3 papers
cs.LG2026
Why LoRA Resists Label Noise: A Theoretical Framework for Noise-Robust Parameter-Efficient Fine-Tuning
Brady Steele
Parameter-efficient fine-tuning methods like Low-Rank Adaptation (LoRA) have become the dominant paradigm for adapting large pretrained models. We present a theoretical framework e…
cs.LG2026
On the Limits of Learned Importance Scoring for KV Cache Compression
Brady Steele
We investigate learned KV cache compression through Speculative Importance Prediction (SIP), a 1.7M parameter non-query-aware scorer that predicts token importance from KV represen…
cs.AI2026
Scaling Trends for Multi-Hop Contextual Reasoning in Mid-Scale Language Models
Brady Steele, Micah Katz
We present a controlled study of multi-hop contextual reasoning in large language models, providing a clean demonstration of the task-method dissociation: rule-based pattern matchi…