Sebastian Farquhar
14 papers · 2020–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
🌍 Conference Polyglot (5) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🏃 Academic Marathon (5)
🐝
Cross-Pollinator
(8)
🐣
Hot Topic Early Bird
🌍
Conference Polyglot
(5)
👑
Triple Crown
🏆
Grand Slam
🗃️
Keyword Collector
(62)
💎
Century Club
(14)
🔥
Unstoppable
(6)
❓
The Questioner
Conferences
AISTATS (3)
ICLR (3)
ICML (3)
NIPS (3)
AAAI (2)
Top co-authors
Keywords
bayesian neural network
(3)
variational inference
(3)
model evaluation
(2)
posterior approximation
(2)
causal inference
(2)
sample efficiency
(2)
acquisition strategy
(2)
active learning
(2)
acquisition function
(2)
causal discovery
(1)
policy learning
(1)
model architecture
(1)
model analysis
(1)
ai safety
(1)
game theory
(1)
medical imaging
(1)
bayesian active learning
(1)
stochastic process
(1)
uncertainty sampling
(1)
mean-field approximation
(1)
Papers
MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking
ICML 2025
Discovering Agents (Abstract Reprint)
AAAI 2024
Prediction-Oriented Bayesian Active Learning
AISTATS 2023
Tracr: Compiled Transformers as a Laboratory for Interpretability
NIPS 2023
Do Bayesian Neural Networks Need To Be Fully Stochastic?
AISTATS 2023
Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation
ICLR 2023
Prioritized Training on Points that are Learnable, Worth Learning, and not yet Learnt
ICML 2022
Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients
ICLR 2022
Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation
NIPS 2022
Path-Specific Objectives for Safer Agent Incentives
AAAI 2022
On Statistical Bias In Active Learning: How and When to Fix It
ICLR 2021
Active Testing: Sample-Efficient Model Evaluation
ICML 2021
Radial Bayesian Neural Networks: Beyond Discrete Support In Large-Scale Bayesian Deep Learning
AISTATS 2020
Liberty or Depth: Deep Bayesian Neural Nets Do Not Need Complex Weight Posterior Approximations
NIPS 2020