NanoKV: High-Ratio KV Cache Compression for Autoregressive Video Generation
cs.CV
Submitted: 2026-11-04
Updated: 2026-11-04
Terminology
Sources
- Focused Forcing: Content-Aware Per-Frame KV Selection for Efficient Autoregressive Video Diffusion
- Past- and Future-Informed KV Cache Policy with Salience Estimation in Autoregressive Video Diffusion
- Infinite Worlds with Versatile Interactions
- Efficient Autoregressive Video Diffusion with Dummy Head
- Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models
- PackCache: A Training-Free Acceleration Method for Unified Autoregressive Video Generation via Compact KV-Cache
- Future Forcing: Future-aware Training-free KV Cache Policy for Autoregressive Video Generation
- Sparse Forcing: Native Trainable Sparse Attention for Real-time Autoregressive Diffusion Video Generation
- VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video Diffusion
- WorldKV: Efficient World Memory with World Retrieval and Compression
- WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs