news

Apr 30, 2026 Excited to share that Extending Prediction-Powered Inference through Conformal Prediction was accepted to ICML 2026!
Apr 30, 2026 Happy to share that Avoid What You Know: Divergent Trajectory Balance for GFlowNets was accepted to ICML 2026!
Apr 27, 2026 Presented our work Avoid What You Know: Divergent Trajectory Balance for GFlowNets at the DeLTa Workshop at ICLR 2026 in Rio de Janeiro, Brazil.
Jan 22, 2026 Excited to share that Boosted GFlowNets was accepted to AISTATS 2026! I will be presenting our work on boosting for generative flow networks in Morocco. See you there!
Nov 12, 2025 New paper on arXiv: Boosted GFlowNets. We introduce a boosting method to tackle mode collapse in sparse environments.
Oct 17, 2025 New preprint on arXiv: Extending Prediction-Powered Inference through Conformal Prediction. Our approach enables PPI with privacy, robustness, and validity under continuous distribution shifts.