Juyeon Heo
9 papers · 2019–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
🐝 Cross-Pollinator (15) 🌍 Conference Polyglot (4) 🏃 Academic Marathon (6) 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (12)
🧭
Keyword Pioneer
🐣
Hot Topic Early Bird
❓
The Questioner
(2)
Conferences
ICLR (4)
COLING (2)
NIPS (2)
AAAI (1)
Top co-authors
Keywords
neural network interpretation
(2)
adversarial robustness
(2)
feature attribution
(2)
decision making
(1)
function approximation
(1)
weakly supervised learning
(1)
question answering
(1)
evaluation framework
(1)
model alignment
(1)
prior knowledge
(1)
perturbation analysis
(1)
saliency map
(1)
local smoothness
(1)
gradient alignment
(1)
model interpretation
(1)
robustness optimization
(1)
problem solving
(1)
human explanation
(1)
large language model
(1)
adversarial manipulation
(1)
Papers
Do LLMs estimate uncertainty well in instruction-following?
ICLR 2025
LLMs on interactive feature collections with implicit dynamic decision strategy
COLING 2025
On Evaluating LLMs’ Capabilities as Functional Approximators: A Bayesian Evaluation Framework
COLING 2025
Do LLMs ``know'' internally when they follow instructions?
ICLR 2025
Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization
ICLR 2024
Robust Explanation Constraints for Neural Networks
ICLR 2023
Use perturbations when learning from explanations
NIPS 2023
Towards More Robust Interpretation via Local Gradient Alignment
AAAI 2023
Fooling Neural Network Interpretations via Adversarial Model Manipulation
NIPS 2019