LLM News

Every LLM release, update, and milestone.

Filtered by:imagenet✕ clear
research

Researchers extend Vision Mamba sequence length 4x with separator-based pretraining

Researchers have introduced STAR (Separators for AutoRegressive pretraining), a method that extends Vision Mamba's input sequence length by 4x through strategic separator insertion between images. The STAR-B model achieved 83.5% accuracy on ImageNet-1k, demonstrating improved long-range dependency modeling in vision tasks.