# Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization

arXiv: https://arxiv.org/abs/2602.02958 · HTML: https://mlsanity.com/paper/2602.02958/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 26 of its 33 references that are in the map.
- First posted on arXiv 3 Feb 2026.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)
- Efficient LLM inference and serving / [Fast autoregressive visual generation](https://mlsanity.com/inference/fast-autoregressive-visual-generation/)

## Builds on (most cited first, 26 of 26)

- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion](https://mlsanity.com/paper/2407.01392/) (2024)
- [Movie Gen: A Cast of Media Foundation Models](https://mlsanity.com/paper/2410.13720/) (2024)
- [KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache](https://mlsanity.com/paper/2402.02750/) (2024)
- [QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs](https://mlsanity.com/paper/2404.00456/) (2024)
- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization](https://mlsanity.com/paper/2401.18079/) (2024)
- [From Slow Bidirectional to Fast Autoregressive Video Diffusion Models](https://mlsanity.com/paper/2412.07772/) (2024)
- [StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text](https://mlsanity.com/paper/2403.14773/) (2024)
- [FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling](https://mlsanity.com/paper/2310.15169/) (2023)
- [WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling](https://mlsanity.com/paper/2512.14614/) (2025)
- [WorldMem: Long-term Consistent World Simulation with Memory](https://mlsanity.com/paper/2504.12369/) (2025)
- [HunyuanVideo 1.5 Technical Report](https://mlsanity.com/paper/2511.18870/) (2025)
- [GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM](https://mlsanity.com/paper/2403.05527/) (2024)
- [Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models](https://mlsanity.com/paper/2504.12626/) (2025)
- [PQCache: Product Quantization-based KVCache for Long Context LLM Inference](https://mlsanity.com/paper/2407.12820/) (2024)
- [ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification](https://mlsanity.com/paper/2405.14256/) (2024)
- [FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention](https://mlsanity.com/paper/2407.19918/) (2024)
- [LongCat-Video Technical Report](https://mlsanity.com/paper/2510.22200/) (2025)
- [MotionStream: Real-Time Video Generation with Interactive Motion Controls](https://mlsanity.com/paper/2511.01266/) (2025)
- [RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers](https://mlsanity.com/paper/2502.15894/) (2025)
- [RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations](https://mlsanity.com/paper/2501.16383/) (2025)
- [SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models](https://mlsanity.com/paper/2405.06219/) (2024)
- [StreamDiffusionV2: A Streaming System for Dynamic and Interactive Video Generation](https://mlsanity.com/paper/2511.07399/) (2025)
- [KVSink: Understanding and Enhancing the Preservation of Attention Sinks in KV Cache Quantization for LLMs](https://mlsanity.com/paper/2508.04257/) (2025)
- [FreeLong++: Training-Free Long Video Generation via Multi-band SpectralFusion](https://mlsanity.com/paper/2507.00162/) (2025)

## Built on by (most cited first, 23 of 23)

- [LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation](https://mlsanity.com/paper/2605.18739/) (2026)
- [SLA2: Sparse-Linear Attention with Learnable Routing and QAT](https://mlsanity.com/paper/2602.12675/) (2026)
- [SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning](https://mlsanity.com/paper/2602.13515/) (2026)
- [ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU](https://mlsanity.com/paper/2607.19191/) (2026)
- [SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing](https://mlsanity.com/paper/2603.08982/) (2026)
- [SageBwd: A Trainable Low-bit Attention](https://mlsanity.com/paper/2603.02170/) (2026)
- [Future Forcing: Future-aware Training-free KV Cache Policy for Autoregressive Video Generation](https://mlsanity.com/paper/2605.30083/) (2026)
- [Advancing Narrative Long Video Generation via Training-Free Identity-Aware Memory](https://mlsanity.com/paper/2605.18733/) (2026)
- [SAW-INT4: System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving](https://mlsanity.com/paper/2604.19157/) (2026)
- [Attend Locally, Remember Linearly: Linear Attention as Cross-Frame Memory for Autoregressive Video Diffusion](https://mlsanity.com/paper/2605.16579/) (2026)
- [OmniMem: Scalable and Adaptive Memory Retrieval for Long Video Generation](https://mlsanity.com/paper/2605.30519/) (2026)
- [KV Cache Quantization for Self-Forcing Video Generation: A 33-Method Empirical Study](https://mlsanity.com/paper/2603.27469/) (2026)
- [Recurrent Residual Quantization: A Progressive Multi-Precision Representation for LLMs](https://mlsanity.com/paper/2608.04048/) (2026)
- [Quantized Keys Steal Attention: Bias Correction for KV-Cache Compression in Video Diffusion](https://mlsanity.com/paper/2605.26266/) (2026)
- [VC-Attention: Value Smoothing and Softmax Casting for Low-bit Attention](https://mlsanity.com/paper/2609.15810/) (2026)
- [Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation](https://mlsanity.com/paper/2609.20744/) (2026)
- [QuantWM: Temporally Consistent 2-Bit KV Cache Quantization for World Models and Video Generation](https://mlsanity.com/paper/2609.26425/) (2026)
- [DeCoPrune: Efficient KV-Cache Pruning for Autoregressive Video Diffusion via Denoising Consistency](https://mlsanity.com/paper/2609.39096/) (2026)
- [MosaiChunk: Compositing Spatio-Temporal Memory for Autoregressive Video Generation](https://mlsanity.com/paper/2610.02153/) (2026)
- [CORAL-KV: Compact Cross-Layer Prediction and Residual Coding for Autoregressive Video KV Caches](https://mlsanity.com/paper/2610.12514/) (2026)
- [FrameFold: Response-Guided KV Cache Consolidation for Autoregressive Long Video Generation](https://mlsanity.com/paper/2610.14568/) (2026)
- [TempoKV: Predictive KV Cache Quantization for Autoregressive Video Generation](https://mlsanity.com/paper/2610.15324/) (2026)
- [Into the LidarVerse: A Real-Time Unified LiDAR World Model Across Tasks and Sensors](https://mlsanity.com/paper/2610.19201/) (2026)

## Abstract (arXiv)

Despite rapid progress in autoregressive video diffusion, an emerging system algorithm bottleneck limits both deployability and generation capability: KV cache memory. In autoregressive video generation models, the KV cache grows with generation history and quickly dominates GPU memory, often exceeding 30 GB, preventing deployment on widely available hardware. More critically, constrained KV cache budgets restrict the effective working memory, directly degrading long horizon consistency in identity, layout, and motion. To address this challenge, we present Quant VideoGen (QVG), a training free KV cache quantization framework for autoregressive video diffusion models. QVG leverages video spatiotemporal redundancy through Semantic Aware Smoothing, producing low magnitude, quantization friendly residuals. It further introduces Progressive Residual Quantization, a coarse to fine multi stage scheme that reduces quantization error while enabling a smooth quality memory trade off. Across LongCat Video, HY WorldPlay, and Self Forcing benchmarks, QVG establishes a new Pareto frontier between quality and memory efficiency, reducing KV cache memory by up to 7.0 times with less than 4% end to end latency overhead while consistently outperforming existing baselines in generation quality. Code is available at: https://github.com/svg-project/Quant-VideoGen