Papers by Kumara Kahatapitiya

2 papers
Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA (2026.eacl-long)

Copied to clipboard

Challenge: Recent studies leverage large language models (LLMs) in LVQA benchmarks, achieving exceptional performance while relying on vision language models to convert all visual content into natural language.
Approach: They propose a modular and training-free framework that leverages large language models to generate a small subset of informative frames tailored to each question.
Outcome: The proposed framework achieves state-of-the-art performance among similar models across four benchmark LVQA datasets: EgoSchema, NExT-QA, IntentQA, VideoMME.
Language Repository for Long Video Understanding (2025.findings-acl)

Copied to clipboard

Challenge: Language-based learning models (LLMs) support long context-lengths but their effectiveness in handling long-term information gradually declines with input length.
Approach: They propose a Language Repository (LangRepo) that maintains concise and structured information as an interpretable representation.
Outcome: The proposed framework is evaluated on zero-shot visual question-answering benchmarks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations