Mark Ibrahim

OpenApps: Simulating Environment Variations to Measure UI Agent Reliability

LLM knowledge is brittle: truthfulness representations rely on superficial resemblance

A Single Character Can Make or Break your LLM Evals

Joint‑Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self‑Supervised Learning

Rethinking the Role of Verbatim Memorization in LLM Privacy

$\mathbb{X}$-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs

Transformers Can Navigate Mazes With Multi-Step Prediction

Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations