Search Results - "Chen, Xiusi"
-
1
Influence of Structural Parameters on Mechanical Properties of Triply Periodic Minimal Surface Structure
Published in Metals (Basel ) (01-01-2023)“…Titanium alloy is widely used in aerospace and other fields due to its low density, high specific strength, corrosion resistance, and other advantages. With…”
Get full text
Journal Article -
2
One Step Towards Autonomous AI Agent: Reasoning, Alignment and Planning
Published 01-01-2024“…The recent development of artificial intelligence (AI) has facilitated the prosperity of foundation models, such as large language models (LLMs) and vision…”
Get full text
Dissertation -
3
A Multi-View Multi-Task Learning Framework for Multi-Variate Time Series Forecasting
Published in IEEE transactions on knowledge and data engineering (01-08-2023)“…Multi-variate time series (MTS) data is a ubiquitous class of data abstraction in the real world. Any instance of MTS is generated from a hybrid dynamical…”
Get full text
Journal Article -
4
Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting
Published in IEEE transactions on knowledge and data engineering (01-08-2024)“…Multivariate time-series (MTS) forecasting is a paramount and fundamental problem in many real-world applications. The core issue in MTS forecasting is how to…”
Get full text
Journal Article -
5
COVID-19 Surveiller: toward a robust and effective pandemic surveillance system basedon social media mining
Published in Philosophical transactions of the Royal Society of London. Series A: Mathematical, physical, and engineering sciences (10-01-2022)“…The outbreak of the novel coronavirus, COVID-19, has become one of the most severe pandemics in human history. In this paper, we propose to leverage social…”
Get full text
Journal Article -
6
How the experience of California wildfires shape Twitter climate change framings
Published in Climatic change (2024)“…Climate communication scientists search for effective message strategies to engage the ambivalent public in support of climate advocacy. The personal…”
Get full text
Journal Article -
7
COVID-19 Surveiller: toward a robust and effective pandemic surveillance system based on social media mining
Published in Philosophical transactions of the Royal Society of London. Series A: Mathematical, physical, and engineering sciences (22-11-2021)“…The outbreak of the novel coronavirus, COVID-19, has become one of the most severe pandemics in human history. In this paper, we propose to leverage social…”
Get full text
Journal Article -
8
Large Scale Knowledge Washing
Published 26-05-2024“…Large language models show impressive abilities in memorizing world knowledge, which leads to concerns regarding memorization of private information, toxic or…”
Get full text
Journal Article -
9
SemiEvol: Semi-supervised Fine-tuning for LLM Adaptation
Published 17-10-2024“…Supervised fine-tuning (SFT) is crucial in adapting large language models (LLMs) to a specific domain or task. However, only a limited amount of labeled data…”
Get full text
Journal Article -
10
Self-Updatable Large Language Models with Parameter Integration
Published 01-10-2024“…Despite significant advancements in large language models (LLMs), the rapid and frequent integration of small-scale experiences, such as interactions with…”
Get full text
Journal Article -
11
Strategist: Learning Strategic Skills by LLMs via Bi-Level Tree Search
Published 20-08-2024“…In this paper, we propose a new method STRATEGIST that utilizes LLMs to acquire new skills for playing multi-agent games through a self-improvement process…”
Get full text
Journal Article -
12
A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery
Published 16-06-2024“…In many scientific fields, large language models (LLMs) have revolutionized the way text and other modalities of data (e.g., molecules and proteins) are…”
Get full text
Journal Article -
13
IterAlign: Iterative Constitutional Alignment of Large Language Models
Published 27-03-2024“…With the rapid development of large language models (LLMs), aligning LLMs with human values and societal norms to ensure their reliability and safety has…”
Get full text
Journal Article -
14
Bridging Language and Items for Retrieval and Recommendation
Published 06-03-2024“…This paper introduces BLaIR, a series of pretrained sentence embedding models specialized for recommendation scenarios. BLaIR is trained to learn correlations…”
Get full text
Journal Article -
15
TinyLLM: Learning a Small Student from Multiple Large Language Models
Published 07-02-2024“…Transferring the reasoning capability from stronger large language models (LLMs) to smaller ones has been quite appealing, as smaller LLMs are more flexible to…”
Get full text
Journal Article -
16
TPD: Enhancing Student Language Model Reasoning via Principle Discovery and Guidance
Published 24-01-2024“…Large Language Models (LLMs) have recently showcased remarkable reasoning abilities. However, larger models often surpass their smaller counterparts in…”
Get full text
Journal Article -
17
Chain-of-Factors Paper-Reviewer Matching
Published 22-10-2023“…With the rapid increase in paper submissions to academic conferences, the need for automated and accurate paper-reviewer matching is more critical than ever…”
Get full text
Journal Article -
18
MinPrompt: Graph-based Minimal Prompt Data Augmentation for Few-shot Question Answering
Published 08-10-2023“…Recent advances in few-shot question answering (QA) mostly rely on the power of pre-trained large language models (LLMs) and fine-tuning in specific settings…”
Get full text
Journal Article -
19
MotifClass: Weakly Supervised Text Classification with Higher-order Metadata Information
Published 07-11-2021“…We study the problem of weakly supervised text classification, which aims to classify text documents into a set of pre-defined categories with category surface…”
Get full text
Journal Article -
20
Weakly Supervised Multi-Label Classification of Full-Text Scientific Papers
Published 24-06-2023“…Instead of relying on human-annotated training samples to build a classifier, weakly supervised scientific paper classification aims to classify papers only…”
Get full text
Journal Article