storage devices (batteries) have shown great promise in eliminating supply/demand power mismatch and reducing energy/power cost in green datacenters. These important components progressively age due to irregular usage patterns, which result in less effective …

Truncated differential cryptanalysis of PRINCE

2015 · Security and Communication Networks

Abstract PRINCE is a lightweight block cipher whose block size and key size are 64‐bit and 128‐bit, respectively. The core component of PRINCE is PRINCE which is wrapped by the initial and final key whitening. …

New Permutation Trinomials Constructed from Fractional Polynomials

2016 · arXiv (Cornell University)

Permutation trinomials over finite fields consititute an active research due to their simple algebraic form, additional extraordinary properties and their wide applications in many areas of science and engineering. In the present paper, six new …

Predicting Research Trends From Arxiv

2018 · arXiv (Cornell University)

Knowing trends in research has been a long-standing dream of scientists. Projects on popular research topics often lead to higher acceptance rates at conferences and journals, as well as funding application approvals. Further, knowing future …

Sturgeon: Preference-aware Co-location for Improving Utilization of Power Constrained Computers

2020

Large-scale datacenters often host latency-sensitive services that have stringent Quality-of-Service requirement and experience diurnal load pattern. Co-locating best-effort applications that have no QoS requirement with latency-sensitive services has been widely used to improve the resource …

Interpretability is a Kind of Safety: An Interpreter-based Ensemble for Adversary Defense

2020

While having achieved great success in rich real-life applications, deep neural network (DNN) models have long been criticized for their vulnerability to adversarial attacks. Tremendous research efforts have been dedicated to mitigating the threats of …

A Distributed SGD Algorithm with Global Sketching for Deep Learning Training Acceleration

2021 · arXiv (Cornell University)

Distributed training is an effective way to accelerate the training process of large-scale deep learning models. However, the parameter exchange and synchronization of distributed stochastic gradient descent introduce a large amount of communication overhead. Gradient …

Towards Robust Knowledge Graph Embedding via Multi-Task Reinforcement Learning

2021 · IEEE Transactions on Knowledge and Data Engineering

Nowadays, Knowledge graphs (KGs) have been playing a pivotal role in AI-related applications. Despite the large sizes, existing KGs are far from complete and comprehensive. In order to continuously enrich KGs, automatic knowledge construction and …

Research on Feature Fusion Speech Emotion Recognition Technology for Smart Teaching

2022 · Mobile Information Systems

At present, there are numerous intelligent teaching applications based on various advanced pattern recognition technologies, such as face sign-in, classroom action recognition, student facial expression recognition, and other systems which have been gradually applied to …

Accelerating Self-Imitation Learning from Demonstrations via Policy Constraints and Q-Ensemble

2022 · arXiv (Cornell University)

Deep reinforcement learning (DRL) provides a new way to generate robot control policy. However, the process of training control policy requires lengthy exploration, resulting in a low sample efficiency of reinforcement learning (RL) in real-world …

Robust Intrusion Detection for Industrial Control Systems Using Improved Autoencoder and Bayesian Gaussian Mixture Model

2023 · Mathematics

Machine learning-based intrusion detection systems are an effective way to cope with the increasing security threats faced by industrial control systems. Considering that it is hard and expensive to obtain attack data, it is more …

RiskQ: Risk-sensitive Multi-Agent Reinforcement Learning Value Factorization

2023 · arXiv (Cornell University)

Multi-agent systems are characterized by environmental uncertainty, varying policies of agents, and partial observability, which result in significant risks. In the context of Multi-Agent Reinforcement Learning (MARL), learning coordinated and decentralized policies that are sensitive …

Bottom-up approach to room-temperature quantum systems

2023 · Physical Review A

We demonstrate a key ingredient in a bottom-up approach to building complex quantum matter using thermal atomic vapors. We isolate and track very slowly moving individual atoms without the aid of laser cooling. Passive filtering …

Electronic Warfare UAV Combat Effectiveness Evaluation Based on GrC-Elm

2023

To increase the combat capability of Electronic Warfare Unmanned Air Vehicle (EWUAV), a combat effectiveness evaluation method is proposed based on Granular Computing (GrC) and modified Extreme Learning Machine (ELM). In the method, the combat …

AI-Assisted College Students' English Writing Scoring with Hierarchical LSTM for Enhanced Contextual Understanding and Grading Accuracy

2024

In the realm of college English instruction, assessing students' writing abilities both objectively and effectively presents a variety of ongoing challenges. To address these issues, this paper proposes an AI-supported system for automated English writing …

AndesVL Technical Report: An Efficient Mobile-side Multimodal Large Language Model

2025 · arXiv (Cornell University)

In recent years, while cloud-based MLLMs such as QwenVL, InternVL, GPT-4o, Gemini, and Claude Sonnet have demonstrated outstanding performance with enormous model sizes reaching hundreds of billions of parameters, they significantly surpass the limitations in …

ICAD-LLM: One-for-All Anomaly Detection via In-Context Learning with Large Language Models

2025 · arXiv (Cornell University)

Anomaly detection (AD) is a fundamental task of critical importance across numerous domains. Current systems increasingly operate in rapidly evolving environments that generate diverse yet interconnected data modalities -- such as time series, system logs, …

Adaptive State-Space Mamba for Real-Time Sensor Data Anomaly Detection

2025 · arXiv (Cornell University)

State-space modeling has emerged as a powerful paradigm for sequence analysis in various tasks such as natural language processing, time-series forecasting, and signal processing. In this work, we propose an \emph{Adaptive State-Space Mamba} (\textbf{ASSM}) framework …

Multi-Interest Network with Dynamic Routing for Recommendation at Tmall

2019

Industrial recommender systems have embraced deep learning algorithms for building intelligent systems to make accurate recommendations. At its core, deep learning offers powerful ability for learning representations from data, especially for user and item representations. …