Krishnamurthy Dvijotham
17 papers · 2019–2023 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
π Cross-Pollinator (13) π§ Keyword Pioneer π Interdisciplinary Bridge π Conference Polyglot (7) π Renaissance Researcher (6)
π§
Keyword Pioneer
π
Cross-Pollinator
(13)
π₯
Unstoppable
(5)
π
Century Club
(17)
β‘
Prolific Year
(5)
ποΈ
Keyword Collector
(73)
Conferences
NIPS (9)
AAAI (2)
CVPR (2)
EMNLP (1)
IJCAI (1)
IJCNLP (1)
UAI (1)
Top co-authors
Keywords
adversarial robustness
(8)
neural network verification
(7)
formal verification
(6)
uncertainty quantification
(3)
convex optimization
(3)
adversarial attack
(3)
adversarial training
(2)
interpretable machine learning
(2)
selective prediction
(2)
concept bottleneck model
(2)
text classification
(2)
convex relaxation
(2)
interval bound propagation
(2)
symbol substitution
(2)
explainable ai
(1)
policy learning
(1)
machine translation
(1)
semidefinite programming
(1)
representation learning
(1)
self-supervised learning
(1)
Papers
Interactive Concept Bottleneck Models
AAAI 2023
Provably Bounding Neural Network Preimages
NIPS 2023
Training Private Models That Know What They Donβt Know
NIPS 2023
Learning to Receive Help: Intervention-Aware Concept Embedding Models
NIPS 2023
Role of Human-AI Interaction in Selective Prediction
AAAI 2022
Overcoming the Convex Barrier for Simplex Inputs
NIPS 2021
Make Sure You're Unsure: A Framework for Verifying Probabilistic Specifications
NIPS 2021
Lagrangian Decomposition for Neural Network Verification
UAI 2020
Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming
NIPS 2020
An efficient nonconvex reformulation of stagewise convex optimization problems
NIPS 2020
The Autoencoding Variational Autoencoder
NIPS 2020
Achieving Robustness in the Wild via Adversarial Mixing With Disentangled Representations
CVPR 2020
Adversarial Robustness through Local Linearization
NIPS 2019
Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagation
EMNLP 2019
A Dual Approach to Verify and Train Deep Networks
IJCAI 2019
Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagation
IJCNLP 2019
Knowing When to Stop: Evaluation and Verification of Conformity to Output-Size Specifications
CVPR 2019