← Search

Seokwon Song

3 accepted papers

2026

MAVIS: A Benchmark for Multimodal Source Attribution in Long-form Visual Question Answering

AAAI 2026technical

Source attribution aims to enhance the reliability of AI-generated answers by including references for each statement, helping users validate the provided answers. However, existing work has primarily focused on text-only scenario and largely overlooked the role of multimodality. We introduce MAVIS,

Cited by 0SourcePDFScholar
2025

Is a Peeled Apple Still Red? Evaluating LLMs’ Ability for Conceptual Combination with Property Type

NAACL 2025long

Conceptual combination is a cognitive process that merges basic concepts, enabling the creation of complex expressions. During this process, the properties of combination (e.g., the whiteness of a peeled apple) can be inherited from basic concepts, newly emerge, or be canceled. However, previous stu…

2023

Read-only Prompt Optimization for Vision-Language Few-shot Learning

ICCV 2023poster

In recent years, prompt tuning has proven effective in adapting pre-trained vision-language models to down- stream tasks. These methods aim to adapt the pre-trained models by introducing learnable prompts while keeping pre- trained weights frozen. However, learnable prompts can affect the internal r…

Cited by 64PDFcodeScholar