| 2026 | FPGA | Striking the Balance: GEMM Performance Optimization Across Generations of Ryzen™ AI NPUs. | Endri Taka, Andre Roesti, Joseph Melber, Pranathi Vasireddy, Kristof Denolf, Diana Marculescu |
| 2026 | ISCAS | VeriMaAS: Automated Verilog Code Generation with Multi-Agent Reasoning. | Janani Ramamoorthy, Amulya Bhattaram, Ranit Gupta, Diana Marculescu, Dimitrios Stamoulis |
| 2025 | CVPR | Movie Weaver: Tuning-Free Multi-Concept Video Personalization with Anchored Prompts. | Feng Liang, Haoyu Ma, Zecheng He, Tingbo Hou, Ji Hou, Kunpeng Li, Xiaoliang Dai, Felix Juefei-Xu, Samaneh Azadi, Animesh Sinha, Peizhao Zhang, Peter Vajda, Diana Marculescu |
| 2025 | FPGA | Systolic Sparse Tensor Slices: FPGA Building Blocks for Sparse and Dense AI Acceleration. | Endri Taka, Ning-Chi Huang, Chi-Chih Chang, Kai-Chiang Wu, Aman Arora, Diana Marculescu |
| 2025 | ICLR | Quamba: A Post-Training Quantization Recipe for Selective State Space Models. | Hung-Yueh Chiang, Chi-Chih Chang, Natalia Frumkin, Kai-Chiang Wu, Diana Marculescu |
| 2025 | ICLR | Looking Backward: Streaming Video-to-Video Translation with Feature Banks. | Feng Liang, Akio Kodaira, Chenfeng Xu, Masayoshi Tomizuka, Kurt Keutzer, Diana Marculescu |
| 2025 | ICML | Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models. | Hung-Yueh Chiang, Chi-Chih Chang, Natalia Frumkin, Kai-Chiang Wu, Mohamed S. Abdelfattah, Diana Marculescu |
| 2025 | WACV | Ada-VE: Training-Free Consistent Video Editing Using Adaptive Motion Prior. | Tanvir Mahmud, Mustafa Munir, Radu Marculescu, Diana Marculescu |
| 2025 | WACV | Similarity Trajectories: Linking Sampling Process to Artifacts in Diffusion-Generated Images. | Dennis Menn, Feng Liang, Hung-Yueh Chiang, Diana Marculescu |
| 2024 | CVPR | ELSA: Exploiting Layer-wise N: M Sparsity for Vision Transformer Acceleration. | Ning-Chi Huang, Chi-Chih Chang, Wei-Cheng Lin, Endri Taka, Diana Marculescu, Kai-Chiang Wu |
| 2024 | CVPR | FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis. | Feng Liang, Bichen Wu, Jialiang Wang, Licheng Yu, Kunpeng Li, Yinan Zhao, Ishan Misra, Jia-Bin Huang, Peizhao Zhang, Peter Vajda, Diana Marculescu |
| 2024 | CVPR | MA-AVT: Modality Alignment for Parameter-Efficient Audio-Visual Transformers. | Tanvir Mahmud, Shentong Mo, Yapeng Tian, Diana Marculescu |
| 2024 | CVPR | T-VSL: Text-Guided Visual Sound Source Localization in Mixtures. | Tanvir Mahmud, Yapeng Tian, Diana Marculescu |
| 2024 | CVPR | Cache and Reuse: Rethinking the Efficiency of On-device Transfer Learning. | Yuedong Yang, Hung-Yueh Chiang, Guihong Li, Diana Marculescu, Radu Marculescu |
| 2024 | ECCV | PaPr: Training-Free One-Step Patch Pruning with Lightweight ConvNets for Faster Inference. | Tanvir Mahmud, Burhaneddin Yaman, Chun-Hao Liu, Diana Marculescu |
| 2024 | EMNLP | OpenSep: Leveraging Large Language Models with Textual Inversion for Open World Audio Separation. | Tanvir Mahmud, Diana Marculescu |
| 2024 | FCCM | Efficient Approaches for GEMM Acceleration on Leading AI-Optimized FPGAs. | Endri Taka, Dimitrios Gourounas, Andreas Gerstlauer, Diana Marculescu, Aman Arora |
| 2024 | ICLR | Weakly-supervised Audio Separation via Bi-modal Semantic Similarity. | Tanvir Mahmud, Saeed Amizadeh, Kazuhito Koishida, Diana Marculescu |
| 2024 | WACV | FLORA: Fine-grained Low-Rank Architecture Search for Vision Transformer. | Chi-Chih Chang, Yuan-Yao Sung, Shixing Yu, Ning-Chi Huang, Diana Marculescu, Kai-Chiang Wu |
