register tokens
PulseAugur coverage of register tokens — every cluster mentioning register tokens across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New arXiv Paper Compares Image Tokenizer Strategies for Generative Models
A new arXiv paper by Philipp Schenkel compares two methods for creating variable-length image tokens for generative modeling: patch-derived tokens and register tokens. Patch-derived tokens are more computationally effic…
-
New method enhances image retrieval using region-aware tokens
Researchers have developed a novel method to enhance fine-grained image retrieval by augmenting the standard [CLS] token in vision transformers with region-aware spatial tokens. This approach, inspired by the ColBERT fr…
-
Vision Transformer tokens show specialization in semantic vs. background representation
Researchers have investigated the functional roles of specific token types within self-supervised Vision Transformers (ViTs), such as DINOv2. By training sparse autoencoders on register tokens and high-norm outlier patc…
-
Register tokens enhance pixel-space Diffusion Transformers, study finds
Researchers have investigated the utility of register tokens in Diffusion Transformers (DiTs), finding that while DiTs do not exhibit the same patch-token outliers as Vision Transformers (ViTs), they still benefit from …
-
Vision Transformers gain interpretability and performance with register tokens
Researchers have developed a new method using register tokens to improve the interpretability and performance of Vision Transformers (ViTs) for face recognition. By adding learnable register tokens to the initial patch …