English
Related papers

Related papers: UniCorn: Towards Self-Improving Unified Multimodal…

200 papers

Humans construct internal world models and reason by manipulating the concepts within these models. Recent advances in AI, particularly chain-of-thought (CoT) reasoning, approximate such human cognitive abilities, where world models are…

Artificial Intelligence · Computer Science 2026-01-28 Jialong Wu , Xiaoying Zhang , Hongyi Yuan , Xiangcheng Zhang , Tianhao Huang , Changjing He , Chaoyi Deng , Renrui Zhang , Youbin Wu , Mingsheng Long

Unified Multimodal Models (UMMs) have emerged as a promising paradigm that integrates multimodal understanding and generation within a unified modeling framework. However, current generative training paradigms suffer from inherent…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Jiyeong Kim , Yerim So , Hyesong Choi , Uiwon Hwang , Dongbo Min

Unified Multimodal Models struggle to bridge the fundamental gap between the abstract representations needed for visual understanding and the detailed primitives required for generation. Existing approaches typically compromise by employing…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Xuerui Qiu , Yutao Cui , Guozhen Zhang , Junzhe Li , JiaKui Hu , Xiao Zhang , Yang Li , Songtao Liu , Miles Yang , Yu Shi , Zhao Zhong , Liefeng Bo

Most existing vision-language pre-training methods focus on understanding tasks and use BERT-like objectives (masked language modeling and image-text matching) during pretraining. Although they perform well in many understanding downstream…

Computer Vision and Pattern Recognition · Computer Science 2021-12-16 Tianyi Liu , Zuxuan Wu , Wenhan Xiong , Jingjing Chen , Yu-Gang Jiang

Unified multimodal understanding and generation have recently received much attention in the area of vision and language. Existing UniMs are designed to simultaneously learn both multimodal understanding and generation capabilities,…

Computer Vision and Pattern Recognition · Computer Science 2025-06-09 Jianwen Sun , Yukang Feng , Chuanhao Li , Fanrui Zhang , Zizhen Li , Jiaxin Ai , Sizhuo Zhou , Yu Dai , Shenglin Zhang , Kaipeng Zhang

The task of visual dialog requires a multimodal chatbot to answer sequential questions from humans about image content. Prior work performs the standard likelihood training for answer generation on the positive instances (involving correct…

Computation and Language · Computer Science 2022-11-28 Zihao Wang , Junli Wang , Changjun Jiang

Unified multimodal models (UMMs) achieve strong performance in both understanding and generation by learning a shared latent space, yet they often exhibit functional inconsistency between these two capabilities. We observe that this issue…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Yinyi Luo , Wenwen Wang , Hayes Bai , Marios Savvides , Jindong Wang

Commonsense reasoning in multimodal contexts remains a foundational challenge in artificial intelligence. We introduce Multimodal UNcommonsense(MUN), a benchmark designed to evaluate models' ability to handle scenarios that deviate from…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Yejin Son , Saejin Kim , Dongjun Min , Younjae Yu

The integration of visual understanding and generation into unified multimodal models represents a significant stride toward general-purpose AI. However, a fundamental question remains unanswered by existing benchmarks: does this…

This paper presents a new Unified pre-trained Language Model (UniLM) that can be fine-tuned for both natural language understanding and generation tasks. The model is pre-trained using three types of language modeling tasks: unidirectional,…

Computation and Language · Computer Science 2019-10-16 Li Dong , Nan Yang , Wenhui Wang , Furu Wei , Xiaodong Liu , Yu Wang , Jianfeng Gao , Ming Zhou , Hsiao-Wuen Hon

Empowering models to dynamically accomplish tasks specified through natural language instructions represents a promising path toward more capable and general artificial intelligence. In this work, we introduce InstructSeq, an…

Computer Vision and Pattern Recognition · Computer Science 2023-12-01 Rongyao Fang , Shilin Yan , Zhaoyang Huang , Jingqiu Zhou , Hao Tian , Jifeng Dai , Hongsheng Li

Recent advancements in multimodal foundation models have yielded significant progress in vision-language understanding. Initial attempts have also explored the potential of multimodal large language models (MLLMs) for visual content…

Computer Vision and Pattern Recognition · Computer Science 2024-10-22 Rongyao Fang , Chengqi Duan , Kun Wang , Hao Li , Hao Tian , Xingyu Zeng , Rui Zhao , Jifeng Dai , Hongsheng Li , Xihui Liu

Recent text-to-image (T2I) models have made remarkable progress in generating visually realistic and semantically coherent images. However, they still suffer from randomness and inconsistency with the given prompts, particularly when…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Kaishen Wang , Ruibo Chen , Tong Zheng , Heng Huang

Long-context processing is a critical ability that constrains the applicability of large language models (LLMs). Although there exist various methods devoted to enhancing the long-context processing ability of LLMs, they are developed in an…

Computation and Language · Computer Science 2024-08-20 Junjie Fang , Likai Tang , Hongzhe Bi , Yujia Qin , Si Sun , Zhenyu Li , Haolun Li , Yongjian Li , Xin Cong , Yankai Lin , Yukun Yan , Xiaodong Shi , Sen Song , Zhiyuan Liu , Maosong Sun

Unified Multimodal Models (uMMs) aim to support both visual understanding and visual generation within a shared representation. However, existing evaluation protocols assess these two capabilities independently and do not examine whether…

Computer Vision and Pattern Recognition · Computer Science 2026-04-29 Weixing Wang , Liudvikas Zekas , Anton Hackl , Constantin Alexander Auga , Parisa Shahabinejad , Jona Otholt , Antonio Rueda-Toicen , Gerard de Melo

Recent advancements in Multimodal Large Language Models (MLLMs) underscore the significance of scalable models and data to boost performance, yet this often incurs substantial computational costs. Although the Mixture of Experts (MoE)…

Artificial Intelligence · Computer Science 2024-05-21 Yunxin Li , Shenyuan Jiang , Baotian Hu , Longyue Wang , Wanqi Zhong , Wenhan Luo , Lin Ma , Min Zhang

Decoding text stimuli from cognitive signals (e.g. fMRI) enhances our understanding of the human language system, paving the way for building versatile Brain-Computer Interface. However, existing studies largely focus on decoding individual…

Signal Processing · Electrical Eng. & Systems 2023-07-12 Nuwa Xi , Sendong Zhao , Haochun Wang , Chi Liu , Bing Qin , Ting Liu

Diffusion models have gained tremendous success in text-to-image generation, yet still lag behind with visual understanding tasks, an area dominated by autoregressive vision-language models. We propose a large-scale and fully end-to-end…

Computer Vision and Pattern Recognition · Computer Science 2025-04-03 Zijie Li , Henry Li , Yichun Shi , Amir Barati Farimani , Yuval Kluger , Linjie Yang , Peng Wang

Generative self-supervised learning on graphs, particularly graph masked autoencoders, has emerged as a popular learning paradigm and demonstrated its efficacy in handling non-Euclidean data. However, several remaining issues limit the…

Machine Learning · Computer Science 2024-02-14 Yijun Tian , Chuxu Zhang , Ziyi Kou , Zheyuan Liu , Xiangliang Zhang , Nitesh V. Chawla

The remarkable success of multimodal large language models (MLLMs) has driven advances in multimodal embeddings, yet existing models remain inherently discriminative, limiting their ability to benefit from reasoning-driven generation…

Machine Learning · Computer Science 2026-03-03 Zhibin Lan , Liqiang Niu , Fandong Meng , Jie Zhou , Jinsong Su