Nannan Zhu

Efficient Training with Foresight: Multi-Token Auxiliary Supervision for Autoregressive Image Generation

MTAR introduces multi-token prediction (MTP) to alleviate the sparsity and myopia of traditional NTP by imposing joint supervision on multiple future tokens; employs token-level contrastive regularization (TCR) to explicitly enhance the separability of sampled token representations and thereby improve representation di...