Tuomas Oikarinen
10 papers · 2021–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Cross-Pollinator (15) πΊοΈ Taxonomy Completionist (15) π§ Keyword Pioneer π Conference Polyglot (6) π Renaissance Researcher (5)
π
Interdisciplinary Bridge
π
Century Club
(10)
β‘
Prolific Year
(5)
Conferences
ICLR (4)
ICML (2)
CVPR (1)
ICCV (1)
NIPS (1)
WACV (1)
Top co-authors
Keywords
adversarial perturbation
(2)
policy learning
(1)
robust reinforcement learning
(1)
visual concept
(1)
adversarial attack
(1)
generative model
(1)
diffusion model
(1)
deep neural network
(1)
generative adversarial network
(1)
concept bottleneck
(1)
open-set recognition
(1)
clip model
(1)
neuron explanation
(1)
concept bottleneck model
(1)
concept discovery
(1)
robustness analysis
(1)
deep q-learning
(1)
adversarial network
(1)
model steering
(1)
open-vocabulary learning
(1)
Papers
SAND: Enhancing Open-Set Neuron Descriptions through Spatial Awareness
WACV 2025
Interpretable Generative Models through Post-hoc Concept Bottlenecks
CVPR 2025
Concept Bottleneck Large Language Models
ICLR 2025
Concept Bottleneck Language Models For Protein Design
ICLR 2025
Evaluating Neuron Explanations: A Unified Framework with Sanity Checks
ICML 2025
Linear Explanations for Individual Neurons
ICML 2024
Corrupting Neuron Explanations of Deep Visual Features
ICCV 2023
Label-free Concept Bottleneck Models
ICLR 2023
CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks
ICLR 2023
Robust Deep Reinforcement Learning through Adversarial Loss
NIPS 2021