6 papers
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…
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…
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…
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…
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…
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…