Scholar
Neil Band
Google Scholar ID: 2Dab2vkAAAAJ
Stanford University
Citations & Impact
Citations
975
H-index
10
i10-index
10
Publications
11
Co-authors
11
list available
Publications
Resume (English only)
Academic Achievements
- ICLR 2025 (Oral, top 1.8%): 'Synthetic Continued Pretraining' – a graph-based synthetic data generation and continued pretraining approach
- ICML 2024: 'Linguistic Calibration of Long-Form Generations' – an alignment objective for calibrated confidence in long-form outputs
- NeurIPS 2021 Datasets and Benchmarks Track (Spotlight, top 4.6%): 'Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks' – open-source expert-guided benchmark suite
- NeurIPS 2021: 'Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks' – industry-scale robustness and uncertainty evaluation tasks
- NeurIPS 2021: 'Self-Attention Between Datapoints' – a novel architecture processing entire datasets via self-attention across datapoints
- arXiv 2025 preprint: 'Reasoning to Learn from Latent Thoughts' – bootstrapping LM capabilities by inferring latent thoughts in pretraining documents
