paper-with-me

Papers

MIMIC-IT: Multi-Modal In-Context Instruction Tuning

2023-06-08 · Bo Li, Yuanhan Zhang, Liangyu Chen, Jinghao Wang, Fanyi Pu, Jingkang Yang, Chunyuan Li, Ziwei Liu

High-quality instructions and responses are essential for the zero-shot performance of large language models on interactive natural language tasks. For interactive vision-language tasks involving intricate visual scenes, a large quantity of diverse and creative instruction-response pairs should be imperative to tune vision-language models (VLMs). Nevertheless, the current availability of vision-language instruction-response pairs in terms of quantity, diversity, and creativity remains limited, posing challenges to the generalization of interactive VLMs. Here we present MultI-Modal In-Context Instruction Tuning (MIMIC-IT), a dataset comprising 2.8 million multimodal instruction-response pairs, with 2.2 million unique instructions derived from images and videos. Each pair is accompanied by multi-modal in-context information, forming conversational contexts aimed at empowering VLMs in perception, reasoning, and planning. The instruction-response collection process, dubbed as Syphus, is scaled using an automatic annotation pipeline that combines human expertise with GPT's capabilities. Using the MIMIC-IT dataset, we train a large VLM named Otter. Based on extensive evaluations conducted on vision-language benchmarks, it has been observed that Otter demonstrates remarkable proficiency in multi-modal perception, reasoning, and in-context learning. Human evaluation reveals it effectively aligns with the user's intentions. We release the MIMIC-IT dataset, instruction-response collection pipeline, benchmarks, and the Otter model.

📄 PDF Abstract BibTeX arXiv:2306.05425

Code (2)

luodian/otter 공식 구현 pytorch
One-2-3-45/One-2-3-45 pytorch

Tasks

In-Context LearningVisual Question Answering

Similar Papers 제목 키워드 기반

Otter: A Multi-Modal Model with In-Context Instruction Tuning

2023-05-05 · Bo Li, Yuanhan Zhang, Liangyu Chen, Jinghao Wang 외

Large language models (LLMs) have demonstrated significant universal capabilities as few/zero-shot learners in various tasks due to their pre-training on vast amounts of text data, as exemplified by GPT-3, which boosted …

GPUIn-Context LearningInstruction FollowingVisual Question Answering+2

Comparison Visual Instruction Tuning

2024-06-13 · Wei Lin, Muhammad Jehanzeb Mirza, Sivan Doveh, Rogerio Feris 외

Comparing two images in terms of Commonalities and Differences (CaD) is a fundamental human capability that forms the basis of advanced visual reasoning and interpretation. It is essential for the generation of detailed …

Instruction FollowingNovelty DetectionVisual Reasoning

Correlating instruction-tuning (in multimodal models) with vision-language processing (in the brain)

2025-05-26 · Subba Reddy Oota, Akshett Jindal, Ishani Mondal, Khushbu Pahwa 외

Transformer-based language models, though not explicitly trained to mimic brain recordings, have demonstrated surprising alignment with brain activity. Progress in these models-through increased size, instruction-tuning,…

Image Captioning

Benchmarking Retrieval-Augmented Generation in Multi-Modal Contexts

2025-02-24 · Zhenghao Liu, Xingsheng Zhu, Tianshuo Zhou, Xinyi Zhang 외

This paper introduces Multi-Modal Retrieval-Augmented Generation (M^2RAG), a benchmark designed to evaluate the effectiveness of Multi-modal Large Language Models (MLLMs) in leveraging knowledge from multi-modal retrieva…

BenchmarkingFact VerificationImage CaptioningQuestion Answering+4

Read to Play (R2-Play): Decision Transformer with Multimodal Game Instruction

2024-02-06 · Yonggang Jin, Ge Zhang, Hao Zhao, Tianyu Zheng 외

Developing a generalist agent is a longstanding objective in artificial intelligence. Previous efforts utilizing extensive offline datasets from various tasks demonstrate remarkable performance in multitasking scenarios …