Rui Liu

Simultaneous Low-rank Component and Graph Estimation for High-dimensional Graph Signals: Application to Brain Imaging

2016 · arXiv (Cornell University)

We propose an algorithm to uncover the intrinsic low-rank component of a high-dimensional, graph-smooth and grossly-corrupted dataset, under the situations that the underlying graph is unknown. Based on a model with a low-rank component plus …

Phase Conductor on Multi-layered Attentions for Machine Comprehension

2017 · arXiv (Cornell University)

Attention models have been intensively studied to improve NLP tasks such as machine comprehension via both question-aware passage attention model and self-matching attention model. Our research proposes phase conductor (PhaseCond) for attention models in two …

Research and Application UAV Operation Data Trusted Storage Technology Based on Blockchain

2020 · 2020 IEEE 2nd International Conference on Civil Aviation Safety and Information Technology (ICCASIT

With the wide application of UAV (Unmanned Aircraft Vehicle), UAVs have the characteristics of multiple models and scattered operation. In order to strengthen the management of UAVs and eliminate hidden safety hazards, the Civil Aviation …

Robot Inner Attention Modeling for Task-Adaptive Teaming of Heterogeneous Multi Robots

2020 · arXiv (Cornell University)

Attracted by team scale and function diversity, a heterogeneous multi-robot system (HMRS), where multiple robots with different functions and numbers are coordinated to perform tasks, has been widely used for complex and large-scale scenarios, including …

Synthesized Trust Learning from Limited Human Feedback for Human-Load-Reduced Multi-Robot Deployments

2021

Human multi-robot system (MRS) collaboration is demonstrating potentials in wide application scenarios due to the integration of human cognitive skills and a robot team’s powerful capability introduced by its multi-member structure. However, due to limited …

Gating Dropout: Communication-efficient Regularization for Sparsely Activated Transformers

2022 · arXiv (Cornell University)

Sparsely activated transformers, such as Mixture of Experts (MoE), have received great interest due to their outrageous scaling capability which enables dramatical increases in model size without significant increases in computational cost. To achieve this, …

Extreme Learning Machine Classifier Based on Novel Particle Swarm Optimization Algorithm

2023

Aiming at the problem of low classification accuracy caused by random input weights and hidden layer bias in ELM (Extreme Learning Machines, ELM), a method based on IPSO (Improved Particle Swarm Optimization, IPSO) to optimize …

Exploring Large Language Model-Aided Document Expansion for Sparse Retrieval

2025

Document expansion is a technique designed to mitigate the term mismatch problem by enriching documents with related terms or queries, thereby improving retrieval performance. Notable approaches like doc2query and docT5query utilize sequence-to-sequence transformers or T5 …