Paul Gavrikov
6 papers · 2022–2026 · 3 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)
❓
The Questioner
(2)
Venues
Top co-authors
Research topics
Artificial Intelligence
(3)
Computer Vision
(3)
Deep Learning
(3)
Machine Learning
(3)
Core AI · Artificial Intelligence
(3)
Core AI · Computer Vision
(2)
Learning Types · Machine Learning
(2)
Optimization & Theory · Machine Learning
(2)
Application Areas
(1)
Applications
(1)
Architectures
(1)
Learning Types · Deep Learning
(1)
Optimization & Theory · Deep Learning
(1)
Techniques
(1)
Keywords
vision-language model
(3)
visual question answering
(2)
adversarial attack
(2)
convolutional neural network
(2)
model robustness
(2)
test-time adaptation
(1)
adversarial training
(1)
deep learning
(1)
out-of-distribution generalization
(1)
pre-trained model
(1)
spectral bia
(1)
multimodal fusion
(1)
visual understanding
(1)
prediction confidence
(1)
error analysis
(1)
visual cue
(1)
group relative policy optimization
(1)
shape bia
(1)
model bia
(1)
language prompting
(1)
Papers
TTRV: Test-Time Reinforcement Learning for Vision Language Models
CVPR 2026
VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes
CVPR 2026
Can We Talk Models Into Seeing the World Differently?
ICLR 2025
Can Biases in ImageNet Models Explain Generalization?
CVPR 2024
CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters
CVPR 2022
Robust Models are less Over-Confident
NeurIPS 2022