Yehonatan Elisha
9 papers · 2024–2026 · 4 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
(18)
🏆
Keyword Champion
(2)
🗃️
Keyword Collector
(52)
Top co-authors
Research topics
Artificial Intelligence
(8)
Core AI · Artificial Intelligence
(8)
Machine Learning
(7)
Deep Learning
(6)
Core Methods
(4)
Optimization & Theory · Machine Learning
(4)
Learning Types · Deep Learning
(2)
Learning Types · Machine Learning
(2)
Optimization & Theory · Deep Learning
(2)
Computer Vision
(1)
Natural Language Processing
(1)
Core AI · Computer Vision
(1)
Models
(1)
Techniques
(1)
Understanding
(1)
Keywords
feature attribution
(3)
path integration
(2)
language model
(2)
recommender system
(2)
explainable ai
(1)
spurious correlation
(1)
vision transformer
(1)
distribution shift
(1)
attention mechanism
(1)
saliency map
(1)
user-item embedding
(1)
variational autoencoder
(1)
model interpretability
(1)
sparse autoencoder
(1)
model explanation
(1)
deep learning
(1)
evaluation metric
(1)
overfitting detection
(1)
semantic preservation
(1)
matrix factorization
(1)
Papers
Concept-Guided Fine-Tuning: Steering ViTs away from Spurious Correlations to Improve Robustness
CVPR 2026
Extracting Interaction-Aware Monosemantic Concepts in Recommender Systems
AAAI 2026
Fidelity-Aware Recommendation Explanations via Stochastic Path Integration
AAAI 2026
Rethinking Saliency Maps: A Cognitive Human Aligned Taxonomy and Evaluation Framework for Explanations
AAAI 2026
BEE: Metric-Adapted Explanations via Baseline Exploration-Exploitation
AAAI 2025
Forget What You Know about LLMs Evaluations - LLMs are Like a Chameleon
EMNLP 2025
Soft Local Completeness: Rethinking Completeness in XAI
ICCV 2025
Improving LLM Attributions with Randomized Path-Integration
EMNLP 2024
LLM Explainability via Attributive Masking Learning
EMNLP 2024