collaborators

6 papers

cs.CV2026

FigmaTrace: Capturing Creative Nuances in Human Figma Design Workflows

Darshan Deshpande, Yoshinari Fujinuma, Martyna Markiewicz +5

Vision Language Models have recently shown improvements in several objective and verifiable domains such as object detection but continue to underperform on subjective and creative…

cs.AI2026

TreeAgent: A Generalizable Multi-Agent Framework for Automated Bias Labeling in Forestry via Compiled Expert Rules and Vision-Language Models

Shiyi Chen, Nicholas Saban, Collin Hargreaves +1

Human-labeled data are widely used as reference annotations in ML, despite known variability across annotators in many expert-driven domains. In addition, expert annotation is slow…

cs.LG2026

FailureScope: Cross-Regime Behavioral Diagnosis of Language Model Weaknesses

Nicholas Saban

Standard benchmarks report aggregate accuracy, but practitioners need to know which specific capabilities a model lacks. We introduce FailureScope, a behavioral-diagnosis method th…

cs.CR2026

Domain-Conditioned Safety in Frontier Computer-Using Agents: A 793-Episode Browser Benchmark, a Coding-Domain Cross-Reference, and a Reproducibility Audit of Recent Red-Teaming

Nicholas Saban

Recent computer-using-agent (CUA) red-teaming papers report prompt-injection attack success rates (ASR) of 42-98%, but these headline numbers cluster on retired models and on the m…

cs.CR2025

AutoAdv: Automated Adversarial Prompting for Multi-Turn Jailbreaking of Large Language Models

Aashray Reddy, Andrew Zagula, Nicholas Saban

Large Language Models (LLMs) continue to exhibit vulnerabilities to jailbreaking attacks: carefully crafted malicious inputs intended to circumvent safety guardrails and elicit har…

cs.CL2025

AutoAdv: Automated Adversarial Prompting for Multi-Turn Jailbreaking of Large Language Models

Aashray Reddy, Andrew Zagula, Nicholas Saban

Large Language Models (LLMs) remain vulnerable to jailbreaking attacks where adversarial prompts elicit harmful outputs. Yet most evaluations focus on single-turn interactions whil…