| 2024 | WACV | SSVOD: Semi-Supervised Video Object Detection with Sparse Annotations. | Tanvir Mahmud, Chun-Hao Liu, Burhaneddin Yaman, Diana Marculescu |
| 2023 | AAAI | MobileTL: On-Device Transfer Learning with Inverted Residual Blocks. | Hung-Yueh Chiang, Natalia Frumkin, Feng Liang, Diana Marculescu |
| 2023 | CVPR | Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP. | Feng Liang, Bichen Wu, Xiaoliang Dai, Kunpeng Li, Yinan Zhao, Hang Zhang, Peizhao Zhang, Peter Vajda, Diana Marculescu |
| 2023 | ICASSP | CLIP4VideoCap: Rethinking Clip for Video Captioning with Multiscale Temporal Fusion and Commonsense Knowledge. | Tanvir Mahmud, Feng Liang, Yaling Qing, Diana Marculescu |
| 2023 | ICCV | Jumping through Local Minima: Quantization in the Loss Landscape of Vision Transformers. | Natalia Frumkin, Dibakar Gope, Diana Marculescu |
| 2023 | WACV | AVE-CLIP: AudioCLIP-based Multi-window Temporal Transformer for Audio Visual Event Localization. | Tanvir Mahmud, Diana Marculescu |
| 2022 | CVPR | ANT: Adapt Network Across Time for Efficient Video Processing. | Feng Liang, Ting-Wu Chin, Yang Zhou, Diana Marculescu |
| 2021 | CVPR | Width Transfer: On the (In)variance of Width Optimization. | Ting-Wu Chin, Diana Marculescu, Ari S. Morcos |
| 2021 | CVPR | Renofeation: A Simple Transfer Learning Method for Improved Adversarial Robustness. | Ting-Wu Chin, Cha Zhang, Diana Marculescu |
| 2021 | ISLPED | When Climate Meets Machine Learning: Edge to Cloud ML Energy Efficiency. | Diana Marculescu |
| 2020 | CVPR | Towards Efficient Model Compression via Learned Global Ranking. | Ting-Wu Chin, Ruizhou Ding, Cha Zhang, Diana Marculescu |
| 2020 | DATE | DeepNVM: A Framework for Modeling and Analysis of Non-Volatile Memory Technologies for Deep Learning Applications. | Ahmet Fatih Inci, Mehmet Meric Isgenc, Diana Marculescu |
| 2020 | ECCV | One Weight Bitwidth to Rule Them All. | Ting-Wu Chin, Pierce I-Jen Chuang, Vikas Chandra, Diana Marculescu |
| 2020 | KDD | Edge AI: Systems Design and ML for IoT Data Analytics. | Radu Marculescu, Diana Marculescu, mit Y. Ogras |
| 2020 | WACV | ViP: Virtual Pooling for Accelerating CNN-based Image Classification and Object Detection. | Zhuo Chen, Jiyuan Zhang, Ruizhou Ding, Diana Marculescu |
| 2019 | CVPR | Regularizing Activation Distribution for Training Binarized Deep Networks. | Ruizhou Ding, Ting-Wu Chin, Zeye Liu, Diana Marculescu |
| 2019 | DAC | FLightNNs: Lightweight Quantized Deep Neural Networks for Fast and Accurate Inference. | Ruizhou Ding, Zeye Liu, Ting-Wu Chin, Diana Marculescu, R. D. (Shawn) Blanton |
| 2018 | ASPDAC | Quantized deep neural networks for energy efficient hardware-based inference. | Ruizhou Ding, Zeye Liu, R. D. (Shawn) Blanton, Diana Marculescu |
| 2018 | DATE | HyperPower: Power- and memory-constrained hyper-parameter optimization for neural networks. | Dimitrios Stamoulis, Ermao Cai, Da-Cheng Juan, Diana Marculescu |
| 2018 | ICCAD | Hybrid on-chip communication architectures for heterogeneous manycore systems. | Biresh Kumar Joardar, Janardhan Rao Doppa, Partha Pratim Pande, Diana Marculescu, Radu Marculescu |
| 2018 | ICCAD | Hardware-aware machine learning: modeling and optimization. | Diana Marculescu, Dimitrios Stamoulis, Ermao Cai |
| 2018 | ICCAD | Designing adaptive neural networks for energy-constrained image classification. | Dimitrios Stamoulis, Ting-Wu (Rudy) Chin, Anand Krishnan Prakash, Haocheng Fang, Sribhuvan Sajja, Mitchell Bognar, Diana Marculescu |
