Skip to content

Author

Kanchan Sarkar

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

ViTok: Improving Dense Semantics in AM-RADIO-Style Multi-Teacher Distillation with PHI-S and Masked Image Modelling

We study how to consolidate the current VITOK progress into a single multi-teacher distillation recipe that jointly preserves global recognition and dense semantics. Our starting point is an AM-RADIO-style student distilled from SigLIP2 and DINOv3-L, where SigLIP2 supplies strong global semantics and DINOv3-L supplies...

Hai-Lun Xu, Kanchan Sarkar · 0 citations
#machine learning Preprint Sep 2026

Loop Dropout: Regularizing Shared Updates in Looped Language Models

Loop Dropout is introduced, which couples stochastic masking of adapter applications with inverse-survival rescaling to preserve expected update strength and promote effective adaptation across loops and outperforms existing LoRA variants and adapter regularizers.

Zi-Rui Zhu, Hai-Lun Xu, Xuan-Lei Zhao et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.