collaborators

10 papers

cs.LG2026

Epiphany-Aware KV Cache Eviction Without the Attention Matrix

Steven Kolawole, Virginia Smith

As reasoning models emit chains of thought tens of thousands of tokens long, KV cache increasingly becomes a deployment bottleneck. Existing cache eviction methods rank tokens by a…

cs.LG2026

What Survives When You Compress a Recursive Reasoner for the Edge?

Pearse Jim, Steven Kolawole, Opegbemi Matthias Busoye +2

Recursive reasoning models can solve complex structured tasks with only a few million parameters by repeatedly updating a latent state. Deploying these models on edge hardware requ…

cs.LG2026

Open-Weight LLM Fine-Tuning Defenses are Susceptible to Simple Attacks

Kevin Kuo, Chhavi Yadav, Virginia Smith

Recent defenses for safeguarding open-weight large language models (LLMs) are intended to prevent adversarial usage. Underlying these defenses is an assumption that new harmful beh…

cs.LG2026

Curriculum Learning for Safety Alignment

Sandeep Kumar, Virginia Smith, Chhavi Yadav

Direct Preference Optimisation (DPO) is widely used for safety alignment in large language models. However, prior work shows it is brittle and exhibits poor out-of-distribution (OO…

cs.CL2026

Beyond LoRA vs. Full Fine-Tuning: Gradient-Guided Optimizer Routing for LLM Adaptation

Haozhan Tang, Xiuqi Zhu, Xinyin Zhang +3

Recent literature on fine-tuning Large Language Models highlights a fundamental debate. While Full Fine-Tuning (FFT) provides the representational plasticity required for high-entr…

cs.CL2026

Automated Concept Discovery for LLM-as-a-Judge Preference Analysis

James Wedgwood, Chhavi Yadav, Virginia Smith

Large Language Models (LLMs) are increasingly used as scalable evaluators of model outputs, but their preference judgments exhibit systematic biases and can diverge from human eval…