Related papers: Hijacking Context in Large Multi-modal Models

Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering. The recent progress in large-scale generative models has further expanded their use in real-world language applications. However, the…

This paper presents the first-ever study of adapting compressed image latents to suit the needs of downstream vision tasks that adopt Multimodal Large Language Models (MLLMs). MLLMs have extended the success of large language models to…

Large Language Models (LLM) have emerged as a tool for robots to generate task plans using common sense reasoning. For the LLM to generate actionable plans, scene context must be provided, often through a map. Recent works have shifted from…

Our research integrates graph data with Large Language Models (LLMs), which, despite their advancements in various fields using large text corpora, face limitations in encoding entire graphs due to context size constraints. This paper…

Masked language modeling (MLM) is one of the key sub-tasks in vision-language pretraining. In the cross-modal setting, tokens in the sentence are masked at random, and the model predicts the masked tokens given the image and the text. In…

In recent years, the emergence of models capable of generating images from text has attracted considerable interest, offering the possibility of creating realistic images from text descriptions. Yet these advances have also raised concerns…

Large language models (LMs) such as GPT-3 have the surprising ability to do in-context learning, where the model learns to do a downstream task simply by conditioning on a prompt consisting of input-output examples. The LM learns from these…

Multimodal Large Language Models (MLLMs) have achieved significant advancements in tasks like Visual Question Answering (VQA) by leveraging foundational Large Language Models (LLMs). However, their abilities in specific areas such as visual…

Large Multimodal Models (LMMs) have made significant strides in visual question-answering for single images. Recent advancements like long-context LMMs have allowed them to ingest larger, or even multiple, images. However, the ability to…

Memes have emerged as a popular form of multimodal online communication, where their interpretation heavily depends on the specific context in which they appear. Current approaches predominantly focus on isolated meme analysis, either for…

Recent advances in large vision-language models (VLMs) have shown significant promise for 3D scene understanding. Existing VLM-based approaches typically align 3D scene features with the VLM's embedding space. However, this implicit…

Modern text-to-vision generative models often hallucinate when the prompt describing the scene to be generated is underspecified. In large language models (LLMs), a prevalent strategy to reduce hallucinations is to retrieve factual…

Recent Multimodal Large Language Models (MLLMs) are remarkable in vision-language tasks, such as image captioning and question answering, but lack the essential perception ability, i.e., object detection. In this work, we address this…

This paper presents several novel findings on the explainability of vision reflection in large multimodal models (LMMs). First, we show that prompting an LMM to verify the prediction of a specialized vision model can improve recognition…

Vision-language models (VLMs) have excelled in multimodal tasks, but adapting them to embodied decision-making in open-world environments presents challenges. One critical issue is bridging the gap between discrete entities in low-level…

Although vision-language models (VLMs) have achieved significant success in various applications such as visual question answering, their resilience to prompt variations remains an under-explored area. Understanding how distractions affect…

Low-shot image classification, where training images are limited or inaccessible, has benefited from recent progress on pre-trained vision-language (VL) models with strong generalizability, e.g. CLIP. Prompt learning methods built with VL…

Despite the impressive capabilities of Multimodal Large Language Models (MLLMs) in integrating text and image modalities, challenges remain in accurately interpreting detailed visual elements. Vision detection models excel at recognizing…

Recent advancements in Large Language Models (LLMs) have significantly enhanced their capacity to process long contexts. However, effectively utilizing this long context remains a challenge due to the issue of distraction, where irrelevant…

Multimodal Large Language Models (MLLMs) have shown significant promise in various applications, leading to broad interest from researchers and practitioners alike. However, a comprehensive evaluation of their long-context capabilities…