Benedikt Alkin

4 papers · 2024–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (14)

Venues

ICLR (2) AAAI (1) NeurIPS (1)

Top co-authors

Johannes Brandstetter (3) Sepp Hochreiter (3) Andreas Fürst (2) Lukas Miklautz (2) Markus Holzleitner (1) Simon Schmid (1) Elisabeth Rumetshofer (1) Johannes Lehner (1) Korbinian Pöppel (1) Lukas Gruber (1)

Research topics

Deep Learning (4) Machine Learning (4) Architectures (4) Learning Types · Machine Learning (3) Core Methods (2) Techniques (2) Artificial Intelligence (1) Mathematics & Optimization (1) Core AI (1) Learning Types · Deep Learning (1) Optimization (1) Optimization & Theory (1)

Keywords

linear probing (2) contrastive learning (2) vision transformer (2) instance discrimination (2) transfer learning (1) feature extraction (1) unsupervised clustering (1) long short-term memory (1) latent space (1) fluid dynamics (1) masked autoencoder (1) vision backbone (1) neural operator (1) physics simulation (1) spatiotemporal dynamics (1) masked image modeling (1) patch token (1) eulerian simulation (1) nearest neighbor contrastive learning (1) physics surrogate model (1)

Papers

MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Masked Image Modeling Representations ICLR 2025 Vision-LSTM: xLSTM as Generic Vision Backbone ICLR 2025 Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget AAAI 2024 Universal Physics Transformers: A Framework For Efficiently Scaling Neural Operators NeurIPS 2024