Abhirama Subramanyam's picture

3 8 1

Abhirama Subramanyam

abhiram4572

·

http://abhiram4572.github.io

AI & ML interests

Multimodal deep learning

Recent Activity

upvoted a paper about 1 month ago

left|,circlearrowright,text{BUS},right|: A Large and Diverse Multimodal Benchmark for evaluating the ability of Vision-Language Models to understand Rebus Puzzles

authored a paper 3 months ago

When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs

upvoted a paper 3 months ago

When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs

View all activity

Organizations

upvoted a paper about 1 month ago

left|,circlearrowright,text{BUS},right|: A Large and Diverse Multimodal Benchmark for evaluating the ability of Vision-Language Models to understand Rebus Puzzles

Paper • 2511.01340 • Published Nov 3 • 12

upvoted 5 papers 3 months ago

When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs

Paper • 2509.16633 • Published Sep 20 • 2

COFAR: Commonsense and Factual Reasoning in Image Search

Paper • 2210.08554 • Published Oct 16, 2022 • 1

Answer Mining from a Pool of Images: Towards Retrieval-Based Visual Question Answering

Paper • 2306.16713 • Published Jun 29, 2023 • 1

Visual Text Matters: Improving Text-KVQA with Visual Text Entity Knowledge-aware Large Multimodal Assistant

Paper • 2410.19144 • Published Oct 24, 2024 • 1

Mind the (Language) Gap: Towards Probing Numerical and Cross-Lingual Limits of LVLMs

Paper • 2508.17334 • Published Aug 24 • 2

upvoted a paper 4 months ago

Audiopedia: Audio QA with Knowledge

Paper • 2412.20619 • Published Dec 29, 2024 • 1

upvoted an article 9 months ago

Article

SmolVLM2: Bringing Video Understanding to Every Device

+4

Feb 20

•

316