Agustinus Kristiadi
15 papers · 2018–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
🏃 Academic Marathon (7) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (5) 🐝 Cross-Pollinator (7)
🐝
Cross-Pollinator
(7)
🤝
Dynamic Duo
(10)
👥
Mega-Team
(25)
❓
The Questioner
🔥
Unstoppable
(6)
💎
Century Club
(15)
Conferences
ICML (5)
NIPS (4)
AISTATS (3)
UAI (2)
CONLL (1)
Top co-authors
Keywords
uncertainty quantification
(5)
bayesian neural network
(4)
predictive uncertainty
(3)
laplace approximation
(3)
variational inference
(3)
bayesian inference
(2)
relu network
(2)
out-of-distribution detection
(2)
neural network
(2)
posterior approximation
(2)
bayesian deep learning
(2)
inductive bia
(1)
normalizing flow
(1)
parameter space
(1)
uncertainty calibration
(1)
discriminative model
(1)
overconfident prediction
(1)
discriminative neural network
(1)
softmax output
(1)
gibbs prior
(1)
Papers
Towards Cost-Effective Reward Guided Text Generation
ICML 2025
Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI
ICML 2024
Structured Inverse-Free Natural Gradient Descent: Memory-Efficient & Numerically-Stable KFAC
ICML 2024
Preventing Arbitrarily High Confidence on Far-Away Data in Point-Estimated Discriminative Neural Networks
AISTATS 2024
A Sober Look at LLMs for Material Discovery: Are They Actually Good for Bayesian Optimization Over Molecules?
ICML 2024
The Geometry of Neural Nets' Parameter Spaces Under Reparametrization
NIPS 2023
Discovering Inductive Bias with Gibbs Priors: A Diagnostic Tool for Approximate Bayesian Inference
AISTATS 2022
Posterior Refinement Improves Sample Efficiency in Bayesian Neural Networks
NIPS 2022
Fast predictive uncertainty for classification with Bayesian deep networks
UAI 2022
Being a Bit Frequentist Improves Bayesian Neural Networks
AISTATS 2022
An Infinite-Feature Extension for Bayesian ReLU Nets That Fixes Their Asymptotic Overconfidence
NIPS 2021
Laplace Redux - Effortless Bayesian Deep Learning
NIPS 2021
Learnable uncertainty under Laplace approximations
UAI 2021
Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks
ICML 2020
Improving Response Selection in Multi-Turn Dialogue Systems by Incorporating Domain Knowledge
CONLL 2018