| 2018 | ICDM | Understanding the Impact of Label Granularity on CNN-Based Image Classification. | Zhuo Chen, Ruizhou Ding, Ting-Wu Chin, Diana Marculescu |
| 2017 | ACML | \emphNeuralPower: Predict and Deploy Energy-Efficient Convolutional Neural Networks. | Ermao Cai, Da-Cheng Juan, Dimitrios Stamoulis, Diana Marculescu |
| 2017 | DSAA | M3A: Model, MetaModel and Anomaly Detection for Inter-arrivals of Web Searches and Postings. | Da-Cheng Juan, Neil Shah, Mingyu Tang, Zhiliang Qian, Diana Marculescu, Christos Faloutsos |
| 2016 | CASES | Hybrid network-on-chip architectures for accelerating deep learning kernels on heterogeneous manycore platforms. | Wonje Choi, Karthi Duraisamy, Ryan Gary Kim, Janardhan Rao Doppa, Partha Pratim Pande, Radu Marculescu, Diana Marculescu |
| 2016 | ICCAD | Exploring aging deceleration in FinFET-based multi-core systems. | Ermao Cai, Dimitrios Stamoulis, Diana Marculescu |
| 2016 | ISLPED | Can We Guarantee Performance Requirements under Workload and Process Variations? | Dimitrios Stamoulis, Diana Marculescu |
| 2015 | DAC | Energy efficient MapReduce with VFI-enabled multicore platforms. | Karthi Duraisamy, Ryan Gary Kim, Wonje Choi, Guangshuo Liu, Partha Pratim Pande, Radu Marculescu, Diana Marculescu |
| 2015 | DATE | Distributed reinforcement learning for power limited many-core system performance optimization. | Zhuo Chen, Diana Marculescu |
| 2015 | ICCAD | Statistical Learning in Chip (SLIC). | Ronald D. Blanton, Xin Li, Ken Mai, Diana Marculescu, Radu Marculescu, Jeyanandh Paramesh, Jeff G. Schneider, Donald E. Thomas |
| 2015 | ICCAD | TEI-Turbo: Temperature Effect Inversion-Aware Turbo Boost for FinFET-Based Multi-Core Systems. | Ermao Cai, Diana Marculescu |
| 2015 | ICCAD | The (Low) Power of Less Wiring: Enabling Energy Efficiency in Many-Core Platforms Through Wireless NoC. | Partha Pratim Pande, Ryan Gary Kim, Wonje Choi, Zhuo Chen, Diana Marculescu, Radu Marculescu |
| 2014 | ASPDAC | A comprehensive and accurate latency model for Network-on-Chip performance analysis. | Zhiliang Qian, Da-Cheng Juan, Paul Bogdan, Chi-Ying Tsui, Diana Marculescu, Radu Marculescu |
| 2014 | CASES | Energy-efficient VFI-partitioned multicore design using wireless NoC architectures. | Ryan Gary Kim, Guangshuo Liu, Paul Wettin, Radu Marculescu, Diana Marculescu, Partha Pratim Pande |
| 2014 | DAC | The EDA Challenges in the Dark Silicon Era: Temperature, Reliability, and Variability Perspectives. | Muhammad Shafique, Siddharth Garg, Jrg Henkel, Diana Marculescu |
| 2014 | PAKDD | Beyond Poisson: Modeling Inter-Arrival Time of Requests in a Datacenter. | Da-Cheng Juan, Lei Li, Huan-Kai Peng, Diana Marculescu, Christos Faloutsos |
| 2013 | DAC | Dynamic behavior of cell signaling networks: model design and analysis automation. | Natasa Miskov-Zivanov, Diana Marculescu, James R. Faeder |
| 2013 | DAC | HaDeS: architectural synthesis for <u>h</u>eterogeneous <u>d</u>ark <u>s</u>ilicon chip multi-processors. | Yatish Turakhia, Bharathwaj Raghunathan, Siddharth Garg, Diana Marculescu |
| 2013 | DATE | SVR-NoC: a performance analysis tool for network-on-chips using learning-based support vector regression model. | Zhiliang Qian, Da-Cheng Juan, Paul Bogdan, Chi-Ying Tsui, Diana Marculescu, Radu Marculescu |
| 2013 | DATE | Cherry-picking: exploiting process variations in dark-silicon homogeneous chip multi-processors. | Bharathwaj Raghunathan, Yatish Turakhia, Siddharth Garg, Diana Marculescu |
