7 papers · 1 filter
Have an LLM Write Your Anomaly Detector: Autonomous Discovery of Compact, Interpretable Detectors for Time Series
David Berghaus
Time-series anomaly detection trades off predictive accuracy, computational efficiency, and interpretability. We use a large language model not as the detector but as the author of…
LoopMTP: A looped transformer guided by latent multi-token prediction
Behzad Shomali, Markus Frey, David Berghaus +2
Looped transformers have emerged as a parameter-efficient alternative to scaling depth for strong reasoning. By reusing one stack of layers across iterations, they attain the e…
EVIL: Evolving Interpretable Algorithms for Zero-Shot Inference on Event Sequences and Time Series with LLMs
David Berghaus
We introduce EVIL (\textbf{EV}olving \textbf{I}nterpretable algorithms with \textbf{L}LMs), an approach that uses LLM-guided evolutionary search to discover simple, interpretable a…
Adaptive Loops and Memory in Transformers: Think Harder or Know More?
Markus Frey, Behzad Shomali, Ali Hamza Bashir +3
Chain-of-thought (CoT) prompting enables reasoning in language models but requires explicit verbalization of intermediate steps. Looped transformers offer an alternative by iterati…
Is continuous CoT better suited for multi-lingual reasoning?
Ali Hamza Bashir, Behzad Shomali, Markus Frey +3
We investigate whether performing reasoning in a continuous latent space leads to more robust multilingual capabilities. We compare Continuous Chain-of-Thought (using the CODI fram…
Beyond Reinforcement Learning: Fast and Scalable Quantum Circuit Synthesis
Lukas Theißinger, Thore Gerlach, David Berghaus +1
Quantum unitary synthesis addresses the problem of translating abstract quantum algorithms into sequences of hardware-executable quantum gates. Solving this task exactly is infeasi…
Foundation Inference Models for Ordinary Differential Equations
Maximilian Mauel, Johannes R. Hübers, David Berghaus +2
Ordinary differential equations (ODEs) are central to scientific modelling, but inferring their vector fields from noisy trajectories remains challenging. Current approaches such a…