paper-with-me

홈 › Papers

Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision Language Audio and Action

2024-01-01 · CVPR 2024 1 · Jiasen Lu, Christopher Clark, Sangho Lee, Zichen Zhang, Savya Khosla, Ryan Marten, Derek Hoiem, Aniruddha Kembhavi

We present Unified-IO 2 a multimodal and multi-skill unified model capable of following novel instructions. Unified-IO 2 can use text images audio and/or videos as input and can generate text image or audio outputs which is accomplished in a unified way by tokenizing these different inputs and outputs into a shared semantic space that can then be processed by a single encoder-decoder transformer model. Unified-IO 2 is trained from scratch on a custom-built multimodal pre-training corpus and then learns an expansive set of skills through fine-tuning on over 120 datasets including datasets for segmentation object detection image editing audio localization video tracking embodied AI and 3D detection. To facilitate instruction-following we add prompts and other data augmentations to these tasks to allow Unified-IO 2 to generalize these skills to new tasks zero-shot. Unified-IO 2 is the first model to be trained on such a diverse and wide-reaching set of skills and unify three separate generation capabilities. Unified-IO 2 achieves state-of-the-art performance on the multi-task GRIT benchmark and achieves strong results on 30 diverse datasets including SEED-Bench image and video understanding TIFA image generation VQA 2.0 ScienceQA VIMA robotic manipulation VGG-Sound and Kinetics-Sounds and can perform unseen tasks and generate free-form responses. We release our model and code to facilitate future work.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Image GenerationInstruction Followingobject-detectionObject DetectionVideo UnderstandingVisual Question Answering (VQA)

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action

2023-12-28 · Jiasen Lu, Christopher Clark, Sangho Lee, Zichen Zhang 외

We present Unified-IO 2, the first autoregressive multimodal model that is capable of understanding and generating image, text, audio, and action. To unify different modalities, we tokenize inputs and outputs -- images, …

DecoderImage GenerationNatural Language Understanding

STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation

2026-05-08 · Ying Shen, Tianrong Chen, Yuan Gao, Yizhe Zhang 외 arxiv

Deep generative models have advanced rapidly across text and vision, motivating unified multimodal systems that can understand, reason over, and generate interleaved text-image sequences. Most existing approaches combine…

multimodal generationImage GenerationText Generation

MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer

2025-09-19 · Yanghao Li, Rui Qian, Bowen Pan, Haotian Zhang 외 arxiv

Unified multimodal Large Language Models (LLMs) that can both understand and generate visual content hold immense potential. However, existing open-source models often suffer from a performance trade-off between these ca…

Text-to-Image Generation

Unified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to Unification

2026-06-16 · Wujian Peng, Lingchen Meng, Yuxuan Cai, Xianwei Zhuang 외 arxiv

Unified Multimodal Modeling aims to integrate visual understanding and generation within a single system. However, existing approaches typically rely on two disparate visual tokenizers, which splits the representation sp…

Reinforcement LearningImage GenerationImage Editing

OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generation

2025-09-03 · Han Li, Xinyu Peng, Yaoming Wang, Zelin Peng 외 arxiv

We introduce OneCAT, a unified multimodal model that seamlessly integrates understanding, generation, and editing within a novel, pure decoder-only transformer architecture. Our framework uniquely eliminates the need for…

multimodal generation