Smitha Milli
8 papers · 2016–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Cross-Pollinator (15) πΊοΈ Taxonomy Completionist (12) π£ Hot Topic Early Bird π§ Keyword Pioneer π Conference Polyglot (5)
π
Academic Marathon
(9)
π
Interdisciplinary Bridge
π
Conference Pioneer
β
The Questioner
(2)
Conferences
ICML (3)
NIPS (2)
EMNLP (1)
IJCAI (1)
UAI (1)
Top co-authors
Keywords
reward function
(2)
human-robot interaction
(2)
model misspecification
(1)
preference learning
(1)
inverse reinforcement learning
(1)
preference inference
(1)
classifier design
(1)
reward learning
(1)
implicit feedback
(1)
human feedback
(1)
incentive design
(1)
reward hacking
(1)
autonomous agent
(1)
strategic classification
(1)
objective learning
(1)
human model misspecification
(1)
pedagogic assumption
(1)
common-payoff game
(1)
literal interpretation
(1)
causal framework
(1)
Papers
Representative Ranking for Deliberation in the Public Sphere
ICML 2025
Position: Democratic AI is Possible. The Democracy Levels Framework Shows How It Might Work.
ICML 2025
Reward-rational (implicit) choice: A unifying formalism for reward learning
NIPS 2020
Strategic Classification is Causal Modeling in Disguise
ICML 2020
Literal or Pedagogic Human? Analyzing Human Model Misspecification in Objective Learning
UAI 2019
Should Robots be Obedient?
IJCAI 2017
Inverse Reward Design
NIPS 2017
Beyond Canonical Texts: A Computational Analysis of Fanfiction
EMNLP 2016