Imagen de Portada

MosaicMem: Hybrid Spatial Memory for Controllable Video World Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yu, Wei, Qian, Runjia, Li, Yumeng, Wang, Liquan, Yin, Songheng, P, Sri Siddarth Chakaravarthy, Anthony, Dennis, Ye, Yang, Li, Yidi, Wan, Weiwei, Garg, Animesh
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Walking the Web of Concept-Class Relationships in Incrementally Trained Interpretable Models
por: Agrawal, Susmit, et al.
Publicado: (2025)

TopoCut: Learning Multi-Step Cutting with Spectral Rewards and Discrete Diffusion Policies
por: Wang, Liquan, et al.
Publicado: (2025)

Discovering Robotic Interaction Modes with Discrete Representation Learning
por: Wang, Liquan, et al.
Publicado: (2024)

Q-GeoMem: Question-Guided Geometric Memory for Video Spatial Reasoning
por: Gao, Xianqiang, et al.
Publicado: (2026)

FreshMem: Brain-Inspired Frequency-Space Hybrid Memory for Streaming Video Understanding
por: Li, Kangcong, et al.
Publicado: (2026)

VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory
por: Li, Runjia, et al.
Publicado: (2025)

RenderMem: Rendering as Spatial Memory Retrieval
por: Park, JooHyun, et al.
Publicado: (2026)

SpatialMem: Metric-Aligned Long-Horizon Video Memory for Language Grounding and QA
por: Zheng, Xinyi, et al.
Publicado: (2026)

MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives
por: Ji, Sihui, et al.
Publicado: (2025)

WorldMem: Long-term Consistent World Simulation with Memory
por: Xiao, Zeqi, et al.
Publicado: (2025)

DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory
por: Yang, Zhenhao, et al.
Publicado: (2026)

MemFail: Stress-Testing Failure Modes of LLM Memory Systems
por: Garg, Ishir, et al.
Publicado: (2026)

Memory Mosaics
por: Zhang, Jianyu, et al.
Publicado: (2024)

MemCam: Memory-Augmented Camera Control for Consistent Video Generation
por: Gao, Xinhang, et al.
Publicado: (2026)

MemWeaver: Weaving Hybrid Memories for Traceable Long-Horizon Agentic Reasoning
por: Ye, Juexiang, et al.
Publicado: (2026)

MemCog: From Memory-as-Tool to Memory-as-Cognition in Conversational Agents
por: Li, Zihan, et al.
Publicado: (2026)

HyMem: Hybrid Memory Architecture with Dynamic Retrieval Scheduling
por: Zhao, Xiaochen, et al.
Publicado: (2026)

Memory Mosaics at scale
por: Zhang, Jianyu, et al.
Publicado: (2025)

StoryMem: Multi-shot Long Video Storytelling with Memory
por: Zhang, Kaiwen, et al.
Publicado: (2025)

FluxMem: Adaptive Hierarchical Memory for Streaming Video Understanding
por: Xie, Yiweng, et al.
Publicado: (2026)

Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models
por: Chen, Kaijin, et al.
Publicado: (2026)

HaluMem: Evaluating Hallucinations in Memory Systems of Agents
por: Chen, Ding, et al.
Publicado: (2025)

WorldMemArena: Evaluating Multimodal Agent Memory Through Action-World Interaction
por: Liu, Chengzhi, et al.
Publicado: (2026)

RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction
por: Bian, Haonan, et al.
Publicado: (2026)

Chameleon: Automated Color Palette Adaptation for Dark Mode Data Visualizations
por: Karunathilaka, Manusha, et al.
Publicado: (2025)

PWM: Policy Learning with Multi-Task World Models
por: Georgiev, Ignat, et al.
Publicado: (2024)

FlashMem: Distilling Intrinsic Latent Memory via Computation Reuse
por: Hou, Yubo, et al.
Publicado: (2026)

Video World Models with Long-term Spatial Memory
por: Wu, Tong, et al.
Publicado: (2025)

MemEmo: Evaluating Emotion in Memory Systems of Agents
por: Liu, Peng, et al.
Publicado: (2026)

OmniMem: Scalable and Adaptive Memory Retrieval for Long Video Generation
por: Zhao, Lin, et al.
Publicado: (2026)

VideoMem: Enhancing Ultra-Long Video Understanding via Adaptive Memory Management
por: Jin, Hongbo, et al.
Publicado: (2025)

Spatial Metaphors for LLM Memory: A Critical Analysis of the MemPalace Architecture
por: Dey, Robin, et al.
Publicado: (2026)

MemFactory: Unified Inference & Training Framework for Agent Memory
por: Guo, Ziliang, et al.
Publicado: (2026)

Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment Network
por: Shu, Yong, et al.
Publicado: (2024)

ReinforceGen: Hybrid Skill Policies with Automated Data Generation and Reinforcement Learning
por: Zhou, Zihan, et al.
Publicado: (2025)

Mem3R: Streaming 3D Reconstruction with Hybrid Memory via Test-Time Training
por: Liu, Changkun, et al.
Publicado: (2026)

On the Conjecture of Stability Preservation in Arbitrary-Order Adams-Bashforth-Type Integrators
por: Yin, Daopeng, et al.
Publicado: (2025)

Asymptotically Compatible Fractional Grönwall Inequality and its Applications
por: Yin, Daopeng, et al.
Publicado: (2024)

Vision-Language Models Assisted Unsupervised Video Anomaly Detection
por: Jiang, Yalong, et al.
Publicado: (2024)

Mem-T: Densifying Rewards for Long-Horizon Memory Agents
por: Yue, Yanwei, et al.
Publicado: (2026)