English
Related papers

Related papers: Redundancy-Adaptive Multimodal Learning for Imperf…

200 papers

Instruction tuning fine-tunes pre-trained Multi-modal Large Language Models (MLLMs) to handle real-world tasks. However, the rapid expansion of visual instruction datasets introduces data redundancy, leading to excessive computational…

Computer Vision and Pattern Recognition · Computer Science 2025-08-15 Qifan Yu , Zhebei Shen , Zhongqi Yue , Yang Wu , Bosheng Qin , Wenqiao Zhang , Yunfei Li , Juncheng Li , Siliang Tang , Yueting Zhuang

Retrieval augmented generation (RAG), while effectively integrating external knowledge to address the inherent limitations of large language models (LLMs), can be hindered by imperfect retrieval that contain irrelevant, misleading, or even…

Computation and Language · Computer Science 2025-06-03 Fei Wang , Xingchen Wan , Ruoxi Sun , Jiefeng Chen , Sercan Ö. Arık

In this paper, we propose SimMLM, a simple yet powerful framework for multimodal learning with missing modalities. Unlike existing approaches that rely on sophisticated network architectures or complex data imputation techniques, SimMLM…

Computer Vision and Pattern Recognition · Computer Science 2025-08-07 Sijie Li , Chen Chen , Jungong Han

Tabular machine learning systems are frequently trained on data affected by non-uniform corruption, including noisy measurements, missing entries, and feature-specific biases. In practice, these defects are often documented only through…

Machine Learning · Computer Science 2026-02-04 Mattia Sabella , Alberto Archetti , Pietro Pinoli , Matteo Matteucci , Cinzia Cappiello

Modern deep architectures often rely on large-scale datasets, but training on these datasets incurs high computational and storage overhead. Real-world datasets often contain substantial redundancies, prompting the need for more…

Machine Learning · Computer Science 2025-06-27 Suorong Yang , Peijia Li , Furao Shen , Jian Zhao

Learning from multiple modalities, such as audio and video, offers opportunities for leveraging complementary information, enhancing robustness, and improving contextual understanding and performance. However, combining such modalities…

Multimedia · Computer Science 2024-10-15 Konstantinos Kontras , Christos Chatzichristos , Matthew Blaschko , Maarten De Vos

We consider the problem of recovering an expert's reward function with inverse reinforcement learning (IRL) when there are missing/incomplete state-action pairs or observations in the demonstrated trajectories. This issue of missing…

Machine Learning · Computer Science 2019-11-19 Tien Mai , Quoc Phong Nguyen , Kian Hsiang Low , Patrick Jaillet

Multi-modal deep metric learning is crucial for effectively capturing diverse representations in tasks such as face verification, fine-grained object recognition, and product search. Traditional approaches to metric learning, whether based…

Computer Vision and Pattern Recognition · Computer Science 2024-11-06 Hadush Hailu Gebrerufael , Anil Kumar Tiwari , Gaurav Neupane , Goitom Ybrah Hailu

Surgical workflow recognition is vital for automating tasks, supporting decision-making, and training novice surgeons, ultimately improving patient safety and standardizing procedures. However, data corruption can lead to performance…

Computer Vision and Pattern Recognition · Computer Science 2025-05-06 Long Bai , Boyi Ma , Ruohan Wang , Guankun Wang , Beilei Cui , Zhongliang Jiang , Mobarakol Islam , Zhe Min , Jiewen Lai , Nassir Navab , Hongliang Ren

In multi-agent reinforcement learning (MARL), ensuring robustness against unpredictable or worst-case actions by allies is crucial for real-world deployment. Existing robust MARL methods either approximate or enumerate all possible threat…

Machine Learning · Computer Science 2024-05-22 Simin Li , Ruixiao Xu , Jingqiao Xiu , Yuwei Zheng , Pu Feng , Yaodong Yang , Xianglong Liu

Simultaneously using multimodal inputs from multiple sensors to train segmentors is intuitively advantageous but practically challenging. A key challenge is unimodal bias, where multimodal segmentors over rely on certain modalities, causing…

Computer Vision and Pattern Recognition · Computer Science 2025-05-19 Xu Zheng , Haiwei Xue , Jialei Chen , Yibo Yan , Lutao Jiang , Yuanhuiyi Lyu , Kailun Yang , Linfeng Zhang , Xuming Hu

Despite recent advancements in federated learning (FL) for medical image diagnosis, addressing data heterogeneity among clients remains a significant challenge for practical implementation. A primary hurdle in FL arises from the non-IID…

Machine Learning · Computer Science 2024-07-09 Pranab Sahoo , Ashutosh Tripathi , Sriparna Saha , Samrat Mondal

Multimodal information retrieval (MMIR) has gained attention for its flexibility in handling text, images, or mixed queries and candidates. Recent breakthroughs in multimodal large language models (MLLMs) boost MMIR performance by…

Information Retrieval · Computer Science 2026-02-27 Dawei Su , Dongsheng Wang

Multimodal data plays a critical role in web-based recommendation systems, where information from diverse modalities such as vision and text enhances representation learning. However, real-world multimodal datasets often suffer from…

Information Retrieval · Computer Science 2026-05-04 Yuan Li , Jun Hu , Jiaxin Jiang , Bryan Hooi , Bingsheng He

Recent advancements in Large Language Models (LLMs) have demonstrated impressive capabilities across a range of natural language processing tasks, especially in reasoning, a cornerstone for achieving Artificial General Intelligence (AGI).…

Computation and Language · Computer Science 2023-10-09 Wenbei Xie

Multimodal learning (MML) aims to jointly exploit the common priors of different modalities to compensate for their inherent limitations. However, existing MML methods often optimize a uniform objective for different modalities, leading to…

Machine Learning · Computer Science 2022-11-15 Yunfeng Fan , Wenchao Xu , Haozhao Wang , Junxiao Wang , Song Guo

The quest for incremental unified multimodal anomaly detection seeks to empower a single model with the ability to systematically detect anomalies across all categories and support incremental learning to accommodate emerging…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Kaifang Long , Lianbo Ma , Jiaqi Liu , Liming Liu , Guoyang Xie

Deep learning based computer vision fails to work when labeled images are scarce. Recently, Meta learning algorithm has been confirmed as a promising way to improve the ability of learning from few images for computer vision. However,…

Machine Learning · Computer Science 2018-11-27 Yunxiao Qin , Chenxu Zhao , Zezheng Wang , Junliang Xing , Jun Wan , Zhen Lei

Traditional Reinforcement Learning (RL) frameworks generally assume that the agent perceives the state of the underlying Markov process instantaneously and then takes actions accordingly. If the agent cannot directly observe the process,…

Machine Learning · Computer Science 2026-05-12 Pietro Talli , Federico Mason , Federico Chiariotti , Andrea Zanella

Skeleton-based action recognition has garnered significant attention due to the utilization of concise and resilient skeletons. Nevertheless, the absence of detailed body information in skeletons restricts performance, while other…

Computer Vision and Pattern Recognition · Computer Science 2024-08-16 Jinfu Liu , Chen Chen , Mengyuan Liu
‹ Prev 1 8 9 10 Next ›