SOURCE-LINKED INTELLIGENCE

Understanding and Exploiting Diagonal Attention Sparsity in Autoregressive Image Generation

arXiv · AI, language, vision and robotics · article · Sep 17, 2026 · UTC

Autoregressive image generation has emerged as a paradigm for multimodal AI systems due to its compatibility with transformer-based LLM serving infrastructures. However, generating thousands of visual tokens per request makes decoding increasingly bottlenecked by KV cache accesses during attention computation. Sparse attention is particularly attractive for this workload because many visual generation applications tolerate moderate quality degradation in exchange for improved performance and efficiency. While sparse attention has been extensively explored for text-based LLM inference, it remai

Read original source ↗ Open in workspace

recordType

paper

region

Global