2 papers
cs.LG2026
Mixture of Chapters: Scaling Learnt Memory in Transformers
Tasmay Pankaj Tibrewal, Pritish Saha, Ankit Meda +2
Transformers lack an explicit architectural mechanism for storing and organizing knowledge acquired during training. We introduce learnable sparse memory banks: a set of latent tok…
cs.LG2026
GRIT -- Geometry-Aware PEFT with K-FACPreconditioning, Fisher-Guided Reprojection, andDynamic Rank Adaptation
Pritish Saha, Chandrav Rajbangshi, Rudra Goyal +6
Parameter-efficient fine-tuning (PEFT) is the default way to adapt LLMs, but widely used LoRA and QLoRA are largely geometry-agnostic: they optimize in fixed, randomly oriented low…