EVIL evolves single compact Python algorithms via LLM-guided search that enable zero-shot inference on temporal point processes, Markov jump processes, and time series imputation, often matching or exceeding deep learning models while remaining interpretable and orders of magnitude faster.
"" 9 10import numpy as np 11from numpy.lib.stride_tricks import sliding_window_view 12 13def _impute_1d(out: np.ndarray, times: np.ndarray) -> None: 14
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
EVIL: Evolving Interpretable Algorithms for Zero-Shot Inference on Event Sequences and Time Series with LLMs
EVIL evolves single compact Python algorithms via LLM-guided search that enable zero-shot inference on temporal point processes, Markov jump processes, and time series imputation, often matching or exceeding deep learning models while remaining interpretable and orders of magnitude faster.