15 citations · 15 across the 4 of their papers we have counts for
4 papers
MANTA: Cross-Modal Semantic Alignment and Information-Theoretic Optimization for Long-form Multimodal Understanding
Ziqi Zhong, Daniel Tang
While multi-modal learning has advanced significantly, current approaches often treat modalities separately, creating inconsistencies in representation and reasoning. We introduce…
DreamFactory: Pioneering Multi-Scene Long Video Generation with a Multi-Agent Framework
Zhifei Xie, Daniel Tang, Dingwei Tan +3
Current video generation models excel at creating short, realistic clips, but struggle with longer, multi-scene videos. We introduce \texttt{DreamFactory}, an LLM-based framework t…
Revisiting Code Similarity Evaluation with Abstract Syntax Tree Edit Distance
Yewei Song, Cedric Lothritz, Daniel Tang +2
This paper revisits recent code similarity evaluation metrics, particularly focusing on the application of Abstract Syntax Tree (AST) editing distance in diverse programming langua…
VisLingInstruct: Elevating Zero-Shot Learning in Multi-Modal Language Models with Autonomous Instruction Optimization
Dongsheng Zhu, Xunzhu Tang, Weidong Han +5
This paper presents VisLingInstruct, a novel approach to advancing Multi-Modal Language Models (MMLMs) in zero-shot learning. Current MMLMs show impressive zero-shot abilities in m…