| 2013 | ICASSP | Hardware-efficient stereo estimation using a residual-based approach. | Abhishek A. Sharma, Kaustubh Neelathalli, Diana Marculescu, Eriko Nurvitadhi |
| 2013 | ICCD | Dynamic thread mapping for high-performance, power-efficient heterogeneous many-core systems. | Guangshuo Liu, Jinpyo Park, Diana Marculescu |
| 2013 | ISCAS | Impact of manufacturing process variations on performance and thermal characteristics of 3D ICs: Emerging challenges and new solutions. | Da-Cheng Juan, Siddharth Garg, Diana Marculescu |
| 2012 | ASPDAC | A learning-based autoregressive model for fast transient thermal analysis of chip-multiprocessors. | Da-Cheng Juan, Huapeng Zhou, Diana Marculescu, Xin Li |
| 2012 | DATE | Statistical thermal modeling and optimization considering leakage power variations. | Da-Cheng Juan, Yi-Lin Chuang, Diana Marculescu, Yao-Wen Chang |
| 2012 | DATE | Mitigating lifetime underestimation: A system-level approach considering temperature variations and correlations between failure mechanisms. | Kai-Chiang Wu, Ming-Chao Lee, Diana Marculescu, Shih-Chieh Chang |
| 2012 | ISLPED | Power-aware performance increase via core/uncore reinforcement control for chip-multiprocessors. | Da-Cheng Juan, Diana Marculescu |
| 2011 | DATE | Statistical thermal evaluation and mitigation techniques for 3D Chip-Multiprocessors in the presence of process variations. | Da-Cheng Juan, Siddharth Garg, Diana Marculescu |
| 2011 | DATE | Aging-aware timing analysis and optimization considering path sensitization. | Kai-Chiang Wu, Diana Marculescu |
| 2011 | ICCAD | PRICE: Power reduction by placement and clock-network co-synthesis for pulsed-latch designs. | Yi-Lin Chuang, Hong-Ting Lin, Tsung-Yi Ho, Yao-Wen Chang, Diana Marculescu |
| 2011 | ISLPED | Analysis and mitigation of NBTI-induced performance degradation for power-gated circuits. | Kai-Chiang Wu, Diana Marculescu, Ming-Chao Lee, Shih-Chieh Chang |
| 2011 | VTS | Special session 4A: New topics parametric yield and reliability of 3D integrated circuits: New challenges and solutions. | Siddharth Garg, Diana Marculescu |
| 2010 | DAC | Formal modeling and reasoning for reliability analysis. | Natasa Miskov-Zivanov, Diana Marculescu |
| 2010 | DATE | Clock skew scheduling for soft-error-tolerant sequential circuits. | Kai-Chiang Wu, Diana Marculescu |
| 2010 | ICCAD | Process variation aware performance modeling and dynamic power management for multi-core systems. | Siddharth Garg, Diana Marculescu, Sebastian Herbert |
| 2010 | ISLPED | Custom feedback control: enabling truly scalable on-chip power management for MPSoCs. | Siddharth Garg, Diana Marculescu, Radu Marculescu |
| 2009 | DAC | Technology-driven limits on DVFS controllability of multiple voltage-frequency island designs: a system-level perspective. | Siddharth Garg, Diana Marculescu, Radu Marculescu, mit Y. Ogras |
| 2009 | DATE | System-level process variability analysis and mitigation for 3D MPSoCs. | Siddharth Garg, Diana Marculescu |
| 2009 | DATE | Joint logic restructuring and pin reordering against NBTI-induced performance degradation. | Kai-Chiang Wu, Diana Marculescu |
| 2009 | HPCA | Variation-aware dynamic voltage/frequency scaling. | Sebastian Herbert, Diana Marculescu |
| 2009 | ISLPED | Integrating dynamic voltage/frequency scaling and adaptive body biasing using test-time voltage selection. | Alyssa Bonnoit, Sebastian Herbert, Diana Marculescu, Lawrence T. Pileggi |
