Qian Yu

Product Question Intent Detection using Indicative Clause Attention and Adversarial Learning

2018

Due to the provision of QA service in many E-commerce sites, product question understanding becomes important. Product questions have different characteristics from traditional questions in that they are long and verbose as well as associated …

Straggler Mitigation in Distributed Matrix Multiplication: Fundamental Limits and Optimal Coding

2018

Consider massive matrix multiplication, a problem that underlies many data analytic applications, in a large-scale distributed system comprising a group of workers. We target the stragglers' delay performance bottleneck, which is due to the unpredictable …

Feature Decomposition for Reducing Negative Transfer: A Novel Multi-task Learning Method for Recommender System

2023 · arXiv (Cornell University)

In recent years, thanks to the rapid development of deep learning (DL), DL-based multi-task learning (MTL) has made significant progress, and it has been successfully applied to recommendation systems (RS). However, in a recommender system, …

Experimental demonstration of a photonic reservoir computing system based on Fabry Perot laser for multiple tasks processing

2024 · Nanophotonics

Photonic reservoir computing (RC) is a simple and efficient neuromorphic computing framework for human cortical circuits, which is featured with fast training speed and low training cost. Photonic time delay RC, as a simple hardware …

Short-term prediction for chaotic time series based on photonic reservoir computing using VCSEL with a feedback loop

2024 · Photonics Research

Chaos, occurring in a deterministic system, has permeated various fields such as mathematics, physics, and life science. Consequently, the prediction of chaotic time series has received widespread attention and made significant progress. However, many problems, …

CBLN: A User Behavior Prediction Model Considering Content Correlation

2024

The core of user behavior prediction is Click-through Rate (CTR) prediction, which requires deep analysis of user actions such as clicks and browse. It is crucial to model user behavior sequences, content attributes, and user …

Enhancing Auto-regressive Chain-of-Thought through Loop-Aligned Reasoning

2025 · arXiv (Cornell University)

Chain-of-Thought (CoT) prompting has emerged as a powerful technique for enhancing language model's reasoning capabilities. However, generating long and correct CoT trajectories is challenging. Recent studies have demonstrated that Looped Transformers possess remarkable length generalization …