G. Thomas Hudson — accepted AI-conference papers

2025

Everything is a Video: Unifying Modalities through Next-Frame Prediction

G. Thomas Hudson, Dean Slack, Thomas Winterbottom, Jamie Sterling, Chenghao Xiao, Junjie Shentu +1

ICCV 2025poster

Multimodal learning, which involves integrating information from various modalities such as text, images, audio, and video, is pivotal for numerous complex tasks like visual question answering, cross-modal retrieval, and caption generation. Traditional approaches rely on modality-specific encoders a…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2023

Length is a Curse and a Blessing for Document-level Semantics

Chenghao Xiao, Yizhi LI, G Thomas Hudson, Chenghua Lin, Noura Al Moubayed

EMNLP 2023long main

In recent years, contrastive learning (CL) has been extensively utilized to recover sentence and document-level encoding capability from pre-trained language models. In this work, we question the length generalizability of CL-based models, i.e., their vulnerability towards length-induced semantic sh…

Cited by 0 Source ↗code ↗Scholar ↗