Enhancing Instructor-Student and Student-Student Interactions with Mobile Interfaces and Summarization

no code implementations • NAACL 2015 • Wencan Luo, Xiangmin Fan, Muhsin Menekse, Jingtao Wang, Diane Litman

Clustering

An Interactive Analytic Tool for Peer-Review Exploration

no code implementations • WS 2012 • Wenting Xiong, Diane Litman, Jingtao Wang, Christian Schunn

Reinforcement Learning Driven Heuristic Optimization

no code implementations • 16 Jun 2019 • Qingpeng Cai, Will Hang, Azalia Mirhoseini, George Tucker, Jingtao Wang, Wei Wei

In this paper, we introduce a novel framework to generate better initial solutions for heuristic algorithms using reinforcement learning (RL), named RLHO.

Combinatorial Optimization reinforcement-learning +1

Business Metric-Aware Forecasting for Inventory Management

no code implementations • 24 Aug 2023 • Helen Zhou, Sercan O. Arik, Jingtao Wang

We explore a wide range of plausible cost trade-off scenarios, and empirically demonstrate that end-to-end optimization often outperforms optimization of standard business-agnostic forecasting metrics (by up to 45. 7% for a simple scaling model, and up to 54. 0% for an LSTM encoder-decoder model).

Management Time Series

SSF: Accelerating Training of Spiking Neural Networks with Stabilized Spiking Flow

no code implementations • ICCV 2023 • Jingtao Wang, Zengjie Song, Yuxi Wang, Jun Xiao, Yuran Yang, Shuqi Mei, Zhaoxiang Zhang

Surrogate gradient (SG) is one of the most effective approaches for training spiking neural networks (SNNs).