collaborators

11 papers

cs.DL2026

Submission Responsibility Matters: Role-Aware Submission Quotas under Coauthorship

Furkan Mumcu, Yasin Yilmaz

Author-level submission quotas are increasingly used to control growing peer-review load. Recent coauthorship-sensitive quota rules improve over fixed per-author limits by reducing…

cs.CV2026

Is Video Anomaly Detection Misframed? Evidence from LLM-Based and Multi-Scene Models

Furkan Mumcu, Michael J. Jones, Anoop Cherian +1

Recent video anomaly detection research has expanded rapidly with an emphasis on general models of normality intended to work across many different scenes. While this focus has led…

cs.LG2026

Detecting Adversarial Data via Provable Adversarial Noise Amplification

Furkan Mumcu, Yasin Yilmaz

The nonuniform and growing impact of adversarial noise across the layers of deep neural networks has been used in the literature, without a formal mathematical justification, to de…

cs.LG2026

Robustness of Agentic AI Systems via Adversarially-Aligned Jacobian Regularization

Furkan Mumcu, Yasin Yilmaz

As Large Language Models (LLMs) transition into autonomous multi-agent ecosystems, robust minimax training becomes essential yet remains prone to instability when highly non-linear…

cs.CV2026

Leveraging Multimodal LLM Descriptions of Activity for Explainable Semi-Supervised Video Anomaly Detection

Furkan Mumcu, Michael J. Jones, Anoop Cherian +1

Existing semi-supervised video anomaly detection (VAD) methods often struggle with detecting complex anomalies involving object interactions and generally lack explainability. To o…

cs.MA2026

Socially-Weighted Alignment: A Game-Theoretic Framework for Multi-Agent LLM Systems

Furkan Mumcu, Yasin Yilmaz

Deploying large language model (LLM) agents in shared environments introduces a fundamental tension between individual alignment and collective stability: locally rational decision…