English
Related papers

Related papers: ViM: Vision Middleware for Unified Downstream Tran…

200 papers

This paper presents the Large Vision Diffusion Transformer (LaVin-DiT), a scalable and unified foundation model designed to tackle over 20 computer vision tasks in a generative framework. Unlike existing large vision models directly adapted…

Computer Vision and Pattern Recognition · Computer Science 2025-03-07 Zhaoqing Wang , Xiaobo Xia , Runnan Chen , Dongdong Yu , Changhu Wang , Mingming Gong , Tongliang Liu

Fine-tuning is becoming widely used for leveraging the power of pre-trained foundation models in new downstream tasks. While there are many successes of fine-tuning on various tasks, recent studies have observed challenges in the…

Machine Learning · Computer Science 2024-06-21 Yuji Roh , Qingyun Liu , Huan Gui , Zhe Yuan , Yujin Tang , Steven Euijong Whang , Liang Liu , Shuchao Bi , Lichan Hong , Ed H. Chi , Zhe Zhao

Vision Transformers (ViTs) are normally regarded as a stack of transformer layers. In this work, we propose a novel view of ViTs showing that they can be seen as ensemble networks containing multiple parallel paths with different lengths.…

Computer Vision and Pattern Recognition · Computer Science 2023-08-15 Shuning Chang , Pichao Wang , Hao Luo , Fan Wang , Mike Zheng Shou

Pre-trained multi-modal vision-language models (VLMs) are becoming increasingly popular due to their exceptional performance on downstream vision applications, particularly in the few- and zero-shot settings. However, selecting the…

Computer Vision and Pattern Recognition · Computer Science 2023-06-16 Orr Zohar , Shih-Cheng Huang , Kuan-Chieh Wang , Serena Yeung

Transformer, first applied to the field of natural language processing, is a type of deep neural network mainly based on the self-attention mechanism. Thanks to its strong representation capabilities, researchers are looking at ways to…

Computer Vision and Pattern Recognition · Computer Science 2023-07-11 Kai Han , Yunhe Wang , Hanting Chen , Xinghao Chen , Jianyuan Guo , Zhenhua Liu , Yehui Tang , An Xiao , Chunjing Xu , Yixing Xu , Zhaohui Yang , Yiman Zhang , Dacheng Tao

Computer vision researchers are embracing two promising paradigms: Vision Transformers (ViTs) and Multi-task Learning (MTL), which both show great performance but are computation-intensive, given the quadratic complexity of self-attention…

Hardware Architecture · Computer Science 2023-09-14 Rishov Sarkar , Hanxue Liang , Zhiwen Fan , Zhangyang Wang , Cong Hao

Visual foundation models (VFMs) have become increasingly popular due to their state-of-the-art performance. However, interpretability remains crucial for critical applications. In this sense, self-explainable models (SEM) aim to provide…

Computer Vision and Pattern Recognition · Computer Science 2025-02-28 Hugues Turbé , Mina Bjelogrlic , Gianmarco Mengaldo , Christian Lovis

Theory of mind (ToM) enables AI systems to infer agents' hidden goals and mental states, but existing approaches focus mainly on small human understandable gridworld spaces. We introduce HiVAE, a hierarchical variational architecture that…

Machine Learning · Computer Science 2026-02-20 Nigel Doering , Rahath Malladi , Arshia Sangwan , David Danks , Tauhidur Rahman

Conventional wisdom suggests that pre-training Vision Transformers (ViT) improves downstream performance by learning useful representations. Is this actually true? We investigate this question and find that the features and representations…

Machine Learning · Computer Science 2024-11-15 Alexander C. Li , Yuandong Tian , Beidi Chen , Deepak Pathak , Xinlei Chen

Unified multimodal models (UMMs) are emerging as strong foundation models that can do both generation and understanding tasks in a single architecture. However, they are typically trained in centralized settings where all training and…

