ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Harsh Rangwani

Harsh Rangwani

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 15, 2026, 5:10 AM AMS

10

papers

124

total citations

papers (10)

Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data

NEURIPS 2022arXiv

Improving GANs for Long-Tailed Data through Group Spectral Regularization

NoisyTwins: Class-Consistent and Diverse Image Generation Through StyleGANs

DeiT-LT: Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets

Hierarchical Semantic Regularization of Latent Spaces in StyleGANs

Strata-NeRF : Neural Radiance Fields for Stratified Scenes

Cost-Sensitive Self-Training for Optimizing Non-Decomposable Metrics

NEURIPS 2022arXiv

Composing Parts for Expressive Object Generation

Selective Mixup Fine-Tuning for Optimizing Non-Decomposable Objectives

S3VAADA: Submodular Subset Selection for Virtual Adversarial Active Domain Adaptation