No article text was recorded for this version.
high-norm outlier tokens
Version 1 of 124 papers34 conceptsfrozen 2026-10-04
Papers in this version
- Blog: DAMRO: Dive into the Attention Mechanism of LVLM to Reduce Object Hallucination
- Blog: Feature Purification Matters: Suppressing Outlier Propagation for Training-Free Open-Vocabulary Semantic Segmentation
- Blog: Mamba-R: Vision Mamba ALSO Needs Registers
- Blog: Vision Transformers Need Registers
- Blog: Vision Transformers Don't Need Trained Registers
- Blog: CAV-MAE Sync: Improving Contrastive Audio-Visual Mask Autoencoders via Fine-Grained Alignment
- Blog: Mamba-Reg: Vision Mamba Also Needs Registers
- Blog: Leveraging Registers in Vision Transformers for Robust Adaptation
- Blog: Registers Matter for Pixel-space Diffusion Transformers
- Blog: SiNGER: A Clearer Voice Distills Vision Transformers Further
- Blog: Enhancing Concept Localization in CLIP-based Concept Bottleneck Models
- Blog: Attention Hijackers: Detect and Disentangle Attention Hijacking in LVLMs for Hallucination Mitigation
- Blog: Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models
- Blog: Adaptive Patch Contrast for Weakly Supervised Semantic Segmentation
- Blog: ERICT: Enhancing Robustness by Identifying Concept Tokens in Zero-Shot Vision Language Models
- Blog: Improving Visual Discriminability of CLIP for Training-Free Open-Vocabulary Semantic Segmentation
- Blog: Unleashing Diffusion Transformers for Visual Correspondence by Modulating Massive Activations
- Blog: Vision Transformers with Self-Distilled Registers
- Blog: DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformers
- Blog: Don't Miss the Forest for the Trees: Attentional Vision Calibration for Large Vision Language Models
- Blog: Self-Calibrated CLIP for Training-Free Open-Vocabulary Segmentation
- Blog: DEX-AR: A Dynamic Explainability Method for Autoregressive Vision-Language Models
- Blog: Transferable Adversarial Attacks on Vision Transformers with Token Gradient Regularization
- Blog: SINDER: Repairing the Singular Defects of DINOv2
History & citation
Current · Permanent link
- This direction split from Register Tokens and Attention Sinks in Vision Transformers (79% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_high_norm_outlier_tokens_96c5b35e,
title = {high-norm outlier tokens},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/high-norm-outlier-tokens/rdr_96c5b35e4970413c85c20af8fb6546a9},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_high_norm_outlier_tokens_96c5b35e_v1,
title = {high-norm outlier tokens},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/high-norm-outlier-tokens/rdr_96c5b35e4970413c85c20af8fb6546a9/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}