← Search

Zhifan Feng

2 accepted papers

2025

TableDreamer: Progressive and Weakness-guided Data Synthesis from Scratch for Table Instruction Tuning

ACL 2025finding

Despite the commendable progress of recent LLM-based data synthesis methods, they face two limitations in generating table instruction tuning data. First, they can not thoroughly explore the vast input space of table understanding tasks, leading to limited data diversity. Second, they ignore the wea…

2022

Dynamic Multistep Reasoning based on Video Scene Graph for Video Question Answering

NAACL 2022long

Existing video question answering (video QA) models lack the capacity for deep video understanding and flexible multistep reasoning. We propose for video QA a novel model which performs dynamic multistep reasoning between questions and videos. It creates video semantic representation based on the vi…

Cited by 12SourcePDFScholar