Machine Learning · Computer Science 2026-01-23 Zhaolong Su , Leheng Zhao , Xiaoying Wu , Ziyue Xu , Jindong Wang

Vision-Language Models (VLMs) have achieved remarkable progress, yet their large scale often renders them impractical for resource-constrained environments. This paper introduces Unified Reinforcement and Imitation Learning (RIL), a novel…

Computer Vision and Pattern Recognition · Computer Science 2025-10-23 Byung-Kwan Lee , Ryo Hachiuma , Yong Man Ro , Yu-Chiang Frank Wang , Yueh-Hua Wu

Visual grounding aims to align visual information of specific regions of images with corresponding natural language expressions. Current visual grounding methods leverage pre-trained visual and language backbones independently to obtain…

Computer Vision and Pattern Recognition · Computer Science 2024-07-09 Jiaxi Wang , Wenhui Hu , Xueyang Liu , Beihu Wu , Yuting Qiu , YingYing Cai

Deploying large-scale transformer models on edge devices presents significant challenges due to strict constraints on memory, compute, and latency. In this work, we propose a lightweight yet effective multi-stage optimization pipeline…

Machine Learning · Computer Science 2025-12-24 Shoaib Mohammad , Guanqun Song , Ting Zhu

Pretrained foundation models learn embeddings that can be used for a wide range of downstream tasks. These embeddings optimise general performance, and if insufficiently accurate at a specific task the model can be fine-tuned to improve…

Machine Learning · Computer Science 2025-02-20 Matthew P. Wilson , Edward O. Pyzer-Knapp , Nicolas Galichet , Luke Dicks

Building scalable vision-language models to learn from diverse, multimodal data remains an open challenge. In this paper, we introduce an Efficient Vision-languagE foundation model, namely EVE, which is one unified multimodal Transformer…

Computer Vision and Pattern Recognition · Computer Science 2024-03-04 Junyi Chen , Longteng Guo , Jia Sun , Shuai Shao , Zehuan Yuan , Liang Lin , Dongyu Zhang

While deep neural network (DNN)-based video denoising has demonstrated significant performance, deploying state-of-the-art models on edge devices remains challenging due to stringent real-time and energy efficiency requirements.…

Computer Vision and Pattern Recognition · Computer Science 2025-05-29 Shan Gao , Zhiqiang Wu , Yawen Niu , Xiaotao Li , Qingqing Xu

Vision-Language-Action (VLA) models, which integrate pretrained large Vision-Language Models (VLM) into their policy backbone, are gaining significant attention for their promising generalization capabilities. This paper revisits a…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Jianke Zhang , Xiaoyu Chen , Qiuyue Wang , Mingsheng Li , Yanjiang Guo , Yucheng Hu , Jiajun Zhang , Shuai Bai , Junyang Lin , Jianyu Chen

Foundation models have shown outstanding performance and generalization capabilities across domains. Since most studies on foundation models mainly focus on the pretraining phase, a naive strategy to minimize a single task-specific loss is…

Computer Vision and Pattern Recognition · Computer Science 2023-03-24 Dohwan Ko , Joonmyung Choi , Hyeong Kyu Choi , Kyoung-Woon On , Byungseok Roh , Hyunwoo J. Kim

Video understanding tasks have traditionally been modeled by two separate architectures, specially tailored for two distinct tasks. Sequence-based video tasks, such as action recognition, use a video backbone to directly extract…

Computer Vision and Pattern Recognition · Computer Science 2023-03-31 Yucheng Zhao , Chong Luo , Chuanxin Tang , Dongdong Chen , Noel Codella , Zheng-Jun Zha

Sim2Real transfer has gained popularity because it helps transfer from inexpensive simulators to real world. This paper presents a novel system that fuses components in a traditional World Model into a robust system, trained entirely within…

Robotics · Computer Science 2024-03-26 Kiran Lekkala , Chen Liu , Laurent Itti