Vivien Cabannes
11 papers · 2021–2025 · 5 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 ↓+2 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (22) 🌍 Conference Polyglot · Silver 👑 Triple Crown ❓ The Questioner
🔥
Unstoppable · Bronze
💎
Century Club · Bronze
Venues
Top co-authors
Research topics
Machine Learning
(10)
Learning Types · Machine Learning
(7)
Core Methods
(5)
Optimization & Theory
(4)
Artificial Intelligence
(3)
Deep Learning
(2)
Mathematics & Optimization
(2)
Natural Language Processing
(2)
Core AI
(2)
Resources & Methods
(2)
Architectures
(1)
Learning Paradigms
(1)
Learning Types · Deep Learning
(1)
Mathematics
(1)
Optimization
(1)
Keywords
self-supervised learning
(3)
associative memory
(3)
generalization error
(2)
active learning
(2)
outer product
(2)
representation learning
(2)
contrastive learning
(2)
online learning
(1)
weakly supervised learning
(1)
semi-supervised learning
(1)
partial feedback
(1)
data augmentation
(1)
in-context learning
(1)
mode estimation
(1)
attention mechanism
(1)
curse of dimensionality
(1)
laplacian regularization
(1)
entropy coding
(1)
sample complexity
(1)
embedding space
(1)
Papers
X-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs
ICLR 2025
Iteration Head: A Mechanistic Study of Chain-of-Thought
NeurIPS 2024
Learning Associative Memories with Gradient Descent
ICML 2024
Mode Estimation with Partial Feedback
COLT 2024
Scaling Laws for Associative Memories
ICLR 2024
Active Self-Supervised Learning: A Few Low-Cost Relationships Are All You Need
ICCV 2023
Birth of a Transformer: A Memory Viewpoint
NeurIPS 2023
How many samples are needed to leverage smoothness?
NeurIPS 2023
The SSL Interplay: Augmentations, Inductive Bias, and Generalization
ICML 2023
Active Labeling: Streaming Stochastic Gradients
NeurIPS 2022
Overcoming the curse of dimensionality with Laplacian regularization in semi-supervised learning
NeurIPS 2021