8 papers · 1 filter
Scene Co-pilot: Procedural Text to Video Generation with Human in the Loop
Zhaofang Qian, Abolfazl Sharifi, Tucker Carroll +1
Video generation has achieved impressive quality, but it still suffers from artifacts such as temporal inconsistency and violation of physical laws. Leveraging 3D scenes can fundam…
Distilling Vision-Language Pretraining for Efficient Cross-Modal Retrieval
Young Kyun Jang, Donghyun Kim, Ser-nam Lim
``Learning to hash'' is a practical solution for efficient retrieval, offering fast search speed and low storage cost. It is widely applied in various applications, such as image-t…
Towards Cross-modal Backward-compatible Representation Learning for Vision-Language Models
Young Kyun Jang, Ser-nam Lim
Modern retrieval systems often struggle with upgrading to new and more powerful models due to the incompatibility of embeddings between the old and new models. This necessitates a…
Visual Delta Generator with Large Multi-modal Models for Semi-supervised Composed Image Retrieval
Young Kyun Jang, Donghyun Kim, Zihang Meng +2
Composed Image Retrieval (CIR) is a task that retrieves images similar to a query, based on a provided textual modification. Current techniques rely on supervised learning for CIR…
Mitigating Dialogue Hallucination for Large Vision Language Models via Adversarial Instruction Tuning
Dongmin Park, Zhaofang Qian, Guangxing Han +1
Mitigating hallucinations of Large Vision Language Models,(LVLMs) is crucial to enhance their reliability for general-purpose assistants. This paper shows that such hallucinations…
On the Robustness of Large Multimodal Models Against Image Adversarial Attacks
Xuanming Cui, Alejandro Aparcedo, Young Kyun Jang +1
Recent advances in instruction tuning have led to the development of State-of-the-Art Large Multimodal Models (LMMs). Given the novelty of these models, the impact of visual advers…