English
Related papers

Related papers: WorldPack: Compressed Memory Improves Spatial Cons…

200 papers

This paper aims to improve the performance of video multimodal large language models (MLLM) via long and rich context (LRC) modeling. As a result, we develop a new version of InternVideo2.5 with a focus on enhancing the original MLLMs'…

Computer Vision and Pattern Recognition · Computer Science 2025-07-15 Yi Wang , Xinhao Li , Ziang Yan , Yinan He , Jiashuo Yu , Xiangyu Zeng , Chenting Wang , Changlian Ma , Haian Huang , Jianfei Gao , Min Dou , Kai Chen , Wenhai Wang , Yu Qiao , Yali Wang , Limin Wang

Accurate video prediction by deep neural networks, especially for dynamic regions, is a challenging task in computer vision for critical applications such as autonomous driving, remote working, and telemedicine. Due to inherent…

Computer Vision and Pattern Recognition · Computer Science 2024-12-05 Kazuki Kotoyori , Shota Hirose , Heming Sun , Jiro Katto

Learning physical dynamics in a series of non-stationary environments is a challenging but essential task for model-based reinforcement learning (MBRL) with visual inputs. It requires the agent to consistently adapt to novel tasks without…

Machine Learning · Computer Science 2025-07-08 Minting Pan , Wendong Zhang , Geng Chen , Xiangming Zhu , Siyu Gao , Yunbo Wang , Xiaokang Yang

Large Language Models (LLMs) often experience performance degradation during long-running interactions due to increasing context length, memory saturation, and computational overhead. This paper presents an adaptive context compression…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Payal Fofadiya , Sunil Tiwari

Recent advances in foundational Video Diffusion Models (VDMs) have yielded significant progress. Yet, despite the remarkable visual quality of generated videos, reconstructing consistent 3D scenes from these outputs remains challenging, due…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Yisu Zhang , Chenjie Cao , Tengfei Wang , Xuhui Zuo , Junta Wu , Jianke Zhu , Chunchao Guo

Contextual memory integration remains a high challenge in the development of language models, particularly in tasks that require maintaining coherence over extended sequences. Traditional approaches, such as self-attention mechanisms and…

Computation and Language · Computer Science 2025-08-11 George Applegarth , Christian Weatherstone , Maximilian Hollingsworth , Henry Middlebrook , Marcus Irvin

Memory retention challenges in deep neural architectures have ongoing limitations in the ability to process and recall extended contextual information. Token dependencies degrade as sequence length increases, leading to a decline in…

Computation and Language · Computer Science 2025-03-26 Frederick Dillon , Gregor Halvorsen , Simon Tattershall , Magnus Rowntree , Gareth Vanderpool

This paper presents a context key/value compression method for Transformer language models in online scenarios, where the context continually expands. As the context lengthens, the attention process demands increasing memory and…

Machine Learning · Computer Science 2024-02-07 Jang-Hyun Kim , Junyoung Yeom , Sangdoo Yun , Hyun Oh Song

We introduce Spatial-Temporal Memory Networks for video object detection. At its core, a novel Spatial-Temporal Memory module (STMM) serves as the recurrent computation unit to model long-term temporal appearance and motion dynamics. The…

Computer Vision and Pattern Recognition · Computer Science 2018-07-30 Fanyi Xiao , Yong Jae Lee

Recent incremental learning for action recognition usually stores representative videos to mitigate catastrophic forgetting. However, only a few bulky videos can be stored due to the limited memory. To address this problem, we propose…

Computer Vision and Pattern Recognition · Computer Science 2022-11-03 Yixuan Pei , Zhiwu Qing , Jun Cen , Xiang Wang , Shiwei Zhang , Yaxiong Wang , Mingqian Tang , Nong Sang , Xueming Qian

The rapid evolution of video generation has enabled models to simulate complex physical dynamics and long-horizon causalities, positioning them as potential world simulators. However, a critical gap still remains between the theoretical…

Image and Video Processing · Electrical Eng. & Systems 2026-05-06 Muyang He , Hanzhong Guo , Junxiong Lin , Yizhou Yu

Spatio-temporal contexts are crucial in understanding human actions in videos. Recent state-of-the-art Convolutional Neural Network (ConvNet) based action recognition systems frequently involve 3D spatio-temporal ConvNet filters, chunking…

Computer Vision and Pattern Recognition · Computer Science 2018-05-09 Yunfeng Wang , Wengang Zhou , Qilin Zhang , Xiaotian Zhu , Houqiang Li

Embodied world models aim to predict and interact with the physical world through visual observations and actions. However, existing models struggle to accurately translate low-level actions (e.g., joint positions) into precise robotic…

Robotics · Computer Science 2026-04-01 Taiyi Su , Jian Zhu , Yaxuan Li , Chong Ma , Jianjun Zhang , Zitai Huang , Hanli Wang , Yi Xu

Frame quality deterioration is one of the main challenges in the field of video understanding. To compensate for the information loss caused by deteriorated frames, recent approaches exploit transformer-based integration modules to obtain…

Computer Vision and Pattern Recognition · Computer Science 2024-02-07 Guanxiong Sun , Chi Wang , Zhaoyu Zhang , Jiankang Deng , Stefanos Zafeiriou , Yang Hua

Vision-language models (VLMs) have shown strong performance on static visual understanding, yet they still struggle with dynamic spatial reasoning that requires imagining how scenes evolve under egocentric motion. Recent efforts address…

Computer Vision and Pattern Recognition · Computer Science 2026-04-30 Wanyue Zhang , Wenxiang Wu , Wang Xu , Jiaxin Luo , Helu Zhi , Yibin Huang , Shuo Ren , Zitao Liu , Jiajun Zhang

Spatio-temporal consistency is a critical research topic in video generation. A qualified generated video segment must ensure plot plausibility and coherence while maintaining visual consistency of objects and scenes across varying…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Runze Zhang , Guoguang Du , Xiaochuan Li , Qi Jia , Liang Jin , Lu Liu , Jingjing Wang , Cong Xu , Zhenhua Guo , Yaqian Zhao , Xiaoli Gong , Rengang Li , Baoyu Fan

Video-to-video synthesis (vid2vid) aims for converting high-level semantic inputs to photorealistic videos. While existing vid2vid methods can achieve short-term temporal consistency, they fail to ensure the long-term one. This is because…

Computer Vision and Pattern Recognition · Computer Science 2020-07-17 Arun Mallya , Ting-Chun Wang , Karan Sapra , Ming-Yu Liu

Image-goal navigation is a challenging task that requires an agent to navigate to a goal indicated by an image in unfamiliar environments. Existing methods utilizing diverse scene memories suffer from inefficient exploration since they use…

Computer Vision and Pattern Recognition · Computer Science 2024-03-29 Hongxin Li , Zeyu Wang , Xu Yang , Yuran Yang , Shuqi Mei , Zhaoxiang Zhang

Continual RL requires an agent to learn new tasks without forgetting previous ones, while improving on both past and future tasks. The most common approaches use model-free algorithms and replay buffers can help to mitigate catastrophic…

Machine Learning · Computer Science 2024-07-17 Luke Yang , Levin Kuhlmann , Gideon Kowadlo

Many scientific areas, from computer science to the environmental sciences and finance, give rise to multivariate time series which exhibit long memory, or loosely put, a slow decay in their autocorrelation structure. Efficient modelling…

Methodology · Statistics 2025-12-12 Chiara Boetti , Matthew A. Nunes , Marina I. Knight