Baharan Mirzasoleiman

Beyond Semantic Entropy: Boosting LLM Uncertainty Quantification with Pairwise Semantic Similarity ACL 2025 Dataset Distillation via Knowledge Distillation: Towards Efficient Self-Supervised Pre-training of Deep Networks ICLR 2025 Mini-batch Coresets for Memory-efficient Language Model Training on Data Mixtures ICLR 2025 Representations Shape Weak-to-Strong Generalization: Theoretical Insights and Empirical Predictions ICML 2025 Synthetic Text Generation for Training Large Language Models via Gradient Matching ICML 2025 Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks ICML 2024 Changing the Training Data Distribution to Reduce Simplicity Bias Improves In-distribution Generalization NeurIPS 2024 Data Distillation Can Be Like Vodka: Distilling More Times For Better Quality ICLR 2024 Data-Efficient Contrastive Language-Image Pretraining: Prioritizing Data Quality over Quantity AISTATS 2024 Few-shot Adaptation to Distribution Shifts By Mixing Source and Target Embeddings ICML 2024 Graph Contrastive Learning under Heterophily via Graph Filters UAI 2024 Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias AISTATS 2024 Investigating the Benefits of Projection Head for Representation Learning ICLR 2024 Investigating the Impact of Model Width and Density on Generalization in Presence of Label Noise UAI 2024 NeWRF: A Deep Learning Framework for Wireless Radiation Field Reconstruction and Channel Prediction ICML 2024 SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models NeurIPS 2024 Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shift ICLR 2024 Data-Efficient Contrastive Self-supervised Learning: Most Beneficial Examples for Supervised Learning Contribute the Least ICML 2023 High Probability Bounds for Stochastic Continuous Submodular Maximization AISTATS 2023 Mitigating Spurious Correlations in Multi-modal Models during Fine-tuning ICML 2023 Robust Contrastive Language-Image Pretraining against Data Poisoning and Backdoor Attacks NeurIPS 2023 Robust Learning with Progressive Data Expansion Against Spurious Correlation NeurIPS 2023 Towards Sustainable Learning: Coresets for Data-efficient Deep Learning ICML 2023 Which Features are Learnt by Contrastive Learning? On the Role of Simplicity Bias in Class Collapse and Feature Suppression ICML 2023 Adaptive Second Order Coresets for Data-efficient Machine Learning ICML 2022 CrossWalk: Fairness-Enhanced Node Representation Learning AAAI 2022 Data-Efficient Augmentation for Training Neural Networks NeurIPS 2022 Friendly Noise against Adversarial Noise: A Powerful Defense against Data Poisoning Attack NeurIPS 2022 Investigating Why Contrastive Learning Benefits Robustness against Label Noise ICML 2022 Not All Poisons are Created Equal: Robust Training against Data Poisoning ICML 2022 Coresets for Data-efficient Training of Machine Learning Models ICML 2020 Coresets for Estimating Means and Mean Square Error with Limited Greedy Samples UAI 2020 Coresets for Robust Training of Deep Neural Networks against Noisy Labels NeurIPS 2020 Selection via Proxy: Efficient Data Selection for Deep Learning ICLR 2020 Dynamic Network Model from Partial Observations NeurIPS 2018 Deletion-Robust Submodular Maximization: Data Summarization with “the Right to be Forgotten” ICML 2017 Guaranteed Non-convex Optimization: Submodular Maximization over Continuous Domains AISTATS 2017 Distributed Submodular Maximization JMLR 2016 Fast Constrained Submodular Maximization: Personalized Data Summarization ICML 2016 Fast Distributed Submodular Cover: Public-Private Data Summarization NeurIPS 2016 Learning Sparse Combinatorial Representations via Two-stage Submodular Maximization ICML 2016 Distributed Submodular Cover: Succinctly Summarizing Massive Data NeurIPS 2015 Distributed Submodular Maximization: Identifying Representative Elements in Massive Data NeurIPS 2013