2 papers
cs.LG2026
Noise-Response Calibration: A Causal Intervention Protocol for LLM-Judges
Maxim Khomiakov, Jes Frellsen
Large language models (LLMs) are increasingly used as automated judges and synthetic labelers, especially in low-label settings. Yet these systems are stochastic and often overconf…
cs.CV2024
GeoFormer: A Multi-Polygon Segmentation Transformer
Maxim Khomiakov, Michael Riis Andersen, Jes Frellsen
In remote sensing there exists a common need for learning scale invariant shapes of objects like buildings. Prior works relies on tweaking multiple loss functions to convert segmen…