Forschung
Wir trainieren kleine, spezialisierte Modelle, die Allzweck-LLMs bei Netzoperationen übertreffen
Decoupling reasoning and facts in language models
On decoupling reasoning and facts in language models
The Limits of prompt optimization in high-alignment model pairs
The Limits of prompt optimization in high-alignment model pairs
Utilization rate forecasting for EV charging infrastructure
Utilization rate forecasting for EV charging infrastructure
Real-Time Human Activity Recognition Using the H2O AutoML Framework and Imbalance Handling
Real-Time Human Activity Recognition Using the H2O AutoML Framework and Imbalance Handling
The few-shot distraction effect
The Few-shot distraction effect —> when more examples degrade LLM constraint adherence
Small vs Big - NanoChat vs GPT-OSS 20B
nanochat implements a dense transformer decoder with several architectural refinements that have become mainstream since the original GPT-2 paper.
Agents are classes that compose like lego blocks
DSPy takes a fundamentally different approach: agents are Python classes that compose like LEGO blocks.
A Framework for Integrating Intelligent Mobile Energy Storage into Energy Distribution Systems
A Framework for Integrating Intelligent Mobile Energy Storage into Energy Distribution Systems
The Impact of Electric Vehicles on Low Voltage Grids: A Case Study of Berlin
The Impact of Electric Vehicles on Low Voltage Grids: A Case Study of Berlin
Auction-based Peer-to-peer Energy Transaction Model with Prosumer-side Energy Scheduling
Auction-based Peer-to-peer Energy Transaction Model with Prosumer-side Energy Scheduling
A Power Demand Estimator for Electric Vehicle Charging Infrastructure
A Power Demand Estimator for Electric Vehicle Charging Infrastructure
Optimal energy supply scheduling for a single household: Integrating machine learning for power forecasting
Optimal energy supply scheduling for a single household: Integrating machine learning for power forecasting
Probabilistic Risk Assessment in Power Systems With High Wind Energy Penetration
Probabilistic Risk Assessment in Power Systems With High Wind Energy Penetration