Decoding Register Tokens Preserves Global Scene Details

The paper investigates whether keeping non‑spatial register tokens in vision transformer decoders improves image reconstruction and generation. Using representation autoencoders with frozen register‑equipped encoders, the authors show that joint self‑attention over both patch and register tokens yields better reconstruction quality on ImageNet‑1K, with lower FID scores and higher PSNRs compared to patch‑only baselines. For generation, a multi‑head attention pooling predictor recovers register features from sampled patches, further reducing FID by nearly 10% over the patch‑only approach.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

• llms
• diffusion