TempoKV: Predictive KV Cache Quantization for Autoregressive Video Generation
cs.CV
Submitted: 2026-10-11
Updated: 2026-10-11
Terminology
Sources
- Past- and Future-Informed KV Cache Policy with Salience Estimation in Autoregressive Video Diffusion
- SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models
- Efficient Autoregressive Video Diffusion with Dummy Head
- ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification
- StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text
- Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models
- CommVQ: Commutative Vector Quantization for KV Cache Compression
- 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
- LongCat-Video Technical Report
- Movie Gen: A Cast of Media Foundation Models
- RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations
- MAGI-1: Autoregressive Video Generation at Scale
- Wan: Open and Advanced Large-Scale Video Generative Models
- HunyuanVideo 1.5 Technical Report
- PQCache: Product Quantization-based KVCache for Long Context LLM Inference
- Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion 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