arxiv:2508.17334
Abhirama Subramanyam
abhiram4572
ยท
AI & ML interests
Multimodal deep learning
Recent Activity
authored
a paper
9 days ago
Visual Text Matters: Improving Text-KVQA with Visual Text Entity
Knowledge-aware Large Multimodal Assistant
authored
a paper
9 days ago
Answer Mining from a Pool of Images: Towards Retrieval-Based Visual
Question Answering
authored
a paper
9 days ago
COFAR: Commonsense and Factual Reasoning in Image Search
Organizations
models
0
None public yet
datasets
0
None public yet