Nicolas Beltran-Velez
5 papers · 2024–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (3) π Cross-Pollinator (9) πΊοΈ Taxonomy Completionist (13)
β
The Questioner
Conferences
NIPS (3)
ICLR (1)
ICML (1)
Top co-authors
Keywords
large language model
(2)
bayesian inference
(1)
uncertainty quantification
(1)
in-context learning
(1)
model behavior
(1)
neural network analysis
(1)
bayesian model
(1)
hypothesis testing
(1)
probabilistic prediction
(1)
gradient boosting
(1)
posterior predictive
(1)
generative model
(1)
language model
(1)
circuit analysis
(1)
generative ai
(1)
mechanistic interpretability
(1)
hallucination rate
(1)
model likelihood
(1)
hallucination detection
(1)
model internal
(1)
Papers
Can Generative AI Solve Your In-Context Learning Problem? A Martingale Perspective
ICLR 2025
Estimating the Hallucination Rate of Generative AI
NIPS 2024
Hypothesis Testing the Circuit Hypothesis in LLMs
NIPS 2024
Treeffuser: probabilistic prediction via conditional diffusions with gradient-boosted trees
NIPS 2024
ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages
ICML 2024