Search Results for author: Yutong Li

Found 16 papers, 4 papers with code

Distributed Resilient Secondary Control for Microgrids with Attention-based Weights against High-density Misbehaving Agents

no code implementations18 Sep 2024 Yutong Li, Lili Wang

Microgrids (MGs) have been equipped with large-scale distributed energy sources (DESs), and become more vulnerable due to the low inertia characteristic.

ChatCite: LLM Agent with Human Workflow Guidance for Comparative Literature Summary

no code implementations5 Mar 2024 Yutong Li, Lu Chen, Aiwei Liu, Kai Yu, Lijie Wen

In this work, we firstly focus on the independent literature summarization step and introduce ChatCite, an LLM agent with human workflow guidance for comparative literature summary.

Retrieval

System-level Safety Guard: Safe Tracking Control through Uncertain Neural Network Dynamics Models

1 code implementation11 Dec 2023 Xiao Li, Yutong Li, Anouck Girard, Ilya Kolmanovsky

The Neural Network (NN), as a black-box function approximator, has been considered in many control and robotics applications.

Robot Navigation

GarmentTracking: Category-Level Garment Pose Tracking

1 code implementation CVPR 2023 Han Xue, Wenqiang Xu, Jieyi Zhang, Tutian Tang, Yutong Li, Wenxin Du, Ruolin Ye, Cewu Lu

In this work, we present a complete package to address the category-level garment pose tracking task: (1) A recording system VR-Garment, with which users can manipulate virtual garment models in simulation through a VR interface.

Pose Tracking

Evaluating Psychological Safety of Large Language Models

no code implementations20 Dec 2022 Xingxuan Li, Yutong Li, Lin Qiu, Shafiq Joty, Lidong Bing

Despite being instruction fine-tuned with safety metrics to reduce toxicity, InstructGPT, GPT-3. 5, and GPT-4 still showed dark personality patterns; these models scored higher than self-supervised GPT-3 on the Machiavellianism and narcissism traits on SD-3.

Safe Control and Learning Using Generalized Action Governor

no code implementations22 Nov 2022 Nan Li, Yutong Li, Ilya Kolmanovsky, Anouck Girard, H. Eric Tseng, Dimitar Filev

This paper introduces the Generalized Action Governor, which is a supervisory scheme for augmenting a nominal closed-loop system with the capability of strictly handling constraints.

reinforcement-learning Reinforcement Learning (RL)

CurvPnP: Plug-and-play Blind Image Restoration with Deep Curvature Denoiser

1 code implementation14 Nov 2022 Yutong Li, Yuping Duan

Due to the development of deep learning-based denoisers, the plug-and-play strategy has achieved great success in image restoration problems.

Deblurring Image Denoising +3

Robust Action Governor for Uncertain Piecewise Affine Systems with Non-convex Constraints and Safe Reinforcement Learning

no code implementations17 Jul 2022 Yutong Li, Nan Li, H. Eric Tseng, Anouck Girard, Dimitar Filev, Ilya Kolmanovsky

The action governor is an add-on scheme to a nominal control loop that monitors and adjusts the control actions to enforce safety specifications expressed as pointwise-in-time state and control constraints.

RAG Reinforcement Learning (RL) +1

Maps Search Misspelling Detection Leveraging Domain-Augmented Contextual Representations

no code implementations15 Aug 2021 Yutong Li

Building an independent misspelling detector and serve it before correction can bring multiple benefits to speller and other search components, which is particularly true for the most commonly deployed noisy-channel based speller systems.

Representation Learning

Dermoscopic Image Classification with Neural Style Transfer

no code implementations17 May 2021 Yutong Li, Ruoqing Zhu, Annie Qu, Mike Yeh

We represent each dermoscopic image as the style image and transfer the style of the lesion onto a homogeneous content image.

Classification Image Classification +5

Safe Reinforcement Learning Using Robust Action Governor

no code implementations21 Feb 2021 Yutong Li, Nan Li, H. Eric Tseng, Anouck Girard, Dimitar Filev, Ilya Kolmanovsky

Reinforcement Learning (RL) is essentially a trial-and-error learning procedure which may cause unsafe behavior during the exploration-and-exploitation process.

RAG reinforcement-learning +3

Extraction Meets Abstraction: Ideal Answer Generation for Biomedical Questions

no code implementations WS 2018 Yutong Li, Nicholas Gekakis, Qiuze Wu, Boyue Li, Ch, Khyathi u, Eric Nyberg

The growing number of biomedical publications is a challenge for human researchers, who invest considerable effort to search for relevant documents and pinpointed answers.

Abstractive Text Summarization Answer Generation +5

Cannot find the paper you are looking for? You can Submit a new open access paper.