Yintao Tai — accepted AI-conference papers

2024

PIXAR: Auto-Regressive Language Modeling in Pixel Space

Yintao Tai, Xiyang Liao, Alessandro Suglia, Antonio Vergari

ACL 2024findings

Recent work showed the possibility of building open-vocabulary large language models (LLMs) that directly operate on pixel representations. These models are implemented as autoencoders that reconstruct masked patches of rendered text.However, these pixel-based LLMs are limited to discriminative task…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗

2023

Learning to Simulate Natural Language Feedback for Interactive Semantic Parsing

Hao Yan, Saurabh Srivastava, Yintao Tai, Sida I. Wang, Wen-tau Yih, Ziyu Yao

ACL 2023long

Interactive semantic parsing based on natural language (NL) feedback, where users provide feedback to correct the parser mistakes, has emerged as a more practical scenario than the traditional one-shot semantic parsing. However, prior work has heavily relied on human-annotated feedback data to train…

Cited by 18 Source ↗PDF ↗code ↗Scholar ↗