Behnam Neyshabur

Computer Science · Physical Sciences

35h-index6.7kcitations76works197.52yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Neural Networks and Applications(22), Advanced Neural Network Applications(15), Machine Learning and Data Classification(15), Domain Adaptation and Few-Shot Learning(14), Stochastic Gradient Optimization Techniques(13)

Publications74 total

Gemma 2: Improving Open Language Models at a Practical Size
arXiv (Cornell University)·2024· 125 citedOpen Access
Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models
arXiv (Cornell University)·2023· 6 citedOpen Access
Convexifying Transformers: Improving optimization and understanding of transformer networks
arXiv (Cornell University)·2022· 2 citedOpen Access
Layer-Stack Temperature Scaling
arXiv (Cornell University)·2022Open Access
REPAIR: REnormalizing Permuted Activations for Interpolation Repair
arXiv (Cornell University)·2022· 11 citedOpen Access
Teaching Algorithmic Reasoning via In-context Learning
arXiv (Cornell University)·2022· 23 citedOpen Access
Revisiting Neural Scaling Laws in Language and Vision
arXiv (Cornell University)·2022· 22 citedOpen Access
Exploring Length Generalization in Large Language Models
arXiv (Cornell University)·2022· 45 citedOpen Access
Solving Quantitative Reasoning Problems with Language Models
arXiv (Cornell University)·2022· 281 citedOpen Access
Long Range Language Modeling via Gated State Spaces
arXiv (Cornell University)·2022· 44 citedOpen Access
Understanding the effect of sparsity on neural networks robustness
arXiv (Cornell University)·2022· 3 citedOpen Access
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
arXiv (Cornell University)·2022· 546 citedOpen Access
Block-Recurrent Transformers
arXiv (Cornell University)·2022· 27 citedOpen Access
Data Scaling Laws in NMT: The Effect of Noise and Architecture
arXiv (Cornell University)·2022· 8 citedOpen Access
Leveraging Unlabeled Data to Predict Out-of-Distribution Performance
arXiv (Cornell University)·2022· 19 citedOpen Access
The Role of Permutation Invariance in Linear Mode Connectivity of Neural\n Networks
arXiv (Cornell University)·2021· 14 citedOpen Access
The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks
arXiv (Cornell University)·2021· 3 citedOpen Access
A Loss Curvature Perspective on Training Instability in Deep Learning
arXiv (Cornell University)·2021· 6 citedOpen Access
Exploring the Limits of Large Scale Pre-training
arXiv (Cornell University)·2021· 35 citedOpen Access
The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning
arXiv (Cornell University)·2021· 21 citedOpen Access
page 1 of 4Next →

Frequent Co-authors

Nathan Srebro(17), Srinadh Bhojanapalli(10), Hanie Sedghi(10), Anders Andreassen(5), Yuhuai Wu(4), Ryota Tomioka(4), Ruslan Salakhutdinov(4), Yiding Jiang(4), Hossein Mobahi(4), Aitor Lewkowycz(3), Ethan Dyer(3), Samy Bengio(3), Alicia Parrish(2), D. Dohan(2), David McAllester(2), Somaye Hashemifar(2), Vinay Ramasesh(2), Ambrose Slone(2), Cem Anil(2), Imanol Schlag(2)