# Fast autoregressive visual generation

Area: [Efficient LLM inference and serving](https://mlsanity.com/inference/index.md). HTML: https://mlsanity.com/inference/fast-autoregressive-visual-generation/

## Key facts

- Fast autoregressive visual generation: 97 papers on arXiv since 2023 (data through 7 Oct 2026).
- 16 of its 97 mapped papers (16%) cite “Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding” (2024, arXiv 2410.01699).
- 14 of its 97 mapped papers (14%) cite “LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding” (2024, arXiv 2410.03355).
- 6 new papers 24 Sep–7 Oct.

## Most cited here

- [Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding](https://mlsanity.com/paper/2410.01699/) (2024), cited by 16 papers here
- [LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding](https://mlsanity.com/paper/2410.03355/) (2024), cited by 14 papers here
- [On Speculative Decoding for Multimodal Large Language Models](https://mlsanity.com/paper/2404.08856/) (2024), cited by 12 papers here
- [Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression](https://mlsanity.com/paper/2512.05081/) (2025), cited by 12 papers here
- [ZipAR: Parallel Auto-regressive Image Generation through Spatial Locality](https://mlsanity.com/paper/2412.04062/) (2024), cited by 10 papers here
- [ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding](https://mlsanity.com/paper/2509.15235/) (2025), cited by 10 papers here
- [FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning](https://mlsanity.com/paper/2503.23367/) (2025), cited by 8 papers here
- [SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruning](https://mlsanity.com/paper/2508.16201/) (2025), cited by 8 papers here
- [Head-Aware KV Cache Compression for Efficient Visual Autoregressive Modeling](https://mlsanity.com/paper/2504.09261/) (2025), cited by 7 papers here
- [DREAM: Drafting with Refined Target Features and Entropy-Adaptive Cross-Attention Fusion for Multimodal Speculative Decoding](https://mlsanity.com/paper/2505.19201/) (2025), cited by 7 papers here

## New (24 Sep–7 Oct)

- [LOCI: Spatial Linear Memory for Streaming World Models](https://mlsanity.com/paper/2609.40222/) (2026-09-30)
- [GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed](https://mlsanity.com/paper/2609.39600/) (2026-09-30)
- [DeCoPrune: Efficient KV-Cache Pruning for Autoregressive Video Diffusion via Denoising Consistency](https://mlsanity.com/paper/2609.39096/) (2026-09-30)
- [ReCaVSR: One-Step Streaming Diffusion Video Super-Resolution with Recycled Latents and Learned Cache Routing](https://mlsanity.com/paper/2609.37831/) (2026-09-29)
- [WorldAttention: An Efficient Attention Architecture for Interactive Video World Models](https://mlsanity.com/paper/2609.34606/) (2026-09-28)
- [In-Flight KV Cache with Clean Anchors for Faster Autoregressive Video Diffusion](https://mlsanity.com/paper/2609.32540/) (2026-09-26)