Tao Li
16 papers in the PaperMetrix corpus
Papers by this author
-
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 …
-
Research on cloud computing task scheduling algorithm based on particle swarm optimization
2018 · Journal of Computational Methods in Sciences and Engineering
In the field of cloud computing, Particle swarm optimization (PSO) is an important intelligent algorithm for solving the task scheduling problem, and has been rapidly developed. In order to improve the overall optimization ability, and …
-
STRIDE: Single-Trip-Time Based Reliable Data Transport Protocol for the Reconfigurable Cloud
2019
In a recent development, reconfigurable clouds become a viable solution to overcome practical problems in clouds, such as scalability, delay, etc., by offloading computation tasks to reconfigurable hardware, FPGA. Several existing techniques, such as TCP/IP …
-
KEoG: A knowledge-aware edge-oriented graph neural network for document-level relation extraction
2020
Document-level relation extraction (RE) has attracted more and more attentions recently. Edge-oriented graph neural network (EoG) is a new neural network exhibiting greater potential than previous node-oriented graph neural networks for document-level RE. In this …
-
Quantum entanglement creation for distant quantum memories via time-bin multiplexing
2021 · Physical Review A
Quantum networks require parallel quantum entanglement between pairs of distant quantum memories (QMs) for practical applications. However, usually one pair of QMs is entangled using a single photonic pulse and multiple pulses are consumed to …
-
Deterministic secure quantum communication with double-encoded single photons
2022 · Acta Physica Sinica
Quantum communication is an important branch of quantum technology. It can safely transmit private information between legitimate parties and its unconditional security is guaranteed by quantum physics. So far, deterministic secure quantum communication without entanglement …
-
Cross-speaker Emotion Transfer Based On Prosody Compensation for End-to-End Speech Synthesis
2022 · Interspeech 2022
Cross-speaker emotion transfer speech synthesis aims to synthesize emotional speech for a target speaker by transferring the emotion from reference speech recorded by another (source) speaker.In this task, extracting speaker-independent emotion embedding from reference speech …
-
A Blockchain-Based Copyright Protection Scheme With Proactive Defense
2023 · IEEE Transactions on Services Computing
Copyright protection, including copyright registration, copyright transfer and infringement penalty, plays a critical role in preventing illegal usage of original works. The mainstream traditional copyright protection schemes need an authority online all the time to …
-
Aligning Language Models with Offline Learning from Human Feedback
2023 · arXiv (Cornell University)
Learning from human preferences is crucial for language models (LMs) to effectively cater to human needs and societal values. Previous research has made notable progress by leveraging human feedback to follow instructions. However, these approaches …
-
Heralded quantum multiplexing entanglement between stationary qubits via distribution of high-dimensional optical entanglement
2023 · Optics Express
Quantum entanglement between pairs of remote quantum memories (QMs) is a prerequisite for realizing many applications in quantum networks. Here, we present a heralded protocol for the parallel creation of quantum entanglement among multiple pairs …
-
Grimm: A Plug-and-Play Perturbation Rectifier for Graph Neural Networks Defending against Poisoning Attacks
2024 · arXiv (Cornell University)
Recent studies have revealed the vulnerability of graph neural networks (GNNs) to adversarial poisoning attacks on node classification tasks. Current defensive methods require substituting the original GNNs with defense models, regardless of the original's type. …
-
Privacy-Preserving Distributed Online Mirror Descent for Nonconvex Optimization
2025 · arXiv (Cornell University)
We investigate the distributed online nonconvex optimization problem with differential privacy over time-varying networks. Each node minimizes the sum of several nonconvex functions while preserving the node's differential privacy. We propose a privacy-preserving distributed online …
-
Graph Agent Network: Empowering Nodes with Inference Capabilities for Adversarial Resilience
2025 · Proceedings of the AAAI Conference on Artificial Intelligence
End-to-end training with global optimization have popularized graph neural networks (GNNs) for node classification, yet inadvertently introduced vulnerabilities to adversarial edge-perturbing attacks. Adversaries can exploit the inherent opened interfaces of GNNs' input and output, perturbing …
-
Time-Aware Feature Selection: Adaptive Temporal Masking for Stable Sparse Autoencoder Training
2025 · arXiv (Cornell University)
Understanding the internal representations of large language models is crucial for ensuring their reliability and safety, with sparse autoencoders (SAEs) emerging as a promising interpretability approach. However, current SAE training methods face feature absorption, where …
-
Natural Language Processing Applied to Psychiatric Clinical Notes: Scoping Review
2026 · JMIR Medical Informatics
Background: Psychiatric clinical notes in electronic health records (EHRs) provide rich longitudinal information that can support clinical decision-making. Using historical medical data can enable earlier identification of mental illness, better characterization of disease trajectories, and …
-
HiRecS: A Hierarchical Contextual Location Recommendation System
2019 · IEEE Transactions on Computational Social Systems
The point-of-interest (POI) recommender exploits check-in information from location-based social networks (LBSNs) to recommend POIs that match user preferences. The preferences of users vary with region/locality, consumption type, and co-consumers. For instance, the places preferred …