ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Baharan Mirzasoleiman

Baharan Mirzasoleiman

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 14, 2026, 7:30 PM AMS

15

papers

211

total citations

papers (15)

Robust Learning with Progressive Data Expansion Against Spurious Correlation

NEURIPS 2023arXiv

Friendly Noise against Adversarial Noise: A Powerful Defense against Data Poisoning Attack

NEURIPS 2022arXiv

NeWRF: A Deep Learning Framework for Wireless Radiation Field Reconstruction and Channel Prediction

Investigating the Benefits of Projection Head for Representation Learning

Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks

Data Distillation Can Be Like Vodka: Distilling More Times For Better Quality

Data-Efficient Augmentation for Training Neural Networks

NEURIPS 2022arXiv

Mini-batch Coresets for Memory-efficient Language Model Training on Data Mixtures

Synthetic Text Generation for Training Large Language Models via Gradient Matching

Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shift

Representations Shape Weak-to-Strong Generalization: Theoretical Insights and Empirical Predictions

Dataset Distillation via Knowledge Distillation: Towards Efficient Self-Supervised Pre-training of Deep Networks

Few-shot Adaptation to Distribution Shifts By Mixing Source and Target Embeddings

Coresets for Robust Training of Deep Neural Networks against Noisy Labels

Robust Contrastive Language-Image Pretraining against Data Poisoning and Backdoor Attacks