Research collection
#model-selection
Research tagged model-selection: explanations, evidence, limitations and connections between papers.
4 results
A lattice method predicts better decoding schedules before generation
A lattice method estimates lost position dependence to rank decoding schedules before generation, with tested image evidence.
Home automation can use different models for different calls
A live test of per-call model choices matched all-hosted human judgments on 39 of 43 counted cases, at lower hosted spend.
Model weight spectra rank robustness within model groups
A weight-based method ranks out-of-domain robustness within architecture and training groups, with limits across model families.
Why language models can overstate their progress
A statistical model and loop tests show why reused examples can make language-model progress scores too optimistic.