Picture for Junjia Guo

Junjia Guo

VERIFY: A Benchmark of Visual Explanation and Reasoning for Investigating Multimodal Reasoning Fidelity

Add code
Mar 14, 2025
Viaarxiv icon

Generative AI for Cel-Animation: A Survey

Add code
Jan 08, 2025
Viaarxiv icon

Unveiling Visual Perception in Language Models: An Attention Head Analysis Approach

Add code
Dec 24, 2024
Viaarxiv icon

VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?

Add code
Nov 19, 2024
Figure 1 for VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?
Figure 2 for VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?
Figure 3 for VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?
Figure 4 for VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?
Viaarxiv icon