Vardan Papyan
16 papers · 2017–2025 · 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 ↓+6 more ↓ Show less ↑
🗺️ Taxonomy Completionist (24) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🐣 Hot Topic Early Bird
👑
Triple Crown
🧬
Topic Evolution
🌈
Renaissance Researcher
(5)
⚡
Prolific Year · Productive
💎
Century Club · Bronze
🗃️
Keyword Collector
(69)
Venues
Top co-authors
Research topics
Machine Learning
(13)
Deep Learning
(10)
Optimization & Theory · Machine Learning
(8)
Architectures
(7)
Application Areas
(5)
Artificial Intelligence
(4)
Core AI
(4)
Core Methods
(4)
Techniques
(3)
Natural Language Processing
(2)
Learning Types
(2)
Optimization & Theory · Deep Learning
(2)
Computer Vision
(1)
Healthcare & Medicine
(1)
Mathematics & Optimization
(1)
Keywords
neural collapse
(4)
deep neural network
(3)
residual network
(2)
representation learning
(2)
language model
(2)
sparse representation
(1)
low-rank decomposition
(1)
adversarial robustness
(1)
deep learning
(1)
image reconstruction
(1)
feature learning
(1)
feature representation
(1)
image super-resolution
(1)
covariate shift
(1)
spectral analysis
(1)
deep learning theory
(1)
magnetic resonance imaging
(1)
mean squared error
(1)
eigen-spectrum decomposition
(1)
singular value decomposition
(1)
Papers
Breach By A Thousand Leaks: Unsafe Information Leakage in 'Safe' AI Responses
ICLR 2025
OATS: Outlier-Aware Pruning Through Sparse and Low Rank Decomposition
ICLR 2025
On the Importance of Gaussianizing Representations
ICML 2025
Transformer Block Coupling and its Correlation with Generalization in LLMs
ICLR 2025
Linguistic Collapse: Neural Collapse in (Large) Language Models
NeurIPS 2024
Out of the Ordinary: Spectrally Adapting Regression for Covariate Shift
ICML 2024
Position: Fundamental Limitations of LLM Censorship Necessitate New Approaches
ICML 2024
Pushing Boundaries: Mixup's Influence on Neural Collapse
ICLR 2024
Sparsest Models Elude Pruning: An Exposé of Pruning’s Current Capabilities
ICML 2024
Residual Alignment: Uncovering the Mechanisms of Residual Networks
NeurIPS 2023
Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path
ICLR 2022
Traces of Class/Cross-Class Structure Pervade Deep Learning Spectra
JMLR 2020
Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians
ICML 2019
Neural Proximal Gradient Descent for Compressive Imaging
NeurIPS 2018
Convolutional Dictionary Learning via Local Processing
ICCV 2017
Convolutional Neural Networks Analyzed via Convolutional Sparse Coding
JMLR 2017