3 papers
cs.LG2026
Feature Geometry of LoRA Adapters: A Sparse Autoencoder Analysis of Representational Divergence in Fine-Tuned Language Models
Prasanth K K
Low-Rank Adaptation (LoRA) has emerged as a widely adopted approach for adapting large language models, yet the internal representational changes induced by LoRA fine-tuning remain…
cs.LG2025
EchoLSTM: A Self-Reflective Recurrent Network for Stabilizing Long-Range Memory
Prasanth K K, Shubham Sharma
Standard Recurrent Neural Networks, including LSTMs, struggle to model long-range dependencies, particularly in sequences containing noisy or misleading information. We propose a n…
cs.LG2025
Geometric Mixture Classifier (GMC): A Discriminative Per-Class Mixture of Hyperplanes
Prasanth K K, Shubham Sharma
Many real world categories are multimodal, with single classes occupying disjoint regions in feature space. Classical linear models (logistic regression, linear SVM) use a single g…