Archive

Seminar series on the design of cooperative AI

2024/02/07

Seminar series continues

New Work on Optimization Techniques on FPGAs will be presented at FPL2023 this week

2023/09/04

The paper on Optimization Techniques for Hestenes-Jacobi SVD on FPGAs was written by Lukas Stasytis and Zsolt István

Muhammad El-Hindi is now a Doctor of Natural Sciences!

2023/08/24

On August 24, Muhammad El-Hindi successfully defended his Ph.D. thesis titled 'Towards Efficient Trustworthy Data Systems'. Congratulations, Dr. rer. nat. El-Hindi!

Savian is Start-Up of August 2023 at Hub31

2023/08/23

The start-up which began as part of the Systems group under Carsten Binnig is now at home in Hub31.

Tobias Ziegler is now a Doctor of Natural Sciences!

2023/08/22

On August 22, Tobi Ziegler successfully defended his Ph.D. thesis titled 'Towards Scalable OLTP Over Fast Networks'. Congratulations, Dr. rer. nat. Ziegler!

“DiffML: End-to-end Differentiable ML Pipelines” was awarded as Best Paper Runner-Up at DEEM'23

2023/07/13

The paper was written by Benjamin Hilprecht, Christian Hammacher, Eduardo Reis and Mohamed Abdelaal under the supervision of Carsten Binnig

Paper accepted to the 19th International Workshop on Data Management on New Hardware (DaMoN) @ SIGMOD 2023

2023/05/24

Zero-sided RDMA: Network-driven Data Shuffling

Authors: Matthias Jasny, Lasse Thostrup, Carsten Binnig

Paper on Semantic Type Extraction for Data Lakes accepted to SIGMOD 2023

2023/05/15

Congratulations to Sven Langenecker and Carsten Binnig!

Sven Langenecker will present the paper “Steered Training Data Generation for Learned Semantic Type Detection” at SIGMOD 2023 in Seattle.

Paper accepted to Data Management for End-to-End Machine Learning Workshop (DEEM) @ SIGMOD 2023

2023/05/15

DiffML: End-to-end Differentiable ML Pipelines

Authors: Benjamin Hilprecht, Christian Hammacher, Eduardo dos Reis, Mohamed Abdelaal, and Carsten Binnig

Paper accepted to Workshop on Verifiable Database Systems @ SIGMOD 2023

2023/05/10

Towards Merkle Trees for High-Performance Data Systems

Muhammad El-Hindi, Tobias Ziegler and Carsten Binnig will show how it is possible to build high-performance Merkle trees with orders of magnitude performance improvements.