5 papers
Exploiting the Potential of Seq2Seq Models as Robust Few-Shot Learners
Jihyeon Lee, Dain Kim, Doohae Jung +2
In-context learning, which offers substantial advantages over fine-tuning, is predominantly observed in decoder-only models, while encoder-decoder (i.e., seq2seq) models excel in m…
Dense but Efficient VideoQA for Intricate Compositional Reasoning
Jihyeon Lee, Wooyoung Kang, Eun-Sol Kim
It is well known that most of the conventional video question answering (VideoQA) datasets consist of easy questions requiring simple reasoning processes. However, long videos inev…
PePe: Personalized Post-editing Model utilizing User-generated Post-edits
Jihyeon Lee, Taehee Kim, Yunwon Tae +2
Incorporating personal preference is crucial in advanced machine translation tasks. Despite the recent advancement of machine translation, it remains a demanding task to properly r…
Predicting Livelihood Indicators from Community-Generated Street-Level Imagery
Jihyeon Lee, Dylan Grosz, Burak Uzkent +4
Major decisions from governments and other large organizations rely on measurements of the populace's well-being, but making such measurements at a broad scale is expensive and thu…
A Free Lunch in Generating Datasets: Building a VQG and VQA System with Attention and Humans in the Loop
Jihyeon Lee, Sho Arora
Despite their importance in training artificial intelligence systems, large datasets remain challenging to acquire. For example, the ImageNet dataset required fourteen million labe…