Metod Jazbec
@metodjazbec.bsky.social
ML PhD student at University of Amsterdam
Great too see that our Generative Uncertainty won the best paper award at the ICLR QUESTION workshop (uncertainty-foundation-models.github.io). If you're interested in what Bayesian/ensembling methods can bring to the world of diffusion models, check out the paper 👇
arxiv.org/abs/2502.20946
arxiv.org/abs/2502.20946
May 1, 2025 at 7:13 AM
Great too see that our Generative Uncertainty won the best paper award at the ICLR QUESTION workshop (uncertainty-foundation-models.github.io). If you're interested in what Bayesian/ensembling methods can bring to the world of diffusion models, check out the paper 👇
arxiv.org/abs/2502.20946
arxiv.org/abs/2502.20946
Reposted by Metod Jazbec
🚪Fast yet Safe: Early-Exiting with Risk Control
by @metodjazbec.bsky.social*, Alexander Timans*, Tin Hadži Veljković, Kaspar Sakmann, Dan Zhang, @canaesseth.bsky.social, Eric Nalisnick
🪪https://neurips.cc/virtual/2024/poster/94477
📜https://arxiv.org/abs/2405.20915
🧵6 / 12
by @metodjazbec.bsky.social*, Alexander Timans*, Tin Hadži Veljković, Kaspar Sakmann, Dan Zhang, @canaesseth.bsky.social, Eric Nalisnick
🪪https://neurips.cc/virtual/2024/poster/94477
📜https://arxiv.org/abs/2405.20915
🧵6 / 12
December 9, 2024 at 1:24 PM
🚪Fast yet Safe: Early-Exiting with Risk Control
by @metodjazbec.bsky.social*, Alexander Timans*, Tin Hadži Veljković, Kaspar Sakmann, Dan Zhang, @canaesseth.bsky.social, Eric Nalisnick
🪪https://neurips.cc/virtual/2024/poster/94477
📜https://arxiv.org/abs/2405.20915
🧵6 / 12
by @metodjazbec.bsky.social*, Alexander Timans*, Tin Hadži Veljković, Kaspar Sakmann, Dan Zhang, @canaesseth.bsky.social, Eric Nalisnick
🪪https://neurips.cc/virtual/2024/poster/94477
📜https://arxiv.org/abs/2405.20915
🧵6 / 12