| 2008 | ASPDAC | Soft error rate reduction using redundancy addition and removal. | Kai-Chiang Wu, Diana Marculescu |
| 2008 | DAC | Characterizing chip-multiprocessor variability-tolerance. | Sebastian Herbert, Diana Marculescu |
| 2008 | DAC | Variation-adaptive feedback control for networks-on-chip with multiple clock domains. | mit Y. Ogras, Radu Marculescu, Diana Marculescu |
| 2008 | DATE | Design Variability: Challenges and Solutions at Microarchitecture-Architecture Level. | Diana Marculescu, Sani R. Nassif |
| 2008 | ICCAD | Process variability-aware transient fault modeling and analysis. | Natasa Miskov-Zivanov, Kai-Chiang Wu, Diana Marculescu |
| 2008 | ICCD | Power-aware soft error hardening via selective voltage scaling. | Kai-Chiang Wu, Diana Marculescu |
| 2007 | DAC | Voltage-Frequency Island Partitioning for GALS-based Networks-on-Chip. | mit Y. Ogras, Radu Marculescu, Puru Choudhary, Diana Marculescu |
| 2007 | DATE | Interactive presentation: System-level process variation driven throughput analysis for single and multiple voltage-frequency island designs. | Siddharth Garg, Diana Marculescu |
| 2007 | DATE | Soft error rate analysis for sequential circuits. | Natasa Miskov-Zivanov, Diana Marculescu |
| 2007 | DATE | An 0.9 1.2", low power, energy-harvesting system with custom multi-channel communication interface. | Phillip Stanley-Marbell, Diana Marculescu |
| 2007 | ISLPED | Analysis of dynamic voltage/frequency scaling in chip-multiprocessors. | Sebastian Herbert, Diana Marculescu |
| 2006 | DAC | MARS-C: modeling and reduction of soft errors in combinational circuits. | Natasa Miskov-Zivanov, Diana Marculescu |
| 2006 | ICCAD | System-level process-driven variability analysis for single and multiple voltage-frequency island systems. | Diana Marculescu, Siddharth Garg |
| 2005 | ASPDAC | Speed and voltage selection for GALS systems based on voltage/frequency islands. | Koushik Niyogi, Diana Marculescu |
| 2005 | DAC | Variability and energy awareness: a microarchitecture-level perspective. | Diana Marculescu, Emil Talpes |
| 2005 | DATE | Energy Bounds for Fault-Tolerant Nanoscale Designs. | Diana Marculescu |
| 2005 | ISCA | Increased Scalability and Power Efficiency by Using Multiple Speed Pipelines. | Emil Talpes, Diana Marculescu |
| 2005 | ISLPED | System level power and performance modeling of GALS point-to-point communication interfaces. | Koushik Niyogi, Diana Marculescu |
| 2004 | ASPDAC | Mixed-clock issue queue design for energy aware, high-performance cores. | Venkata Syam P. Rapaka, Emil Talpes, Diana Marculescu |
| 2004 | DATE | Local Decisions and Triggering Mechanisms for Adaptive Fault-Tolerance. | Phillip Stanley-Marbell, Diana Marculescu |
| 2004 | ICCD | Toward an Integrated Design Methodology for Fault-Tolerant, Multiple Clock/Voltage Integrated Systems. | Radu Marculescu, Diana Marculescu, Larry T. Pileggi |
| 2004 | ISLPED | Application adaptive energy efficient clustered architectures. | Diana Marculescu |
| 2004 | ISLPED | Impact of technology scaling on energy aware execution cache-based microarchitectures. | Emil Talpes, Diana Marculescu |
| 2003 | DATE | Dynamic Functional Unit Assignment for Low Power. | Steve Haga, Natasha Reeves, Rajeev Barua, Diana Marculescu |
| 2003 | DATE | Ambient Intelligence Visions and Achievements: Linking Abstract Ideas to Real-World Concepts. | Menno Lindwer, Diana Marculescu, Twan Basten, Rainer Zimmermann, Radu Marculescu, Stefan Jung, Eugenio Cantatore |
