CineMem: Attention-Aligned Fine-grained Memory Retrieval for Multi-Shot Long Video Generation
cs.CV, cs.AI
Submitted: 2026-10-13
Updated: 2026-10-13
Comments: Project Page: https://uknowsth.github.io/CineMem/
Code: https://github.com/LAION-AI/aesthetic-predictor
Project page: https://uknowsth.github.io/CineMem
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- GPT-4 Technical Report
- Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
- LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation
- ViD-GPT: Introducing GPT-style Autoregressive Generation in Video Diffusion Models
- End-to-End Training for Autoregressive Video Diffusion via Self-Resampling
- Long Context Tuning for Video Generation
- Animate-A-Story: Storytelling with Retrieval-Augmented Video Generation
- LongLive-RAG: A General Retrieval-Augmented Framework for Long Video Generation
- MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives
- Flow Matching for Generative Modeling
- RealWonder: Real-Time Physical Action-Conditioned Video Generation
- ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling
- CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives
- Score-Based Generative Modeling through Stochastic Differential Equations
- Wan: Open and Advanced Large-Scale Video Generative Models
- InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation
- DreamFactory: Pioneering Multi-Scene Long Video Generation with a Multi-Agent Framework
- LongLive: Real-time Interactive Long Video Generation
- OmniMem: Scalable and Adaptive Memory Retrieval for Long Video Generation
- VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models