FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation

arXiv:2609.38839 · cs.CV · Submitted 2026-09-30 · Read on arXiv

cs.CV

Submitted: 2026-09-30

Updated: 2026-09-30

Project page: https://yinbo0927.github.io/FrameMorrow

Terminology

• Consistency — 43× in this paper · explained in 3 episodes
• Alignment — 14× in this paper · explained in 1 episode
• World Model — 11× in this paper · explained in 7 episodes
• Distillation — 8× in this paper · explained in 2 episodes
• Aggregation — 7× in this paper · explained in 1 episode
• Ablation — 6× in this paper · explained in 1 episode
• RAG — 6× in this paper · explained in 3 episodes
• Benchmark — 4× in this paper · explained in 2 episodes
• Conference on Computer Vision and Pattern Recognition — 4× in this paper
• Transformer — 4× in this paper · explained in 2 episodes
• Action-Conditioned World Model — 3× in this paper · explained in 1 episode
• KV cache — 3× in this paper · explained in 3 episodes
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Diffusion Model — 2× in this paper · explained in 8 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Generative Model — 2× in this paper · explained in 2 episodes
• Generative Models — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Alignment Scores — 1× in this paper · explained in 1 episode
• Diffusion Models — 1× in this paper · explained in 6 episodes
• Feature Extraction — 1× in this paper · explained in 2 episodes
• Multi-Agent System — 1× in this paper · explained in 6 episodes
• Multi-agent Collaboration — 1× in this paper · explained in 2 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes

Sources

• Past- and Future-Informed KV Cache Policy with Salience Estimation in Autoregressive Video Diffusion
• LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation
• LongLive-RAG: A General Retrieval-Augmented Framework for Long Video Generation
• MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives
• FrameOracle: Learning What to See and How Much to See in Videos
• Future Forcing: Future-aware Training-free KV Cache Policy for Autoregressive Video Generation
• ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling
• SkillGraph: Self-Evolving Multi-Agent Collaboration with Multimodal Graph Topology
• Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory
• Memento: Reconstruct to Remember for Consistent Long Video Generation
• LongLive: Real-time Interactive Long Video Generation
• DySink: Dynamic Frame Sinks for Autoregressive Long Video Generation
• Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression
• FeRA: Frequency-Energy Constrained Routing for Effective Diffusion Adaptation Fine-Tuning
• SPOT-E: Test-Time Entropy Shaping with Visual Spotlights for Frozen VLMs
• Dual Latent Memory for Visual Multi-agent System
• StoryMem: Multi-shot Long Video Storytelling with Memory
• EgoLCD: Egocentric Video Generation with Long Context Diffusion
• QuantWM: Temporally Consistent 2-Bit KV Cache Quantization for Video World Models

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