Search Results for author: Chi Wang

Found 41 papers, 16 papers with code

Training Language Model Agents without Modifying Language Models

no code implementations17 Feb 2024 Shaokun Zhang, Jieyu Zhang, Jiale Liu, Linxin Song, Chi Wang, Ranjay Krishna, Qingyun Wu

Researchers and practitioners have recently reframed powerful Large Language Models (LLMs) as agents, enabling them to automate complex tasks largely via the use of specialized functions.

Language Modelling

Towards better Human-Agent Alignment: Assessing Task Utility in LLM-Powered Applications

no code implementations14 Feb 2024 Negar Arabzadeh, Julia Kiseleva, Qingyun Wu, Chi Wang, Ahmed Awadallah, Victor Dibia, Adam Fourney, Charles Clarke

The rapid development in the field of Large Language Models (LLMs) has led to a surge in applications that facilitate collaboration among multiple agents to assist humans in their daily tasks.


EcoAssistant: Using LLM Assistant More Affordably and Accurately

1 code implementation3 Oct 2023 Jieyu Zhang, Ranjay Krishna, Ahmed H. Awadallah, Chi Wang

Today, users ask Large language models (LLMs) as assistants to answer queries that require external knowledge; they ask about the weather in a specific city, about stock prices, and even about where specific locations are within their neighborhood.

A Prefrontal Cortex-inspired Architecture for Planning in Large Language Models

no code implementations30 Sep 2023 Taylor Webb, Shanka Subhra Mondal, Chi Wang, Brian Krabach, Ida Momennejad

To address this, we take inspiration from the human brain, in which planning is accomplished via the recurrent interaction of specialized modules in the prefrontal cortex (PFC).

In-Context Learning

Instruction Mining: When Data Mining Meets Large Language Model Finetuning

no code implementations12 Jul 2023 Yihan Cao, Yanbin Kang, Chi Wang, Lichao Sun

Large language models (LLMs) are initially pretrained for broad capabilities and then finetuned with instruction-following datasets to improve their performance in interacting with humans.

Instruction Following Language Modelling +1

An Empirical Study on Challenging Math Problem Solving with GPT-4

1 code implementation2 Jun 2023 Yiran Wu, Feiran Jia, Shaokun Zhang, Hangyu Li, Erkang Zhu, Yue Wang, Yin Tat Lee, Richard Peng, Qingyun Wu, Chi Wang

Employing Large Language Models (LLMs) to address mathematical problems is an intriguing research endeavor, considering the abundance of math problems expressed in natural language across numerous science and engineering fields.

Elementary Mathematics Math

HyperTime: Hyperparameter Optimization for Combating Temporal Distribution Shifts

no code implementations28 May 2023 Shaokun Zhang, Yiran Wu, Zhonghua Zheng, Qingyun Wu, Chi Wang

In this work, we propose a hyperparameter optimization method named \emph{HyperTime} to find hyperparameters robust to potential temporal distribution shifts in the unseen test data.

Hyperparameter Optimization Philosophy +1

Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference

3 code implementations8 Mar 2023 Chi Wang, Susan Xueqing Liu, Ahmed H. Awadallah

Large Language Models (LLMs) have sparked significant interest in their generative capabilities, leading to the development of various commercial applications.

Hyperparameter Optimization Language Modelling +2

ACE: Adaptive Constraint-aware Early Stopping in Hyperparameter Optimization

no code implementations4 Aug 2022 Yi-Wei Chen, Chi Wang, Amin Saied, Rui Zhuang

Deploying machine learning models requires high model quality and needs to comply with application constraints.

Fairness Hyperparameter Optimization

Mining Robust Default Configurations for Resource-constrained AutoML

no code implementations20 Feb 2022 Moe Kayali, Chi Wang

Automatic machine learning (AutoML) is a key enabler of the mass deployment of the next generation of machine learning systems.

AutoML BIG-bench Machine Learning

Bounding the Last Mile: Efficient Learned String Indexing

no code implementations29 Nov 2021 Benjamin Spector, Andreas Kipf, Kapil Vaidya, Chi Wang, Umar Farooq Minhas, Tim Kraska

RSS achieves this by using the minimal string prefix to sufficiently distinguish the data unlike most learned approaches which index the entire string.

FairAutoML: Embracing Unfairness Mitigation in AutoML

no code implementations11 Nov 2021 Qingyun Wu, Chi Wang

In this work, we propose an Automated Machine Learning (AutoML) system to search for models not only with good prediction accuracy but also fair.

AutoML BIG-bench Machine Learning +1

Geometry Attention Transformer with Position-aware LSTMs for Image Captioning

1 code implementation1 Oct 2021 Chi Wang, Yulin Shen, Luping Ji

In recent years, transformer structures have been widely applied in image captioning with impressive performance.

Image Captioning Position

An Empirical Study on Hyperparameter Optimization for Fine-Tuning Pre-trained Language Models

1 code implementation ACL 2021 Xueqing Liu, Chi Wang

We find that using the same time budget, HPO often fails to outperform grid search due to two reasons: insufficient time budget and overfitting.

Hyperparameter Optimization

ChaCha for Online AutoML

1 code implementation9 Jun 2021 Qingyun Wu, Chi Wang, John Langford, Paul Mineiro, Marco Rossi

We propose the ChaCha (Champion-Challengers) algorithm for making an online choice of hyperparameters in online learning settings.

