Laurent
Bindschaedler

Cache Saver: A Modular Framework for Efficient, Affordable, and Reproducible LLM Inference

2025

Nearchos Potamitis, Lars Henning Klein, Bardia Mohammadi, Chongyang Xu, Attreyee Mukherjee, Niket Tandon, Laurent Bindschaedler, Akhil Arora

EMNLP 2025

PDF Code

A Computational Decision Support Workflow for Requirement Engineering in DAOs

2025

Quentin Botha, Laurent Bindschaedler, Christoph Siebenbrunner

RE4Web3 2025

A Requirements Analysis for a Decentralized Mathematics Prediction Market

2025

Quentin Botha, Laurent Bindschaedler, Christoph Siebenbrunner

RE4Web3 2025

Everything You Wanted to Know About Graph Neural Network Partitioning (But Were Afraid to Ask)

2025

Chongyang Xu, Laurent Bindschaedler

GRADES-NDA 2025

View All Publications

Research Projects

Agentic AI Infrastructure

Developing environments where multiple models and non-model components are integrated to work together efficiently. Research targets optimizing agentic workloads through advanced scheduling, caching, and resource management.

Cache Saver

A modular, plug-and-play framework for high-level LLM inference optimizations. Cache Saver uses a namespace-aware list-valued cache to ensure statistical integrity and reproducibility, reducing inference costs by ~25% and CO2 emissions by ~35% on average.

Code Intelligence

Research on leveraging LLMs for code-related tasks. SQL-of-Thought introduces a multi-agent framework for text-to-SQL with guided error correction, achieving state-of-the-art results on Spider. LoRACode uses parameter-efficient fine-tuning for code embeddings, reducing trainable parameters to under 2%.

LLM-Enhanced Databases

IOLM-DB makes LLM-enhanced database queries practical through query-specific model optimization. Rather than using expensive general-purpose LLMs for all queries, we create specialized lightweight models tailored to specific analytical tasks, enabling scalable processing of millions of rows.

Learned Systems

Benchmarking Learned Systems

Traditional benchmarks fail to characterize learned systems that overfit to static workloads. We propose new benchmarks that measure adaptability through descriptive statistics and outliers, rather than average metrics, to fairly evaluate the cost and benefits of learned database components.

Learned Systems

Updateable Learned Indexes

Learned indexes promise significant performance gains over traditional B-trees, but struggle with updates. We are developing concurrently updateable learned index structures that maintain the performance benefits of learned models while supporting efficient insertions and deletions.

View All Projects

Teaching

Spring 2026

Operating Systems (OS2026)

University of Saarland

Saarbrücken, Germany

Spring 2024

Operating Systems (OS2024)

University of Saarland

Saarbrücken, Germany

Fall 2023

Systems for Large Language Models (SysLLM)

University of Saarland

Saarbrücken, Germany

Spring 2023

Distributed Systems (DS2023)

University of Saarland

Saarbrücken, Germany