Tuomas Oikarinen
11 papers · 2021–2026 · 6 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 ↓+4 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (24) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π€ Dynamic Duo (10)
π¬
Deep Specialist
(10)
ποΈ
Keyword Collector
(61)
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
Top co-authors
Research topics
Artificial Intelligence
(11)
Core AI
(11)
Machine Learning
(5)
Deep Learning
(4)
Learning Types
(3)
Architectures
(2)
Optimization & Theory
(2)
Computer Vision
(1)
Natural Language Processing
(1)
Reinforcement Learning
(1)
Application Areas
(1)
Core Methods
(1)
Generation Β· Computer Vision
(1)
Generation Β· Natural Language Processing
(1)
Learning Paradigms
(1)
Keywords
concept bottleneck
(4)
neuron explanation
(2)
neuron interpretability
(2)
concept discovery
(2)
mechanistic interpretability
(2)
adversarial perturbation
(2)
masked language model
(1)
text generation
(1)
transfer learning
(1)
model interpretability
(1)
importance sampling
(1)
label noise
(1)
visual concept
(1)
adversarial attack
(1)
robust reinforcement learning
(1)
truthfulness
(1)
deep neural network
(1)
causal effect
(1)
machine unlearning
(1)
diffusion model
(1)
Papers
Beyond Top Activations: Efficient and Reliable Crowdsourced Evaluation of Automated Interpretability
CVPR 2026
Concept Bottleneck Language Models For Protein Design
ICLR 2025
Concept Bottleneck Large Language Models
ICLR 2025
Evaluating Neuron Explanations: A Unified Framework with Sanity Checks
ICML 2025
Interpretable Generative Models through Post-hoc Concept Bottlenecks
CVPR 2025
SAND: Enhancing Open-Set Neuron Descriptions through Spatial Awareness
WACV 2025
Linear Explanations for Individual Neurons
ICML 2024
CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks
ICLR 2023
Corrupting Neuron Explanations of Deep Visual Features
ICCV 2023
Label-free Concept Bottleneck Models
ICLR 2023
Robust Deep Reinforcement Learning through Adversarial Loss
NeurIPS 2021