Marian Viorel Craciun

15 papers B 1C 1Misc 1Journal 9Unranked 1
YearRankTypeTitle / Venue / Authors
2026 J jnl
EvalHack: Answer-Side Prompt Injection for Probing LLM Exam-Grading Panel Stability.
Inf.
Catalin Anghel, Marian Viorel Craciun, Adina Cocu, Andreea Alexandra Anghel, Antonio Stefan Balau, Adrian Istrate, Aurelian-Dumitrache Anghele
2026 J jnl
ExamQ-Gen: Instructor-in-the-Loop Generation of Self-Contained Exam Questions from Course Materials and Decision-Support Grading.
Comput.
Catalin Anghel, Emilia Pecheanu, Andreea Alexandra Anghel, Marian Viorel Craciun, Adina Cocu
2025 J jnl
CourseEvalAI: Rubric-Guided Framework for Transparent and Consistent Evaluation of Large Language Models.
Comput.
Catalin Anghel, Marian Viorel Craciun, Emilia Pecheanu, Adina Cocu, Andreea Alexandra Anghel, Paul Iacobescu, Calina Maier, Constantin Adrian Andrei, Cristian Scheau, Serban Dragosloveanu
2025 J jnl
EvalCouncil: A Committee-Based LLM Framework for Reliable and Unbiased Automated Grading.
Comput.
Catalin Anghel, Marian Viorel Craciun, Andreea Alexandra Anghel, Adina Cocu, Antonio Stefan Balau, Constantin Adrian Andrei, Calina Maier, Serban Dragosloveanu, Dana-Georgiana Nedelea, Cristian Scheau
2025 J jnl
GraderAssist: A Graph-Based Multi-LLM Framework for Transparent and Reproducible Automated Evaluation.
Informatics
Catalin Anghel, Andreea Alexandra Anghel, Emilia Pecheanu, Adina Cocu, Marian Viorel Craciun, Paul Iacobescu, Antonio Stefan Balau, Constantin Adrian Andrei
2025 J jnl
PEARL: A Rubric-Driven Multi-Metric Framework for LLM Evaluation.
Inf.
Catalin Anghel, Andreea Alexandra Anghel, Emilia Pecheanu, Marian Viorel Craciun, Adina Cocu, Cristian Niculita
2025 J jnl
SteadyEval: Robust LLM Exam Graders via Adversarial Training and Distillation.
Comput.
Catalin Anghel, Marian Viorel Craciun, Adina Cocu, Andreea Alexandra Anghel, Adrian Istrate
2008 — conf
A Hybrid Approach for Data Preprocessing in the QSAR Problem.
KES (1)
Adina Cocu, Luminita Dumitriu, Marian Viorel Craciun, Cristina Segal
2008 — ch.
Development of Multi-output Neural Networks for Data Integration - A Case Study.
Innovations in Hybrid Intelligent Systems
Paul R. Trundle, Daniel Neagu, Marian Viorel Craciun, Qasim Chaudhry
2008 — ch.
Pre-processing Techniques for the QSAR Problem.
New Trends in Multimedia and Network Information Systems
Luminita Dumitriu, Marian Viorel Craciun, Adina Cocu, Cristina Segal
2006 Misc conf
A Hybrid Feature Selection Algorithm for the QSAR Problem.
International Conference on Computational Science (1)
Marian Viorel Craciun, Adina Cocu, Luminita Dumitriu, Cristina Segal
2005 C conf
Hybrid Intelligent Systems for Predictive Toxicology - a Distributed Approach.
ISDA
Daniel Neagu, Marian Viorel Craciun, Silviu A. Stroia, Severin Bumbaru
2004 J jnl
Combining Unsupervised and Supervised Artificial Neural Networks to PredictAquatic Toxicity.
J. Chem. Inf. Model.
Giuseppina C. Gini, Marian Viorel Craciun, Christoph König, Emilio Benfenati
2004 J jnl
Multiclass Classifier From A Combination Of Local Experts: Toward Distributed Computation For Real-Problem Classifiers.
Int. J. Pattern Recognit. Artif. Intell.
Christoph König, Giuseppina C. Gini, Marian Viorel Craciun, Emilio Benfenati
2003 B conf
A Study of Aquatic Toxicity Using Artificial Neural Networks.
KES
Marian Viorel Craciun, Daniel Neagu, Christoph König, Severin Bumbaru