1 citations · 1 across the 4 of their papers we have counts for
6 papers
Attention Sinks in VLMs Are Borrowed, Not Seen
Dengjia Zhang, Alexander Martin, Pengyu Yan +6
We study how to detect and mitigate visual attention sinks in vision-language models (VLMs). Visual attention sinks are image tokens that absorb a large share of attention over the…
Back2Struct: Making Structured Images Editable Again
Pengyu Yan, Yixin Wu, Yunjie Tian +1
Structured images, such as diagrams, charts, and flowcharts, are inherently symbolic and can be compactly represented in an editable format, yet in practice, they are often rendere…
TRACE: Evidence Grounding-Guided Multi-Video Event Understanding and Claim Generation
Pengyu Yan, Akhil Gorugantu, Mahesh Bhosale +3
Multi-video event understanding demands models that can locate and attribute query-relevant evidence scattered across long, heterogeneous video corpora. Existing large vision-langu…
CRAFT: Critic-Refined Adaptive Key-Frame Targeting for Multimodal Video Question Answering
Mahesh Bhosale, Abdul Wasi, Vishvesh Trivedi +3
Grounded multi-video question answering over real-world news events requires systems to surface query-relevant evidence across heterogeneous video archives while attributing every…
Artemis: Towards Referential Understanding in Complex Videos
Jihao Qiu, Yuan Zhang, Xi Tang +6
Videos carry rich visual information including object description, action, interaction, etc., but the existing multimodal large language models (MLLMs) fell short in referential un…
ChartReformer: Natural Language-Driven Chart Image Editing
Pengyu Yan, Mahesh Bhosale, Jay Lal +2
Chart visualizations are essential for data interpretation and communication; however, most charts are only accessible in image format and lack the corresponding data tables and su…