Corentin Kervadec
8 papers · 2021–2025 · 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 · Silver
🗺️
Taxonomy Completionist
(22)
🐣
Hot Topic Early Bird
❓
The Questioner
(3)
Venues
Top co-authors
Research topics
Artificial Intelligence
(6)
Natural Language Processing
(6)
Core AI
(6)
Machine Learning
(5)
Optimization & Theory
(4)
Resources & Methods
(4)
Deep Learning
(3)
Computer Vision
(2)
Applications · Natural Language Processing
(2)
Applications · Computer Vision
(2)
Architectures
(2)
Core Methods
(2)
Learning Types · Machine Learning
(2)
Learning Types · Deep Learning
(2)
Generation
(1)
Keywords
language model
(4)
visual question answering
(3)
representation learning
(3)
machine-generated prompt
(2)
dataset bia
(2)
reasoning pattern
(2)
attention mechanism
(2)
model behavior
(1)
intrinsic dimension
(1)
intrinsic dimensionality
(1)
training dynamics
(1)
attention head
(1)
out-of-distribution evaluation
(1)
prompt optimization
(1)
token prediction
(1)
reasoning ability
(1)
attention distribution
(1)
attention pattern
(1)
question-answer pair
(1)
natural language prompt
(1)
Papers
Emergence of a High-Dimensional Abstraction Phase in Language Transformers
ICLR 2025
Evil twins are not that evil: Qualitative insights into machine-generated prompts
EMNLP 2025
Learning, Forgetting, Remembering: Insights From Tracking LLM Memorization During Training
EMNLP 2024
Bridging Information-Theoretic and Geometric Compression in Language Models
EMNLP 2023
Unnatural language processing: How do language models handle machine-generated prompts?
EMNLP 2023
How Transferable Are Reasoning Patterns in VQA?
CVPR 2021
Roses Are Red, Violets Are Blue... but Should VQA Expect Them To?
CVPR 2021
Supervising the Transfer of Reasoning Patterns in VQA
NeurIPS 2021