3 papers
cs.CV2026
Do-Undo Bench: Reversibility for Action Understanding in Image Generation
Shweta Mahajan, Shreya Kadambi, Hoang Le +4
We introduce the Do-Undo task and benchmark to address a critical gap in vision-language models: understanding and generating plausible scene transformations driven by real-world a…
cs.CV2025
Attention Guided Alignment in Efficient Vision-Language Models
Shweta Mahajan, Hoang Le, Hyojin Park +3
Large Vision-Language Models (VLMs) rely on effective multimodal alignment between pre-trained vision encoders and Large Language Models (LLMs) to integrate visual and textual info…
cs.CV2024
SilVar: Speech Driven Multimodal Model for Reasoning Visual Question Answering and Object Localization
Tan-Hanh Pham, Hoang-Nam Le, Phu-Vinh Nguyen +2
Visual Language Models have demonstrated remarkable capabilities across tasks, including visual question answering and image captioning. However, most models rely on text-based ins…