In this work we present a new method of black-box optimization and constraint satisfaction. Existing algorithms that have attempted to solve this problem are unable to consider multiple modes, and are not able to adapt to changes in environment dynamics. To address these issues, we developed a modified Cross-Entropy Method (CEM) that uses a masked auto-regressive neural network for modeling uniform distributions over the solution space. We train the model using maximum entropy policy gradient methods from Reinforcement Learning. Our algorithm is able to express complicated solution spaces, thus allowing it to track a variety of different solution regions. We empirically compare our algorithm with variations of CEM, including one with a Gaussian prior with fixed variance, and demonstrate better performance in terms of: number of diverse solutions, better mode discovery in multi-modal problems, and better sample efficiency in certain cases.
Cross-modal Affinity-aligned Multimodal Learning Analytics for Predicting Student Collaboration Satisfaction in Game-Based Learning
Institute of Education, National Cheng Kung University（国立成功大学教育研究所）；Institute of Intelligent System, National Yang Ming Chiao Tung University（阳明交通大学智能系统研究所）；Department of Computer Science, University at Albany, State University of New York（纽约州立大学水牛城分校计算机科学系）
The Promise of RL for Autoregressive Image Editing
Mila – Quebec AI Institute（魁北克AI研究所）；Université de Montréal（蒙特利尔大学）；McGill University（麦吉尔大学）；École de Technologie Supérieure (ETS)（高等技术学院）；Polytechnique Montréal（蒙特利尔理工学院）；ServiceNow（ServiceNow公司）；Canada CIFAR AI Chair（加拿大CIFAR人工智能主席）
CoC: Chain-of-Cancer based on Cross-Modal Autoregressive Traction for Survival Prediction
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Xi'an Jiaotong University（西安交通大学）；The Hong Kong Polytechnic University（香港理工大学）；The Hong Kong University of Science and Technology（香港科技大学）
CAAT-EHR: Cross-Attentional Autoregressive Transformer for Multimodal Electronic Health Record Embeddings
Department of Computer Science and Engineering, University of North Texas（计算机科学与工程系，北卡罗来纳大学达顿分校）；BioDiscovery Institute, University of North Texas（生物发现研究所，北卡罗来纳大学达顿分校）；Center for Computational Life Sciences, University of North Texas（计算生命科学中心，北卡罗来纳大学达顿分校）
There has been a recent explosion of computer vision models which perform many tasks and are composed of an image encoder (usually a ViT) and an autoregressive decoder (usually a Transformer). However, most of this work simply presents one system and its results, leaving many questions regarding design decisions and trade-offs of such systems unanswered. In this work, we aim to provide such answers. We take a close look at autoregressive decoders for multi-task learning in multimodal computer vision, including classification, captioning, visual question answering, and optical character recogni…
AsyncCouple-Flow: Asynchronous Cross-Modal Coupling and Flow Matching for Spatio-Temporal Forecasting
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Emory University（埃默里大学）；University of California, Berkeley（加州大学伯克利分校）；Yale University（耶鲁大学）；Stevens Institute of Technology（史蒂文斯理工学院）；City University of New York（纽约城市大学）
Session-based recommendation is an important task for e-commerce services, where a large number of users browse anonymously or may have very distinct interests for different sessions. In this paper we present one of the winning solutions for the Recommendation task of the SIGIR 2021 Workshop on E-commerce Data Challenge. Our solution was inspired by NLP techniques and consists of an ensemble of two Transformer architectures - Transformer-XL and XLNet - trained with autoregressive and autoencoding approaches. To leverage most of the rich dataset made available for the competition, we describe h…
