3 citations · 9 across the 12 of their papers we have counts for
12 papers
Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-Text Rationales
Brihi Joshi, Ziyi Liu, Sahana Ramnath +6
Among the remarkable emergent capabilities of large language models (LMs) is free-text rationalization; beyond a certain scale, large LMs are capable of generating seemingly useful…
Handling Concept Drift in Global Time Series Forecasting
Ziyi Liu, Rakshitha Godahewa, Kasun Bandara +1
Machine learning (ML) based time series forecasting models often require and assume certain degrees of stationarity in the data when producing forecasts. However, in many real-worl…
Clustered Federated Learning based on Nonconvex Pairwise Fusion
Xue Yu, Ziyi Liu, Wu Wang +1
This study investigates clustered federated learning (FL), one of the formulations of FL with non-i.i.d. data, where the devices are partitioned into clusters and each cluster opti…
XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models
Dong-Ho Lee, Akshen Kadakia, Brihi Joshi +8
NLP models are susceptible to learning spurious biases (i.e., bugs) that work on some datasets but do not properly reflect the underlying task. Explanation-based model debugging ai…
AiM: Taking Answers in Mind to Correct Chinese Cloze Tests in Educational Applications
Yusen Zhang, Zhongli Li, Qingyu Zhou +5
To automatically correct handwritten assignments, the traditional approach is to use an OCR model to recognize characters and compare them to answers. The OCR model easily gets con…
Learning Generalizable Risk-Sensitive Policies to Coordinate in Decentralized Multi-Agent General-Sum Games
Ziyi Liu, Xian Guo, Yongchun Fang
While various multi-agent reinforcement learning methods have been proposed in cooperative settings, few works investigate how self-interested learning agents achieve mutual coordi…
LightFuse: Lightweight CNN based Dual-exposure Fusion
Ziyi Liu, Jie Yang, Svetlana Yanushkevich +1
Deep convolutional neural networks (DCNNs) have aided high dynamic range (HDR) imaging recently and have received a lot of attention. The quality of DCNN-generated HDR images has o…
Mobile-end Tone Mapping based on Integral Image and Integral Histogram
Jie Yang, Mengchen Lin, Ziyi Liu +2
Wide dynamic range (WDR) image tone mapping is in high demand in many applications like film production, security monitoring, and photography. It is especially crucial for mobile d…
Tone Mapping Based on Multi-scale Histogram Synthesis
Jie Yang, Ziyi Liu, Ulian Shahnovich +1
In this paper, we present a novel tone mapping algorithm that can be used for displaying wide dynamic range (WDR) images on low dynamic range (LDR) devices. The proposed algorithm…
Deep Reformulated Laplacian Tone Mapping
Jie Yang, Ziyi Liu, Mengchen Lin +2
Wide dynamic range (WDR) images contain more scene details and contrast when compared to common images. However, it requires tone mapping to process the pixel values in order to di…
WDR FACE: The First Database for Studying Face Detection in Wide Dynamic Range
Ziyi Liu, Jie Yang, Mengchen Lin +3
Currently, face detection approaches focus on facial information by varying specific parameters including pose, occlusion, lighting, background, race, and gender. These studies onl…
A review for Tone-mapping Operators on Wide Dynamic Range Image
Ziyi Liu
The dynamic range of our normal life can exceeds 120 dB, however, the smart-phone cameras and the conventional digital cameras can only capture a dynamic range of 90 dB, which some…