VAR-Q: Tuning-free KV Cache Quantization for Visual Autoregressive Image and Video Generation
cs.CV, cs.PF
Submitted: 2026-07-12
Updated: 2026-07-12
Terminology
Sources
- FireQ: Fast INT4-FP8 Kernel and RoPE-aware Quantization for LLM Inference Acceleration
- ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment
- Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion
- SpinQuant: LLM quantization with learned rotations
- KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
- Movie Gen: A Cast of Media Foundation Models
- Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization
- LongLive: Real-time Interactive Long Video Generation
- VecInfer: Efficient LLM Inference with Low-Bit KV Cache via Outlier-Suppressed Vector Quantization
- The Super Weight in Large Language Models
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