Autoregressive Image Generation with Linear Complexity: A Spatial-Aware Decay Perspective
cs.CV, cs.AI, cs.MM
Submitted: 2025-07-02
Updated: 2026-11-02
Terminology
Sources
- Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation
- You Only Scan Once: Efficient Multi-dimension Sequential Modeling with LightNet
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- LLaMA: Open and Efficient Foundation Language Models
- DeepSeek-V3 Technical Report
- Scaling Laws for Linear Complexity Language Models
- MiniMax-01: Scaling Foundation Models with Lightning Attention
- Jamba: A Hybrid Transformer-Mamba Language Model
- Gated Linear Attention Transformers with Hardware-Efficient Training
- Retentive Network: A Successor to Transformer for Large Language Models
- HGRN2: Gated Linear RNNs with State Expansion
- MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention
- Vector-quantized Image Modeling with Improved VQGAN
- Auto-Encoding Variational Bayes
- Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
- Parallelized Autoregressive Visual Generation
- Next Patch Prediction for Autoregressive Visual Generation
- ZipAR: Parallel Auto-regressive Image Generation through Spatial Locality
- ImageFolder: Autoregressive Image Generation with Folded Tokens
- Scalable Autoregressive Image Generation with Mamba
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