Yang You

Combinational Q-Learning for Dou Di Zhu

2019 · arXiv (Cornell University)

Deep reinforcement learning (DRL) has gained a lot of attention in recent years, and has been proven to be able to play Atari games and Go at or above human levels. However, those games are …

Rethinking the Value of Asynchronous Solvers for Distributed Deep Learning

2019

In recent years, the field of machine learning has seen significant advances as data becomes more abundant and deep learning models become larger and more complex. However, these improvements in accuracy [2] have come at …

Research on the Application of BIM + VR Technology in the Project

2020 · IOP Conference Series Earth and Environmental Science

Abstract At present, the research of BIM + VR technology is the forefront of BIM technology application research. BIM technology can solve some design problems and provide collaborative design solutions for various professions. Virtual reality …

Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models

2023 · arXiv (Cornell University)

Continual learning (CL) can help pre-trained vision-language models efficiently adapt to new or under-trained data distributions without re-training. Nevertheless, during the continual training of the Contrastive Language-Image Pre-training (CLIP) model, we observe that the model's …

A Hierarchical Encoding-Decoding Scheme for Abstractive Multi-document Summarization

2023

Pre-trained language models (PLMs) have achieved outstanding achievements in abstractive single-document summarization (SDS). However, such benefits may not fully extend to multi-document summarization (MDS), where the handling of cross-document information is more complex. Previous works …