Sanyam Kapoor
10 papers · 2021–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π£ Hot Topic Early Bird π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (4) π Cross-Pollinator (10)
πΊοΈ
Taxonomy Completionist
(24)
π
Century Club
(10)
β
The Questioner
π₯
Unstoppable
(5)
Conferences
NIPS (5)
ICML (3)
EACL (1)
ICLR (1)
Top co-authors
Keywords
bayesian inference
(3)
transfer learning
(2)
neural network
(2)
uncertainty estimation
(2)
gaussian process
(2)
uncertainty quantification
(2)
large language model
(2)
variational inference
(2)
covariate shift
(1)
ai safety
(1)
catastrophic forgetting
(1)
question answering
(1)
empirical baye
(1)
maximum a posteriori
(1)
data augmentation
(1)
pac-bayes bound
(1)
generalization bound
(1)
model calibration
(1)
scalable inference
(1)
probability calibration
(1)
Papers
Compute-Optimal LLMs Provably Generalize Better with Scale
ICLR 2025
Large Language Models Must Be Taught to Know What They Donβt Know
NIPS 2024
Calibration-Tuning: Teaching Large Language Models to Know What They Donβt Know
EACL 2024
Function-Space Regularization in Neural Networks: A Probabilistic Perspective
ICML 2023
Should We Learn Most Likely Functions or Parameters?
NIPS 2023
PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization
NIPS 2022
Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors
NIPS 2022
On Uncertainty, Tempering, and Data Augmentation in Bayesian Classification
NIPS 2022
SKIing on Simplices: Kernel Interpolation on the Permutohedral Lattice for Scalable Gaussian Processes
ICML 2021
Variational Auto-Regressive Gaussian Processes for Continual Learning
ICML 2021