Language Is Not All You Need: Aligning Perception with Language Models

A big convergence of language, multimodal perception, action, and world modeling is a key step toward artificial general intelligence. In this work, we introduce Kosmos-1, a Multimodal Large Language Model (MLLM) that can perceive general modalities, learn in context (i.e., few-shot), and follow instructions (i.e., zero-shot). Specifically, we train Kosmos-1 from scratch on web-scale multimodal corpora, including arbitrarily interleaved text and images, image-caption pairs, and text data. We evaluate various settings, including zero-shot, few-shot, and multimodal chain-of-thought prompting, on a wide range of tasks without any gradient updates or finetuning. Experimental results show that Kosmos-1 achieves impressive performance on (i) language understanding, generation, and even OCR-free NLP (directly fed with document images), (ii) perception-language tasks, including multimodal dialogue, image captioning, visual question answering, and (iii) vision tasks, such as image recognition with descriptions (specifying classification via text instructions). We also show that MLLMs can benefit from cross-modal transfer, i.e., transfer knowledge from language to multimodal, and from multimodal to language. In addition, we introduce a dataset of Raven IQ test, which diagnoses the nonverbal reasoning capability of MLLMs.

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Image Captioning COCO Captions KOSMOS-1 (1.6B) (zero-shot) CIDER 84.7 # 33
SPICE 16.8 # 27
Image Captioning Flickr30k Captions test KOSMOS-1 1.6B (zero-shot) CIDEr 67.1 # 2
SPICE 14.5 # 2
Visual Question Answering (VQA) VQA v2 test-dev KOSMOS-1 1.6B (zero-shot) Accuracy 51.0 # 56


No methods listed for this paper. Add relevant methods here