FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation

arXiv:2605.09430 · cs.CV · Submitted 2026-05-10 · Read on arXiv

cs.CV

Submitted: 2026-05-10

Updated: 2026-09-16

Terminology

• Adaptation — 30× in this paper · explained in 1 episode
• Ablation — 5× in this paper · explained in 1 episode
• Fine-Tuning — 5× in this paper · explained in 5 episodes
• Speculative Decoding — 5× in this paper · explained in 2 episodes
• Transformer — 5× in this paper · explained in 2 episodes
• Alignment — 3× in this paper · explained in 1 episode
• Block Diffusion — 3× in this paper · explained in 2 episodes
• Fidelity — 3× in this paper · explained in 2 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Diffusion Model — 2× in this paper · explained in 8 episodes
• Dynamic Gating Mechanism — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Abstraction — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Anisotropy — 1× in this paper · explained in 3 episodes
• Attention Mechanism — 1× in this paper · explained in 2 episodes
• Catastrophic Forgetting — 1× in this paper · explained in 5 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Diffusion Models — 1× in this paper · explained in 6 episodes
• Flow Matching — 1× in this paper · explained in 7 episodes
• Inception Score — 1× in this paper
• KV cache — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Linear Probing — 1× in this paper · explained in 2 episodes
• Nash Equilibrium — 1× in this paper · explained in 2 episodes
• Objective Function — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Scaling Laws — 1× in this paper · explained in 4 episodes
• Semantic Alignment — 1× in this paper · explained in 3 episodes
• Two-stage training — 1× in this paper · explained in 2 episodes

Sources

• Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
• Qwen Technical Report
• ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation
• OpenGPT-4o-Image: A Comprehensive Dataset for Advanced Image Generation and Editing
• Emu3.5: Native Multimodal Models are World Learners
• Uniform Discrete Diffusion with Metric Path for Video Generation
• Flex Attention: A Programming Model for Generating Optimized Attention Kernels
• LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models
• X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Again
• Classifier-Free Diffusion Guidance
• ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment
• T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation
• LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding
• Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation
• Autoregressive Image Generation with Randomized Parallel Decoding
• Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining
• Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model
• Layer by Layer: Uncovering Hidden Representations in Language Models
• Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation
• HART: Efficient Visual Generation with Hybrid Autoregressive Transformer

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