Bálint Mucsányi
@bmucsanyi.bsky.social
ELLIS & IMPRS-IS PhD Student at the University of Tübingen.
Excited about uncertainty quantification, weight spaces, and deep learning theory.
Excited about uncertainty quantification, weight spaces, and deep learning theory.
Reposted by Bálint Mucsányi
Excited to present our work Rethinking Approximate Gaussian Inference (AGI 🤯) in Classification at NeurIPS 2025 in San Diego! Find out why you shouldn’t use Softmax in uncertainty quantification. 😳
Exhibit Hall C,D,E, Poster #601
Thu 4 Dec 11 am - 2 pm
📖 arxiv.org/abs/2502.03366
Exhibit Hall C,D,E, Poster #601
Thu 4 Dec 11 am - 2 pm
📖 arxiv.org/abs/2502.03366
Rethinking Approximate Gaussian Inference in Classification
In classification tasks, softmax functions are ubiquitously used as output activations to produce predictive probabilities. Such outputs only capture aleatoric uncertainty. To capture epistemic uncert...
arxiv.org
December 4, 2025 at 4:08 AM
Excited to present our work Rethinking Approximate Gaussian Inference (AGI 🤯) in Classification at NeurIPS 2025 in San Diego! Find out why you shouldn’t use Softmax in uncertainty quantification. 😳
Exhibit Hall C,D,E, Poster #601
Thu 4 Dec 11 am - 2 pm
📖 arxiv.org/abs/2502.03366
Exhibit Hall C,D,E, Poster #601
Thu 4 Dec 11 am - 2 pm
📖 arxiv.org/abs/2502.03366
Reposted by Bálint Mucsányi
Many LLM uncertainty estimators perform similarly, but does that mean they do the same? No! We find that they use different cues, and combining them gives even better performance. 🧵1/5
📄 openreview.net/forum?id=QKR...
NeurIPS: Sunday, East Exhibition Hall A, Safe Gen AI workshop
📄 openreview.net/forum?id=QKR...
NeurIPS: Sunday, East Exhibition Hall A, Safe Gen AI workshop
December 13, 2024 at 12:37 PM
Many LLM uncertainty estimators perform similarly, but does that mean they do the same? No! We find that they use different cues, and combining them gives even better performance. 🧵1/5
📄 openreview.net/forum?id=QKR...
NeurIPS: Sunday, East Exhibition Hall A, Safe Gen AI workshop
📄 openreview.net/forum?id=QKR...
NeurIPS: Sunday, East Exhibition Hall A, Safe Gen AI workshop
Excited to present our spotlight paper on uncertainty disentanglement at #NeurIPS! Drop by today between 11 am and 2 pm PST at West Ballroom A-D #5509 and let's chat!
December 12, 2024 at 6:00 PM
Excited to present our spotlight paper on uncertainty disentanglement at #NeurIPS! Drop by today between 11 am and 2 pm PST at West Ballroom A-D #5509 and let's chat!
Thrilled to share our NeurIPS spotlight on uncertainty disentanglement! ✨ We study how well existing methods disentangle different sources of uncertainty, like epistemic and aleatoric. While all tested methods fail at this task, there are promising avenues ahead. 🧵 👇 1/7
📖: arxiv.org/abs/2402.19460
📖: arxiv.org/abs/2402.19460
December 3, 2024 at 1:38 PM
Thrilled to share our NeurIPS spotlight on uncertainty disentanglement! ✨ We study how well existing methods disentangle different sources of uncertainty, like epistemic and aleatoric. While all tested methods fail at this task, there are promising avenues ahead. 🧵 👇 1/7
📖: arxiv.org/abs/2402.19460
📖: arxiv.org/abs/2402.19460