← authors · overview

• MAPL: Parameter-Efficient Adaptation of Unimodal Pre-Trained Models for Vision-Language Few-Shot Prompting
  2022 · 7 citations
• Investigating Prompting Techniques for Zero- and Few-Shot Visual Question Answering
  2023 · 5 citations
• MoqaGPT : Zero-Shot Multi-modal Open-domain Question Answering with Large Language Model
  2023 · 4 citations
• Reassessing Evaluation Practices in Visual Question Answering: A Case Study on Out-of-Distribution Generalization
  2022 · 3 citations
• Discovering Failure Modes in Vision-Language Models using RL
  2026
• Learning What Matters: Prioritized Concept Learning Via Relative Error-driven Sample Selection
  2025
• Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding
  2023
• Decompose and Compare Consistency: Measuring VLMs' Answer Reliability via Task-Decomposition Consistency Comparison
  2024
• Benchmarking Vision Language Models for Cultural Understanding
  2024