Latest Research in Neural Compute Optimization

Top Research Topics in Neural Compute Optimization

• Machine Learning — 263 papers
• Computer Vision and Pattern Recognition — 63 papers
• Hardware Architecture — 33 papers
• Artificial Intelligence — 30 papers
• Distributed, Parallel, and Cluster Computing — 30 papers
• Machine Learning — 22 papers
• Advanced Neural Network Applications — 22 papers
• Computation and Language — 14 papers
• Parallel Computing and Optimization Techniques — 12 papers
• Domain Adaptation and Few-Shot Learning — 12 papers

Highest-Cited Papers

1. Model-Based Learning of Whittle indices (1 citations)
2. Model Inversion Attacks Through Target-Specific Conditional Diffusion Models (2 citations)
3. Physics Structure-Informed Neural Networks in the TinyML Pipeline: Antisymmetry Preservation, Deployment Accounting, and Training-Budget Sensitivity (1 citations)
4. Precision-Aware Variable Bit Processing Elements for Hardware-Efficient Systolic Array Designs
5. Computation of Strong Solutions to Stochastic Variational Inequalities
6. Does Recursive Model Succession Change Decision Reproducibility by a Simple Rule? A Pre-Specified 600-Cell Lineage Study
7. Hoeffding adaptive splitting trees for data stream classification with concept drift and ensemble learning
8. Automatic Generation of Deep Learning Models Based on Heterogeneous Pre-Trained Model Stitching
9. Grokking the Discrete Logarithm: Scaling Across Model Capacity and Mechanistic Analysis
10. Does Recursive Model Succession Change Decision Reproducibility by a Simple Rule? A Pre-Specified 600-Cell Lineage Study
11. A Statistical Perspective on Knowledge Distillation: Foundations, Classical Methods, and Large Language Model Extensions
12. Stop-and-Go Distractions: Measuring the Effects of Fragmented Inputs on Recurrent Networks
13. Avoid wasted annotation costs in open-set active learning with pre-trained vision–language model
14. ADEM: Accelerating Sparse Matrix Multiplication with Adaptive Dataflow and Efficient Merging
15. Direction-aware multi-label feature selection via paired signed-deviation lifting
16. Stop-and-Go Distractions: Measuring the Effects of Fragmented Inputs on Recurrent Networks
17. Grokking the Discrete Logarithm: Scaling Across Model Capacity and Mechanistic Analysis
18. Attributing Preprocessing Invariance in Spectral Foundation Models
19. A Logarithmic Regret Bound for Optimistic Hedge in General-Sum Games
20. The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction

Sub-Regions

• Hardware Architecture — 99 papers
• Advanced Neural Network Applications — 59 papers
• Parallel Computing and Optimization Techniques — 58 papers
• Distributed, Parallel, and Cluster Computing — 57 papers
• Machine Learning — 41 papers
• Signal Processing — 32 papers