Diana Marculescu

Identifiers

• name variant Diana Marculescu 0.60 · backfill

Papers (22)

1. DARE: Diffusion Language Model Activation Reuse for Efficient Inference cs.LG · 2026 · author #6
2. Video Compression Meets Video Generation: Latent Inter-Frame Pruning with Attention Recovery cs.CV · 2026 · author #9
3. Single-Path NAS: Device-Aware Efficient ConvNet Design cs.LG · 2019 · author #7
4. Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours cs.LG · 2019 · author #7
5. FLightNNs: Lightweight Quantized Deep Neural Networks for Fast and Accurate Inference cs.CV · 2019 · author #4
6. Regularizing Activation Distribution for Training Binarized Deep Networks cs.CV · 2019 · author #4
7. AdaScale: Towards Real-time Video Object Detection Using Adaptive Scaling cs.CV · 2019 · author #3
8. Understanding the Impact of Label Granularity on CNN-based Image Classification cs.CV · 2019 · author #4
9. Layer-compensated Pruning for Resource-constrained Convolutional Neural Networks cs.CV · 2018 · author #3
10. Hardware-Aware Machine Learning: Modeling and Optimization cs.LG · 2018 · author #1
11. Designing Adaptive Neural Networks for Energy-Constrained Image Classification cs.LG · 2018 · author #7
12. Tractable Learning and Inference for Large-Scale Probabilistic Boolean Networks cs.LG · 2018 · author #2
13. Priority-Aware Near-Optimal Scheduling for Heterogeneous Multi-Core Systems with Specialized Accelerators cs.PF · 2017 · author #2
14. Task Scheduling for Heterogeneous Multicore Systems cs.PF · 2017 · author #2
15. HyperPower: Power- and Memory-Constrained Hyper-Parameter Optimization for Neural Networks cs.LG · 2017 · author #4
16. On-Chip Communication Network for Efficient Training of Deep Convolutional Networks on Heterogeneous Manycore Systems cs.DC · 2017 · author #6
17. LightNN: Filling the Gap between Conventional Deep Neural Networks and Binarized Networks cs.NE · 2017 · author #4
18. Machine Learning and Manycore Systems Design: A Serendipitous Symbiosis cs.LG · 2017 · author #4
19. NeuralPower: Predict and Deploy Energy-Efficient Convolutional Neural Networks cs.LG · 2017 · author #4
20. M3A: Model, MetaModel, and Anomaly Detection in Web Searches cs.IR · 2016 · author #5
21. Thread Progress Equalization: Dynamically Adaptive Power and Performance Optimization of Multi-threaded Applications cs.DC · 2016 · author #4
22. Energy Bounds for Fault-Tolerant Nanoscale Designs cs.CC · 2007 · author #1

Mentions

• 0710.4680 #1 · backfill · confidence 0.70 Diana Marculescu

Frequent Coauthors

• Ruizhou Ding 7 shared papers
• Dimitrios Stamoulis 6 shared papers
• Ting-Wu Chin 6 shared papers
• Da-Cheng Juan 3 shared papers
• Ermao Cai 3 shared papers
• Radu Marculescu 3 shared papers
• Zeye Liu 3 shared papers
• Zhuo Chen 3 shared papers
• Bodhi Priyantha 2 shared papers
• Bokun Wang 2 shared papers
• Dimitrios Lymberopoulos 2 shared papers
• Di Wang 2 shared papers
• Janardhan Rao Doppa 2 shared papers
• Jie Liu 2 shared papers
• Partha Pratim Pande 2 shared papers
• Ryan Gary Kim 2 shared papers
• Anand Krishnan Prakash 1 shared papers
• Cha Zhang 1 shared papers
• Chenfeng Xu 1 shared papers
• Chi-Chih Chang 1 shared papers