
Laurent Bindschaedler
@lbindschaedler
Followers
355
Following
150
Media
21
Statuses
314
Faculty @ MPI-SWS working on systems for Big Data and Machine Learning. Formerly Postdoc @ MIT CSAIL and PhD @ EPFL. Blockchain astronaut. Newbie entrepreneur.
Geneva, Switzerland
Joined August 2012
π Our latest collaboration with AU just came out! . π Transparent client-side caching for LLMs. CacheSaver massively cuts your costs and carbon emissions without impacting performance. Check it out and keep notifications on: more game changing stuff on the way! π±π.
2οΈβ£ Cache Saver: A Modular Framework for Efficient, Affordable, and Reproducible LLM Inference.π Paper: π» Code: π
Fri 18 Jul.- MAS Wkshp.-πWest Meeting Room 109-110. π
Fri 19 Jul.- ESFOMO Wkshp.-πEast Exhibition Hall A. π§΅4/n
0
1
6
RT @lbindschaedler: @illyism So they are basically leveraging delta encoding of QR codes for compression and that is the main innovation heβ¦.
0
1
0
7/π Read the full paper: A huge thanks to my coauthor and intern, Excel Chukwu, for his incredible contributions! π. Letβs build the future of stateful AI systems together. π. #AI #LLMs #MachineLearning #EuroMLSys #EuroSys.
0
0
1
1/ π Excited to share our latest research, "May the Memory Be With You: Efficient and Infinitely Updatable State for Large Language Models," presented at #EuroMLSys 2025! π. We tackle the challenge of making LLMs stateful for personalized and adaptive interactions. Curious?π.
1
0
3
8/ Huge thanks to my amazing intern, Bardia, for leading this work! π Letβs unlock more LLM use cases for analytics together. π #AI #LLMs #Databases #DOLAP2025.
0
0
0
1/ π Excited to present our paper, "The Case for Instance-Optimized LLMs in OLAP Databases", at #DOLAP (EDBT/ICDT) 2025! We tackle the challenge of scaling LLM-enhanced database queries. How? Letβs dive in! ππ§΅
1
1
4