이진욱님의 블로그

https://arxiv.org/pdf/2408.00765

https://arxiv.org/pdf/2410.01044

https://arxiv.org/pdf/2410.04734

https://arxiv.org/pdf/2408.03326

https://arxiv.org/pdf/2410.06961

https://arxiv.org/pdf/2404.05046v1Large Vision-Language Models (LVLMs) have demonstrated proficiency in tackling a variety of visual-language tasks. However, current LVLMs suffer from misalignment between text and image modalities which causes three kinds of hallucination problems, i.e., object existence, object attribute, and object relationship. To tackle this issue, existing methods mainly ut..

https://arxiv.org/pdf/2410.06154In this work, we propose a novel method (GLOV) enabling Large Language Models (LLMs) to act as implicit Optimizers for Vision-Language Models (VLMs) to enhance downstream vision tasks. Our GLOV meta-prompts an LLM with the downstream task description, querying it for suitable VLM prompts (e.g., for zeroshot classification with CLIP). These prompts are ranked accor..

https://arxiv.org/pdf/2410.03450

https://arxiv.org/pdf/2410.07113

https://arxiv.org/abs/2402.11411Instruction-following Vision Large Language Models (VLLMs) have achieved significant progress recently on a variety of tasks. These approaches merge strong pre-trained vision models and large language models (LLMs). Since these components are trained separately, the learned representations need to be aligned with joint training on additional image-language pairs. ..