← Authors

Baharan Mirzasoleiman

43 papers · 2013–2025 · 8 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (8) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird πŸƒ Academic Marathon (12) 🌈 Renaissance Researcher (6) πŸŒ‰ Interdisciplinary Bridge 🌍 Conference Polyglot (8) πŸ—ΊοΈ Taxonomy Completionist (22) 🌱 Topic Pioneer πŸ‘‘ Triple Crown πŸ† Keyword Champion (2) πŸ† Grand Slam 🀝 Dynamic Duo (10) ❓ The Questioner πŸ“ˆ Trend Setter ⚑ Prolific Year (6) πŸ—ƒοΈ Keyword Collector (57) πŸ’Ž Century Club (43)

Conferences

ICML (16) NIPS (11) ICLR (6) AISTATS (4) UAI (3) AAAI (1) ACL (1) JMLR (1)

Top co-authors

Yu Yang (10) Yihao Xue (7) Siddharth Joshi (6) Andreas Krause (6) Amin Karbasi (6) Jure Leskovec (4) Dang Nguyen (4) Eric Gan (4) Wenhan Yang (4) Tian Yu Liu (3)

Research topics

Privacy (2)

Keywords

submodular maximization (5) data summarization (5) submodular optimization (4) contrastive learning (4) data poisoning (3) subset selection (3) spurious correlation (3) approximation guarantee (3) simplicity bia (3) submodular function (3) gradient descent (3) coreset selection (3) stochastic gradient descent (3) distributed algorithm (3) distributed optimization (3) worst-group accuracy (3) inductive bia (2) data selection (2) non-convex optimization (2) adversarial robustness (2)

Papers

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