Anvith Thudi
5 papers · 2023–2025 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(13)
Venues
Top co-authors
Research topics
Keywords
unlearning
(2)
large language model
(2)
uncertainty quantification
(1)
in-context learning
(1)
function space
(1)
risk minimization
(1)
gradient descent
(1)
convex minimization
(1)
selective prediction
(1)
distributionally robust optimization
(1)
privacy loss
(1)
data mixture
(1)
overconfident prediction
(1)
fine tuning
(1)
minimax theorem
(1)
rényi divergence
(1)
model confidence
(1)
fine-tuning data
(1)
scale invariant
(1)
gradient-based approach
(1)
Papers
Fast Exact Unlearning for In-Context Learning Data for LLMs
ICML 2025
Leveraging Per-Instance Privacy for Machine Unlearning
ICML 2025
MixMax: Distributional Robustness in Function Space via Optimal Data Mixtures
ICLR 2025
MixMin: Finding Data Mixtures via Convex Minimization
ICML 2025
Training Private Models That Know What They Don’t Know
NeurIPS 2023