Ilia Sucholutsky
14 papers · 2021–2025 · 8 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 ↓+7 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (30) π Triple Crown
π
Keyword Champion
(2)
π
Grand Slam
π
Renaissance Researcher
(6)
β
The Questioner
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(74)
Top co-authors
Research topics
Artificial Intelligence
(12)
Core AI
(10)
Machine Learning
(7)
Deep Learning
(4)
Learning Paradigms
(4)
Learning Types Β· Deep Learning
(4)
Learning Types Β· Machine Learning
(4)
Interdisciplinary
(3)
Cognitive Science
(3)
Core Methods
(3)
Optimization & Theory
(2)
Natural Language Processing
(1)
Reinforcement Learning
(1)
Robotics
(1)
Security & Privacy
(1)
Keywords
few-shot learning
(4)
language model
(3)
representation learning
(3)
large language model
(2)
deep neural network
(2)
cognitive science
(2)
sample efficiency
(1)
contrastive learning
(1)
one-shot learning
(1)
inverse reinforcement learning
(1)
cognitive modeling
(1)
decision making
(1)
rational choice
(1)
model robustness
(1)
imitation learning
(1)
ai safety
(1)
human-in-the-loop learning
(1)
state abstraction
(1)
information retrieval
(1)
knowledge distillation
(1)
Papers
Large Language Models Assume People are More Rational than We Really are
ICLR 2025
Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse
ICML 2025
Quantifying Knowledge Distillation using Partial Information Decomposition
AISTATS 2025
Adaptive Language-Guided Abstraction from Contrastive Explanations
CoRL 2024
Characterizing Similarities and Divergences in Conversational Tones in Humans and LLMs by Sampling with People
ACL 2024
Learning Human-like Representations to Enable Learning Human Values
NeurIPS 2024
Learning with Language-Guided State Abstractions
ICLR 2024
Alignment with human representations supports robust few-shot learning
NeurIPS 2023
Analyzing Diffusion as Serial Reproduction
ICML 2023
Human-in-the-Loop Mixup
UAI 2023
On the informativeness of supervision signals
UAI 2023
Words are all you need? Language as an approximation for human similarity judgments
ICLR 2023
`Less Than One'-Shot Learning: Learning N Classes From M < N Samples
AAAI 2021
SecDD: Efficient and Secure Method for Remotely Training Neural Networks (Student Abstract)
AAAI 2021