4 citations · 7 across the 12 of their papers we have counts for
13 papers
Virtual Encoders in Multimodal Transformers
Katsuya Ogata, Yuta Nakashima
Multimodal language models traditionally rely on dedicated perceptual encoders to construct task-usable representations. More integrated architectures have recently emerged, which…
MEDit-Bench: A Dataset for Evaluating Message-Driven Narrative Video Editing
Katsuya Ogata, Zongshang Pang, Mayu Otani +1
Video editing is fundamentally message-driven: even from the same source footage, the selected shots change depending on the narrative the editor wishes to convey. Benchmarks for a…
ANCHOR: An External LLM-Driven Supervisory Module Facilitating Healthy Evolution in Self-Evolving Systems
Dianxing Shi, Bowen Wang, Junqi He +2
Self-evolving agents improve through continual self-play and self-generated learning signals, but their internally generated tasks and verifier signals provide limited coverage of…
PANICL: Mitigating Over-Reliance on Single Prompt in Visual In-Context Learning
Jiahao Zhang, Bowen Wang, Hong Liu +2
Visual In-Context Learning (VICL) uses input-output image pairs, referred to as in-context pairs (or examples), as prompts alongside query images to guide models in performing dive…
Taming the Untamed: Graph-Based Knowledge Retrieval and Reasoning for MLLMs to Conquer the Unknown
Bowen Wang, Zhouqiang Jiang, Yasuaki Susumu +3
The real value of knowledge lies not just in its accumulation, but in its potential to be harnessed effectively to conquer the unknown. Although recent multimodal large language mo…
E-InMeMo: Enhanced Prompting for Visual In-Context Learning
Jiahao Zhang, Bowen Wang, Hong Liu +3
Large-scale models trained on extensive datasets have become the standard due to their strong generalizability across diverse tasks. In-context learning (ICL), widely used in natur…
VASCAR: Content-Aware Layout Generation via Visual-Aware Self-Correction
Jiahao Zhang, Ryota Yoshihashi, Shunsuke Kitada +2
Large language models (LLMs) have proven effective for layout generation due to their ability to produce structure-description languages, such as HTML or JSON. In this paper, we ar…
ReLayout: Towards Real-World Document Understanding via Layout-enhanced Pre-training
Zhouqiang Jiang, Bowen Wang, Junhao Chen +1
Recent approaches for visually-rich document understanding (VrDU) uses manually annotated semantic groups, where a semantic group encompasses all semantically relevant but not obvi…
Putting People in LLMs' Shoes: Generating Better Answers via Question Rewriter
Junhao Chen, Bowen Wang, Zhouqiang Jiang +1
Large Language Models (LLMs) have demonstrated significant capabilities, particularly in the domain of question answering (QA). However, their effectiveness in QA is often undermin…
DiReCT: Diagnostic Reasoning for Clinical Notes via Large Language Models
Bowen Wang, Jiuyang Chang, Yiming Qian +6
Large language models (LLMs) have recently showcased remarkable capabilities, spanning a wide range of tasks and applications, including those in the medical domain. Models like GP…
Explainable Image Recognition via Enhanced Slot-attention Based Classifier
Bowen Wang, Liangzhi Li, Jiahao Zhang +2
The imperative to comprehend the behaviors of deep learning models is of utmost importance. In this realm, Explainable Artificial Intelligence (XAI) has emerged as a promising aven…
Instruct Me More! Random Prompting for Visual In-Context Learning
Jiahao Zhang, Bowen Wang, Liangzhi Li +2
Large-scale models trained on extensive datasets, have emerged as the preferred approach due to their high generalizability across various tasks. In-context learning (ICL), a popul…
Improving Facade Parsing with Vision Transformers and Line Integration
Bowen Wang, Jiaxing Zhang, Ran Zhang +3
Facade parsing stands as a pivotal computer vision task with far-reaching applications in areas like architecture, urban planning, and energy efficiency. Despite the recent success…