Gregor Bachmann

According to our database, Gregor Bachmann authored at least 20 papers between 2020 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Tokenisation is NP-Complete.

Philip Whittington, Gregor Bachmann, Tiago Pimentel

CoRR, 2024

Interpolated-MLPs: Controllable Inductive Bias.

Sean Wu, Jordan Hong, Keyu Bai, Gregor Bachmann

CoRR, 2024

A Language Model's Guide Through Latent Space.

Dimitri von Rütte, Sotiris Anagnostidis, Gregor Bachmann, Thomas Hofmann

Proceedings of the Forty-first International Conference on Machine Learning, 2024

The Pitfalls of Next-Token Prediction.

Gregor Bachmann, Vaishnavh Nagarajan

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Navigating Scaling Laws: Compute Optimality in Adaptive Model Training.

Sotiris Anagnostidis, Gregor Bachmann, Imanol Schlag, Thomas Hofmann

Proceedings of the Forty-first International Conference on Machine Learning, 2024

How Good is a Single Basin?

Kai Lion, Lorenzo Noci, Thomas Hofmann, Gregor Bachmann

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

2023

Disentangling Linear Mode-Connectivity.

Gul Sena Altintas, Gregor Bachmann, Lorenzo Noci, Thomas Hofmann

CoRR, 2023

Navigating Scaling Laws: Accelerating Vision Transformer's Training via Adaptive Strategies.

Sotiris Anagnostidis, Gregor Bachmann, Thomas Hofmann

CoRR, 2023

Scaling MLPs: A Tale of Inductive Bias.

Gregor Bachmann, Sotiris Anagnostidis, Thomas Hofmann

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Random Teachers are Good Teachers.

Felix Sarnthein, Gregor Bachmann, Sotiris Anagnostidis, Thomas Hofmann

Proceedings of the International Conference on Machine Learning, 2023

The Curious Case of Benign Memorization.

Sotiris Anagnostidis, Gregor Bachmann, Lorenzo Noci, Thomas Hofmann

Proceedings of the Eleventh International Conference on Learning Representations, 2023

CLIP-Guided Vision-Language Pre-training for Question Answering in 3D Scenes.

Maria Parelli, Alexandros Delitzas, Nikolas Hars, Georgios Vlassis, Sotiris Anagnostidis, Gregor Bachmann, Thomas Hofmann

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Multi-CLIP: Contrastive Vision-Language Pre-training for Question Answering tasks in 3D Scenes.

Alexandros Delitzas, Maria Parelli, Nikolas Hars, Georgios Vlassis, Sotirios-Konstantinos Anagnostidis, Gregor Bachmann, Thomas Hofmann

Proceedings of the 34th British Machine Vision Conference 2023, 2023

2022

How Tempering Fixes Data Augmentation in Bayesian Neural Networks.

Gregor Bachmann, Lorenzo Noci, Thomas Hofmann

Proceedings of the International Conference on Machine Learning, 2022

Generalization Through the Lens of Leave-One-Out Error.

Gregor Bachmann, Thomas Hofmann, Aurélien Lucchi

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Analytic Insights into Structure and Rank of Neural Network Hessian Maps.

Sidak Pal Singh, Gregor Bachmann, Thomas Hofmann

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect.

Lorenzo Noci, Kevin Roth, Gregor Bachmann, Sebastian Nowozin, Thomas Hofmann

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Precise characterization of the prior predictive distribution of deep ReLU networks.

Lorenzo Noci, Gregor Bachmann, Kevin Roth, Sebastian Nowozin, Thomas Hofmann

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Uniform Convergence, Adversarial Spheres and a Simple Remedy.

Gregor Bachmann, Seyed-Mohsen Moosavi-Dezfooli, Thomas Hofmann

Proceedings of the 38th International Conference on Machine Learning, 2021

2020

Constant Curvature Graph Convolutional Networks.

Gregor Bachmann, Gary Bécigneul, Octavian Ganea

Proceedings of the 37th International Conference on Machine Learning, 2020