325 citations · 1.7k across the 55 of their papers we have counts for
59 papers
CodecLM: Aligning Language Models with Tailored Synthetic Data
Zifeng Wang, Chun-Liang Li, Vincent Perot +5
Instruction tuning has emerged as the key in aligning large language models (LLMs) with specific task instructions, thereby mitigating the discrepancy between the next-token predic…
Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs
Jiefeng Chen, Jinsung Yoon, Sayna Ebrahimi +3
Large language models (LLMs) have recently shown great advances in a variety of tasks, including natural language understanding and generation. However, their use in high-stakes de…
TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting
Defu Cao, Furong Jia, Sercan O Arik +4
The past decade has witnessed significant advances in time series modeling with deep learning. While achieving state-of-the-art results, the best-performing architectures vary high…
PAITS: Pretraining and Augmentation for Irregularly-Sampled Time Series
Nicasia Beebe-Wang, Sayna Ebrahimi, Jinsung Yoon +2
Real-world time series data that commonly reflect sequential human behavior are often uniquely irregularly sampled and sparse, with highly nonuniform sampling over time and entitie…
Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Models
Cheng-Yu Hsieh, Si-An Chen, Chun-Liang Li +5
Today, large language models (LLMs) are taught to use new tools by providing a few demonstrations of the tool's usage. Unfortunately, demonstrations are hard to acquire, and can re…
FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extraction
Chen-Yu Lee, Chun-Liang Li, Hao Zhang +13
The recent advent of self-supervised pre-training techniques has led to a surge in the use of multimodal learning in form document understanding. However, existing approaches that…
Better Zero-Shot Reasoning with Self-Adaptive Prompting
Xingchen Wan, Ruoxi Sun, Hanjun Dai +2
Modern large language models (LLMs) have demonstrated impressive capabilities at sophisticated tasks, often through step-by-step reasoning similar to humans. This is made possible…
LANISTR: Multimodal Learning from Structured and Unstructured Data
Sayna Ebrahimi, Sercan O. Arik, Yihe Dong +1
Multimodal large-scale pretraining has shown impressive performance for unstructured data such as language and image. However, a prevalent real-world scenario involves structured d…
Universal Self-Adaptive Prompting
Xingchen Wan, Ruoxi Sun, Hootan Nakhost +4
A hallmark of modern large language models (LLMs) is their impressive general zero-shot and few-shot abilities, often elicited through in-context learning (ICL) via prompting. Howe…
Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes
Cheng-Yu Hsieh, Chun-Liang Li, Chih-Kuan Yeh +6
Deploying large language models (LLMs) is challenging because they are memory inefficient and compute-intensive for practical applications. In reaction, researchers train smaller t…
ASPEST: Bridging the Gap Between Active Learning and Selective Prediction
Jiefeng Chen, Jinsung Yoon, Sayna Ebrahimi +3
Selective prediction aims to learn a reliable model that abstains from making predictions when uncertain. These predictions can then be deferred to humans for further evaluation. A…
TSMixer: An All-MLP Architecture for Time Series Forecasting
Si-An Chen, Chun-Liang Li, Nate Yoder +2
Real-world time-series datasets are often multivariate with complex dynamics. To capture this complexity, high capacity architectures like recurrent- or attention-based sequential…
Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrieval
Kuniaki Saito, Kihyuk Sohn, Xiang Zhang +4
In Composed Image Retrieval (CIR), a user combines a query image with text to describe their intended target. Existing methods rely on supervised learning of CIR models using label…
Neural Spline Search for Quantile Probabilistic Modeling
Ruoxi Sun, Chun-Liang Li, Sercan O. Arik +3
Accurate estimation of output quantiles is crucial in many use cases, where it is desired to model the range of possibility. Modeling target distribution at arbitrary quantile leve…
SPADE: Semi-supervised Anomaly Detection under Distribution Mismatch
Jinsung Yoon, Kihyuk Sohn, Chun-Liang Li +2
Semi-supervised anomaly detection is a common problem, as often the datasets containing anomalies are partially labeled. We propose a canonical framework: Semi-supervised Pseudo-la…
QueryForm: A Simple Zero-shot Form Entity Query Framework
Zifeng Wang, Zizhao Zhang, Jacob Devlin +6
Zero-shot transfer learning for document understanding is a crucial yet under-investigated scenario to help reduce the high cost involved in annotating document entities. We presen…
Invariant Structure Learning for Better Generalization and Causal Explainability
Yunhao Ge, Sercan Ö. Arik, Jinsung Yoon +3
Learning the causal structure behind data is invaluable for improving generalization and obtaining high-quality explanations. We propose a novel framework, Invariant Structure Lear…
Test-Time Adaptation for Visual Document Understanding
Sayna Ebrahimi, Sercan O. Arik, Tomas Pfister
For visual document understanding (VDU), self-supervised pretraining has been shown to successfully generate transferable representations, yet, effective adaptation of such represe…
Interpretable Mixture of Experts
Aya Abdelsalam Ismail, Sercan Ö. Arik, Jinsung Yoon +3
The need for reliable model explanations is prominent for many machine learning applications, particularly for tabular and time-series data as their use cases often involve high-st…
Prefix Conditioning Unifies Language and Label Supervision
Kuniaki Saito, Kihyuk Sohn, Xiang Zhang +4
Image-classification datasets have been used to pretrain image recognition models. Recently, web-scale image-caption datasets have emerged as a source of powerful pretraining alter…
DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning
Zifeng Wang, Zizhao Zhang, Sayna Ebrahimi +8
Continual learning aims to enable a single model to learn a sequence of tasks without catastrophic forgetting. Top-performing methods usually require a rehearsal buffer to store pa…
Learning Instance-Specific Adaptation for Cross-Domain Segmentation
Yuliang Zou, Zizhao Zhang, Chun-Liang Li +3
We propose a test-time adaptation method for cross-domain image segmentation. Our method is simple: Given a new unseen instance at test time, we adapt a pre-trained model by conduc…
FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction
Chen-Yu Lee, Chun-Liang Li, Timothy Dozat +7
Sequence modeling has demonstrated state-of-the-art performance on natural language and document understanding tasks. However, it is challenging to correctly serialize tokens in fo…
Data-Efficient and Interpretable Tabular Anomaly Detection
Chun-Hao Chang, Jinsung Yoon, Sercan Arik +2
Anomaly detection (AD) plays an important role in numerous applications. We focus on two understudied aspects of AD that are critical for integration into real-world applications.…