| 2003 | DATE | Pre-Characterization Free, Efficient Power/Performance Analysis of Embedded and General Purpose Software Applications. | Venkata Syam P. Rapaka, Diana Marculescu |
| 2003 | ICCAD | Fault-Tolerant Techniques for Ambient Intelligent Distributed Systems. | Diana Marculescu, Nicholas H. Zamora, Phillip Stanley-Marbell, Radu Marculescu |
| 2003 | ICCAD | Dynamic Fault-Tolerance and Metrics for Battery Powered, Failure-Prone Systems. | Phillip Stanley-Marbell, Diana Marculescu |
| 2003 | ISLPED | A mixed-clock issue queue design for globally asynchronous, locally synchronous processor cores. | Venkata Syam P. Rapaka, Diana Marculescu |
| 2003 | ISLPED | A critical analysis of application-adaptive multiple clock processors. | Emil Talpes, Diana Marculescu |
| 2002 | DAC | Challenges and opportunities in electronic textiles modeling and optimization. | Diana Marculescu, Radu Marculescu, Pradeep K. Khosla |
| 2002 | ICCAD | Power efficiency of voltage scaling in multiple clock, multiple voltage cores. | Anoop Iyer, Diana Marculescu |
| 2002 | ISCA | Power and Performance Evaluation of Globally Asynchronous Locally Synchronous Processors. | Anoop Iyer, Diana Marculescu |
| 2001 | DATE | Power aware microarchitecture resource scaling. | Anoop Iyer, Diana Marculescu |
| 2001 | ICCAD | Application-Driven Processor Design Exploration for Power-Performance Trade-off Analysis. | Diana Marculescu, Anoop Iyer |
| 2001 | ISLPED | Power reduction through work reuse. | Emil Talpes, Diana Marculescu |
| 2000 | ISLPED | Profile-driven code execution for low power dissipation (poster session). | Diana Marculescu |
| 1999 | ISLPED | Non-stationary effects in trace-driven power analysis. | Radu Marculescu, Diana Marculescu, Massoud Pedram |
| 1998 | DATE | Trace-Driven Steady-State Probability Estimation in FSMs with Application to Power Estimation. | Diana Marculescu, Radu Marculescu, Massoud Pedram |
| 1998 | ISLPED | Theoretical bounds for switching activity analysis in finite-state machines. | Diana Marculescu, Radu Marculescu, Massoud Pedram |
| 1997 | ASPDAC | Adaptive models for input data compaction for power simulators. | Radu Marculescu, Diana Marculescu, Massoud Pedram |
| 1997 | DAC | Sequence Compaction for Probabilistic Analysis of Finite-State Machines. | Diana Marculescu, Radu Marculescu, Massoud Pedram |
| 1997 | DAC | Hierarchical Sequence Compaction for Power Estimation. | Radu Marculescu, Diana Marculescu, Massoud Pedram |
| 1997 | ISLPED | Composite sequence compaction for finite-state machines using block entropy and high-order Markov models. | Radu Marculescu, Diana Marculescu, Massoud Pedram |
| 1996 | DAC | Stochastic Sequential Machine Synthesis Targeting Constrained Sequence Generation. | Diana Marculescu, Radu Marculescu, Massoud Pedram |
| 1996 | DAC | Improving the Efficiency of Power Simulators by Input Vector Compaction. | Chi-Ying Tsui, Radu Marculescu, Diana Marculescu, Massoud Pedram |
| 1995 | DAC | Efficient Power Estimation for Highly Correlated Input Streams. | Radu Marculescu, Diana Marculescu, Massoud Pedram |
| 1995 | ISLPED | Information theoretic measures of energy consumption at register transfer level. | Diana Marculescu, Radu Marculescu, Massoud Pedram |
| 1994 | ICCAD | Switching activity analysis considering spatiotemporal correlations. | Radu Marculescu, Diana Marculescu, Massoud Pedram |