FIELD NOTES TOPIC
autoregressive models
3 notes, newest first.
HeadCast: Casting Attention Heads for Efficient Autoregressive Video Generation
Researchers propose HeadCast, a framework that improves the efficiency of autoregressive video diffusion models without requiring re-training. The framework categorizes attention heads into four types based on their…
Bridging Local Observation and Global Simulation in Closed-Loop Traffic Modeling
Researchers propose a method called CRAFT to improve traffic simulation in closed-loop environments. The proposed method aims to mitigate a local-to-global context mismatch that occurs when autoregressive traffic…
Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks
The authors propose a method for safe image generation using autoregressive unified multimodal models. They introduce Iterative Self-Improving Codebooks to eliminate harmful mappings in the codebook that could generate…
