Qing Li

Forum topic detection based on hierarchical clustering

2016

Forum has become one of the main platforms for people to express their personal point of view, with a lot of information surging in the forum everyday. How to detect automatically a forum topic among …

An Efficient Implementation of Track‐Oriented Multiple Hypothesis Tracker Using Graphical Model Approaches

2017 · Mathematical Problems in Engineering

The multiple hypothesis tracker (MHT) is currently the preferred method for addressing data association problem in multitarget tracking (MTT) application. MHT seeks the most likely global hypothesis by enumerating all possible associations over time, which …

Development of Integrated Geotechnical Safety Monitoring System

2019 · 2019 3rd International Conference on Electronic Information Technology and Computer Engineering (EITCE)

This paper proposes a geological disaster monitoring system based on data fusion algorithm. In a monitoring system consisting of multiple sensors, the target is monitored at the same sampling rate at the same time, and …

Conditional Causal Relationships between Emotions and Causes in Texts

2020

The causal relationships between emotions and causes in text have recently received a lot of attention. Most of the existing works focus on the extraction of the causally related clauses from documents. However, none of …

Learning by Fixing: Solving Math Word Problems with Weak Supervision

2020 · arXiv (Cornell University)

Previous neural solvers of math word problems (MWPs) are learned with full supervision and fail to generate diverse solutions. In this paper, we address this issue by introducing a \textit{weakly-supervised} paradigm for learning MWPs. Our …

A Community of Practice Approach to Integrating Professional Skills Training with Graduate Thesis Research

2024

Background. It is well recognized that current graduate education is too narrowly focused on thesis research. Graduate students have a strong desire to gain skills for their future career success beyond thesis research. This obvious …

Pareto Optimization for Active Learning under Out-of-Distribution Data Scenarios

2022 · arXiv (Cornell University)

Pool-based Active Learning (AL) has achieved great success in minimizing labeling cost by sequentially selecting informative unlabeled samples from a large unlabeled data pool and querying their labels from oracle/annotators. However, existing AL sampling strategies …

Integrated Local and Global Information for Health Risk Prediction Model

2023

Electronic health record (EHR) data has been widely used in health risk prediction models, and it has an important preventive and intervention role in healthcare. Existing approaches typically regard EHR data in a monolayer observational …

Experimental Realization of Criticality-Enhanced Global Quantum Sensing via Non-Equilibrium Dynamics

2025 · arXiv (Cornell University)

Quantum critical systems offer promising advancements in quantum sensing and metrology, yet face limitations like critical slowing down and a restricted criticality-enhanced region. Here, we introduce a critical sensing scheme that mitigate critical slowing down …

Generating on Generated: An Approach Towards Self-Evolving Diffusion Models

2025 · arXiv (Cornell University)

Recursive Self-Improvement (RSI) enables intelligence systems to autonomously refine their capabilities. This paper explores the application of RSI in text-to-image diffusion models, addressing the challenge of training collapse caused by synthetic data. We identify two …

Exposing Numeracy Gaps: A Benchmark to Evaluate Fundamental Numerical Abilities in Large Language Models

2025

Haoyang Li, Xuejia Chen, Zhanchao Xu, Darian Li, Nicole Hu, Fei Teng, Yiming Li, Luyu Qiu, Chen Jason Zhang, Li Qing, Lei Chen. Findings of the Association for Computational Linguistics: ACL 2025. 2025.

CoQuIR: A Comprehensive Benchmark for Code Quality-Aware Information Retrieval

2026

Jiahui Geng, Fengyu Cai, Shaobo Cui, Qing Li, Liangwei Chen, Chenyang Lyu, Haonan Li, Derui Zhu, Alexander Pretschner, Heinz Koeppl, Fakhri Karray. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume …

ExpStar: Towards Automatic Commentary Generation for Multi-discipline Scientific Experiments

2025

Experiment commentary is crucial in describing the experimental procedures, delving into underlying scientific principles, and incorporating content-related safety guidelines. In practice, human teachers rely heavily on subject-specific expertise and invest significant time preparing such commentary. …

Graph Neural Networks for Social Recommendation

2019

In recent years, Graph Neural Networks (GNNs), which can naturally integrate node information and topological structure, have been demonstrated to be powerful in learning on graph data. These advantages of GNNs provide great potential to …

Deep social collaborative filtering

2019

Recommender systems are crucial to alleviate the information overload problem in online worlds. Most of the modern recommender systems capture users' preference towards items via their interactions based on collaborative filtering techniques. In addition to …

A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models

2024

As one of the most advanced techniques in AI, Retrieval-Augmented Generation (RAG) can offer reliable and up-to-date external knowledge, providing huge convenience for numerous tasks. Particularly in the era of AI-Generated Content (AIGC), the powerful …