Copertina

MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokens

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kim, Youngrae, Hu, Qixin, Kuo, C. -C. Jay, Beerel, Peter A.
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Infinity-RoPE: Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout
di: Yesiltepe, Hidir, et al.
Pubblicazione: (2025)

RedVTP: Training-Free Acceleration of Diffusion Vision-Language Models Inference via Masked Token-Guided Visual Token Pruning
di: Xu, Jingqi, et al.
Pubblicazione: (2025)

HIVTP: A Training-Free Method to Improve VLMs Efficiency via Hierarchical Visual Token Pruning Using Middle-Layer-Based Importance Score
di: Xu, Jingqi, et al.
Pubblicazione: (2025)

Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos
di: Feng, X., et al.
Pubblicazione: (2026)

ReRoPE: Repurposing RoPE for Relative Camera Control
di: Li, Chunyang, et al.
Pubblicazione: (2026)

Training-Free Efficient Video Generation via Dynamic Token Carving
di: Zhang, Yuechen, et al.
Pubblicazione: (2025)

DEVIAS: Learning Disentangled Video Representations of Action and Scene
di: Bae, Kyungho, et al.
Pubblicazione: (2023)

VideoRoPE: What Makes for Good Video Rotary Position Embedding?
di: Wei, Xilin, et al.
Pubblicazione: (2025)

RoPECraft: Training-Free Motion Transfer with Trajectory-Guided RoPE Optimization on Diffusion Transformers
di: Gokmen, Ahmet Berke, et al.
Pubblicazione: (2025)

SlotVTG: Object-Centric Adapter for Generalizable Video Temporal Grounding
di: Han, Jiwook, et al.
Pubblicazione: (2026)

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

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

Anchor Forcing: Anchor Memory and Tri-Region RoPE for Interactive Streaming Video Diffusion
di: Yang, Yang, et al.
Pubblicazione: (2026)

Advancing Narrative Long Video Generation via Training-Free Identity-Aware Memory
di: Liu, Jinzhuo, et al.
Pubblicazione: (2026)

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings
di: Xu, Jingqi, et al.
Pubblicazione: (2025)

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

BrainMem: Brain-Inspired Evolving Memory for Embodied Agent Task Planning
di: Ma, Xiaoyu, et al.
Pubblicazione: (2026)

UI-Mem: Self-Evolving Experience Memory for Online Reinforcement Learning in Mobile GUI Agents
di: Xiao, Han, et al.
Pubblicazione: (2026)

Infinite-Story: A Training-Free Consistent Text-to-Image Generation
di: Park, Jihun, et al.
Pubblicazione: (2025)

EVIDENT: Routing MLLM Adaptation through Entity-Grounded Visual Evidence for Cross-Domain Video Temporal Grounding
di: Ahn, Geo, et al.
Pubblicazione: (2026)

vid-TLDR: Training Free Token merging for Light-weight Video Transformer
di: Choi, Joonmyung, et al.
Pubblicazione: (2024)

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

MosaicMem: Hybrid Spatial Memory for Controllable Video World Models
di: Yu, Wei, et al.
Pubblicazione: (2026)

FIFO-Diffusion: Generating Infinite Videos from Text without Training
di: Kim, Jihwan, et al.
Pubblicazione: (2024)

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

FreeFlux: Understanding and Exploiting Layer-Specific Roles in RoPE-Based MMDiT for Versatile Image Editing
di: Wei, Tianyi, et al.
Pubblicazione: (2025)

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

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

$\infty$-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation
di: Santos, Saul, et al.
Pubblicazione: (2025)

Evolving Token Communication with Parametric Memory Network
di: Chen, Weixuan, et al.
Pubblicazione: (2026)

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

VideoMemory: Toward Consistent Video Generation via Memory Integration
di: Zhou, Jinsong, et al.
Pubblicazione: (2026)

Infinite-Homography as Robust Conditioning for Camera-Controlled Video Generation
di: Kim, Min-Jung, et al.
Pubblicazione: (2025)

MemOVCD: Training-Free Open-Vocabulary Change Detection via Cross-Temporal Memory Reasoning and Global-Local Adaptive Rectification
di: Kuang, Zuzheng, et al.
Pubblicazione: (2026)

LightCache: Memory-Efficient, Training-Free Acceleration for Video Generation
di: Xiao, Yang, et al.
Pubblicazione: (2025)

FreeAction: Training-Free Techniques for Enhanced Fidelity of Trajectory-to-Video Generation
di: Kim, Seungwook, et al.
Pubblicazione: (2025)

KTV: Keyframes and Key Tokens Selection for Efficient Training-Free Video LLMs
di: Song, Baiyang, et al.
Pubblicazione: (2026)

Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs
di: Hyun, Jeongseok, et al.
Pubblicazione: (2025)

Block Selective Reprogramming for On-device Training of Vision Transformers
di: Sarkar, Sreetama, et al.
Pubblicazione: (2024)

FreeSpec: Training-Free Long Video Generation via Singular-Spectrum Reconstruction
di: Chen, Fangda, et al.
Pubblicazione: (2026)