← Search

Pedro Dall’Antonia

2 accepted papers

2026

Avoid What You Know: Divergent Trajectory Balance for GFlowNets

ICML 2026poster

Generative Flow Networks (GFlowNets) are a flexible family of amortized samplers trained to generate discrete and compositional objects with probability proportional to a reward function. To this end, they learn a policy function over an intractably large state graph by minimizing a stochastic objec…

Cited by 0SourceScholar
2026

Extending Prediction-Powered Inference through Conformal Prediction

ICML 2026poster

Prediction-powered inference is a recent methodology for the safe use of black-box ML models to impute missing data, strengthening inference of statistical parameters. However, many applications require strong properties besides valid inference, such as privacy, robustness or validity under continuo…

Cited by 0SourceScholar