AutoML Scheduling

Attention-guided Temporally Coherent Video Object Matting

1 code implementation24 May 2021 Yunke Zhang, Chi Wang, Miaomiao Cui, Peiran Ren, Xuansong Xie, Xian-Sheng Hua, Hujun Bao, QiXing Huang, Weiwei Xu

Experimental results show that our method can generate high-quality alpha mattes for various videos featuring appearance change, occlusion, and fast motion.

Image Matting Object +4


no code implementations ICLR 2021 Chi Wang, Qingyun Wu, Silu Huang, Amin Saied

We study the problem of using low cost to search for hyperparameter configurations in a large search space with heterogeneous evaluation cost and model quality.

Hyperparameter Optimization

DynaTune: Dynamic Tensor Program Optimization in Deep Neural Network Compilation

no code implementations ICLR 2021 Minjia Zhang, Menghao Li, Chi Wang, Mingqin Li

Recently, the DL compiler, together with Learning to Compile has proven to be a powerful technique for optimizing deep learning models.

Decision Making Uncertainty Quantification

AdaTune: Adaptive Tensor Program Compilation Made Efficient

no code implementations NeurIPS 2020 Menghao Li, Minjia Zhang, Chi Wang, Mingqin Li

Deep learning models are computationally intense, and implementations often have to be highly optimized by experts or hardware vendors to be usable in practice.

A Matrix Chernoff Bound for Markov Chains and Its Application to Co-occurrence Matrices

no code implementations NeurIPS 2020 Jiezhong Qiu, Chi Wang, Ben Liao, Richard Peng, Jie Tang

Our result gives the first bound on the convergence rate of the co-occurrence matrix and the first sample complexity analysis in graph representation learning.

Graph Learning Graph Representation Learning

Faster Graph Embeddings via Coarsening

1 code implementation ICML 2020 Matthew Fahrbach, Gramoz Goranci, Richard Peng, Sushant Sachdeva, Chi Wang

As computing Schur complements is expensive, we give a nearly-linear time algorithm that generates a coarsened graph on the relevant vertices that provably matches the Schur complement in expectation in each iteration.

Link Prediction Node Classification

Qd-tree: Learning Data Layouts for Big Data Analytics

no code implementations22 Apr 2020 Zongheng Yang, Badrish Chandramouli, Chi Wang, Johannes Gehrke, Yi-Nan Li, Umar Farooq Minhas, Per-Åke Larson, Donald Kossmann, Rajeev Acharya

For a given workload, however, such techniques are unable to optimize for the important metric of the number of blocks accessed by a query.


FLAML: A Fast and Lightweight AutoML Library

2 code implementations12 Nov 2019 Chi Wang, Qingyun Wu, Markus Weimer, Erkang Zhu

We study the problem of using low computational cost to automate the choices of learners and hyperparameters for an ad-hoc training dataset and error metric, by conducting trials of different configurations on the given training data.

Hyperparameter Optimization

NetSMF: Large-Scale Network Embedding as Sparse Matrix Factorization

1 code implementation26 Jun 2019 Jiezhong Qiu, Yuxiao Dong, Hao Ma, Jian Li, Chi Wang, Kuansan Wang, Jie Tang

Previous research shows that 1) popular network embedding benchmarks, such as DeepWalk, are in essence implicitly factorizing a matrix with a closed form, and 2)the explicit factorization of such matrix generates more powerful embeddings than existing methods.

Network Embedding

ALEX: An Updatable Adaptive Learned Index

no code implementations21 May 2019 Jialin Ding, Umar Farooq Minhas, JIA YU, Chi Wang, Jaeyoung Do, Yi-Nan Li, Hantian Zhang, Badrish Chandramouli, Johannes Gehrke, Donald Kossmann, David Lomet, Tim Kraska

The original work by Kraska et al. shows that a learned index beats a B+Tree by a factor of up to three in search time and by an order of magnitude in memory footprint.

ABC: Efficient Selection of Machine Learning Configuration on Large Dataset

no code implementations8 Nov 2018 Silu Huang, Chi Wang, Bolin Ding, Surajit Chaudhuri

A machine learning configuration refers to a combination of preprocessor, learner, and hyperparameters.

BIG-bench Machine Learning Test

Identifying Outlier Arms in Multi-Armed Bandit

no code implementations NeurIPS 2017 Honglei Zhuang, Chi Wang, Yifan Wang

Outlier detection is a powerful method to narrow down the attention to a few objects after the data for them are collected.

Outlier Detection

Identifying Semantically Deviating Outlier Documents

no code implementations EMNLP 2017 Honglei Zhuang, Chi Wang, Fangbo Tao, Lance Kaplan, Jiawei Han

A document outlier is a document that substantially deviates in semantics from the majority ones in a corpus.

Outlier Detection

Scalable Topical Phrase Mining from Text Corpora

no code implementations24 Jun 2014 Ahmed El-Kishky, Yanglei Song, Chi Wang, Clare Voss, Jiawei Han

Our solution combines a novel phrase mining framework to segment a document into single and multi-word phrases, and a new topic model that operates on the induced document partition.

Topic Models

Scalable and Robust Construction of Topical Hierarchies

no code implementations13 Mar 2014 Chi Wang, Xueqing Liu, Yanglei Song, Jiawei Han

Automated generation of high-quality topical hierarchies for a text collection is a dream problem in knowledge engineering with many valuable applications.

Cannot find the paper you are looking for? You can Submit a new open access paper.