Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
An Explicit Feedback Contract for Iterative ML-Agent Harnesses
Kehui Yao, Chuanbo Hu, Jiao Chen +8
Iterative ML agents develop models by editing code, running experiments, reading a validation score, and choosing what to try next. In current harnesses this loop is served by an e…
cs.LG2026
GAUDI: Geometry-Aware Diffusion for Calibrated Air-Quality Time-Series Imputation
Xinjin Li, Yudi Xia, Calvin Chang Liu +7
Air-quality sensor outages often create contiguous missing blocks, where side information useful for isolated missingness may be less reliable. We study a block-specific, GAUDI-ali…