Baharan Mirzasoleiman
~Baharan_Mirzasoleiman1
12
论文总数
6.0
年均投稿
平均评分
接收情况9/12
会议分布
ICLR
8
ICML
2
NeurIPS
2
发表论文 (12 篇)
20255 篇
4
Memory-Efficient Self-Supervised Contrastive Learning with a Supervised Loss
ICLR 2025Rejected
4
Dataset Distillation via Knowledge Distillation: Towards Efficient Self-Supervised Pre-training of Deep Networks
ICLR 2025Poster
3
Representations Shape Weak-to-Strong Generalization: Theoretical Insights and Empirical Predictions
ICML 2025Poster
4
Mini-batch Coresets for Memory-efficient Language Model Training on Data Mixtures
ICLR 2025Poster
4
Synthetic Text Generation for Training Large Language Models via Gradient Matching
ICML 2025Poster
20247 篇
3
Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks
ICLR 2024Rejected
-
Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias
ICLR 2024withdrawn
4
Changing the Training Data Distribution to Reduce Simplicity Bias Improves In-distribution Generalization
NeurIPS 2024Poster
3
Data Distillation Can Be Like Vodka: Distilling More Times For Better Quality
ICLR 2024Poster
4
SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models
NeurIPS 2024Poster
4
Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shift
ICLR 2024Poster
4
Investigating the Benefits of Projection Head for Representation Learning
ICLR 2024Poster