Baharan Mirzasoleiman
Scholar

Baharan Mirzasoleiman

Google Scholar ID: x63j7HEAAAAJ
UCLA
Machine LearningOptimizationSubmodularityML SustainabilityData-quality
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
3,564
 
H-index
28
 
i10-index
43
 
Publications
20
 
Co-authors
21
list available
Contact
No contact links provided.
Publications
18 items
Theoretical Perspectives on Data Quality and Synergistic Effects in Pre- and Post-Training Reasoning Models
2026
Cited
0
Beyond What Seems Necessary: Hidden Gains from Scaling Training-Time Reasoning Length under Outcome Supervision
2026
Cited
0
Data Distribution as a Lever for Guiding Optimizers Toward Superior Generalization in LLMs
2026
Cited
0
Tuning the Implicit Regularizer of Masked Diffusion Language Models: Enhancing Generalization via Insights from $k$-Parity
2026
Cited
1
Understanding the Role of Training Data in Test-Time Scaling
2025
Cited
0
Data Selection for Fine-tuning Vision Language Models via Cross Modal Alignment Trajectories
2025
Cited
0
LoRA is All You Need for Safety Alignment of Reasoning LLMs
2025
Cited
0
Beyond Semantic Entropy: Boosting LLM Uncertainty Quantification with Pairwise Semantic Similarity
2025
Cited
0
Resume (English only)
Co-authors
21 total
Andreas Krause
Andreas Krause
Professor of Computer Science, ETH Zurich
Amin Karbasi
Amin Karbasi
Cisco Foundation AI, ex Robust Intelligence Chief Scientist, ex Yale professor, ex Googler yale.edu
Jure Leskovec
Jure Leskovec
Professor of Computer Science, Stanford University
Co-author 4
Co-author 4
Co-author 5
Co-author 5
Co-author 6
Co-author 6
Rik Sarkar
Rik Sarkar
Reader (Associate Professor), University of Edinburgh
Mahdi Jalili
Mahdi Jalili
Professor at RMIT University, Melbourne, Australia