Tackling Vision Language Tasks Through Learning Inner Monologues
Paper
•
2308.09970
•
Published
Diji Yang
dyang39
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 10 hours ago
GenIR: Generative Visual Feedback for Mental Image Retrieval
upvoted
a
paper
about 10 hours ago
GRIT: Teaching MLLMs to Think with Images
upvoted
a
paper
about 10 hours ago
Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the
Robustness of RAG Against Misleading Retrievals
Organizations
authored
5
papers
7 months ago
Right this way: Can VLMs Guide Us to See More to Answer Questions?
Paper
•
2411.00394
•
Published
Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievals
Paper
•
2502.16101
•
Published
•
1
GRIT: Teaching MLLMs to Think with Images
Paper
•
2505.15879
•
Published
•
13
IM-RAG: Multi-Round Retrieval-Augmented Generation Through Learning Inner Monologues
Paper
•
2405.13021
•
Published
•
2