Michal Klein

According to our database1, Michal Klein authored at least 24 papers between 2022 and 2026.

Collaborative distances:

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
Nectar: Neural Estimation of Cached-Token Attention via Regression.
CoRR, May, 2026

The Coupling Within: Flow Matching via Distilled Normalizing Flows.
CoRR, March, 2026

Amortizing Maximum Inner Product Search with Learned Support Functions.
CoRR, March, 2026

On Fitting Flow Models with Large Sinkhorn Couplings.
Trans. Mach. Learn. Res., 2026

Multivariate Conformal Prediction using Optimal Transport.
Trans. Mach. Learn. Res., 2026

2025
Completed Hyperparameter Transfer across Modules, Width, Depth, Batch and Duration.
CoRR, December, 2025

The Data-Quality Illusion: Rethinking Classifier-Based Quality Filtering for LLM Pretraining.
CoRR, October, 2025

Flow Matching with Semidiscrete Couplings.
CoRR, September, 2025

The Geometries of Truth Are Orthogonal Across Tasks.
CoRR, June, 2025

End-to-end Learning of Sparse Interventions on Activations to Steer Generation.
CoRR, March, 2025

LinEAS: End-to-end Learning of Activation Steering with a Distributional Loss.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Controlling Language and Diffusion Models by Transporting Activations.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Simple ReFlow: Improved Techniques for Fast Flow Models.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Multimodal Autoregressive Pre-training of Large Vision Encoders.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

2024
Learning Elastic Costs to Shape Monge Displacements.
Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Progressive Entropic Optimal Transport Solvers.
Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Contrasting Multiple Representations with the Multi-Marginal Matching Gap.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Careful with that Scalpel: Improving Gradient Surgery with an EMA.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Scalable Pre-training of Large Autoregressive Image Models.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023
Learning Costs for Structured Monge Displacements.
CoRR, 2023

Unbalanced Low-rank Optimal Transport Solvers.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Monge, Bregman and Occam: Interpretable Optimal Transport in High-Dimensions with Feature-Sparse Maps.
Proceedings of the International Conference on Machine Learning, 2023

Predicting Ordinary Differential Equations with Transformers.
Proceedings of the International Conference on Machine Learning, 2023

2022
Discovering ordinary differential equations that govern time-series.
CoRR, 2022


  Loading...