Victor Rühle

Recasting Transformer Layers as Energy Models

Towards Active Synthetic Data Generation for Finetuning Language Models

OdysseyBench: Evaluating LLM Agents on Long-Horizon Complex Office Application Workflows

BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute

Minerva: A Programmable Memory Test Benchmark for Language Models

Exploring How LLMs Capture and Represent Domain-Specific Knowledge

Semi-autoregressive Decoding for Efficient LLM Inference

EcoAct: Economic Agent Determines When to Register What Action