Sumanth Dathathri
9 papers · 2017–2022 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π£ Hot Topic Early Bird π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (6) π Academic Marathon (5)
π
Cross-Pollinator
(10)
π
Renaissance Researcher
(7)
πΊοΈ
Taxonomy Completionist
(23)
π
Conference Pioneer
Conferences
NIPS (3)
EMNLP (2)
AAAI (1)
CORL (1)
ICLR (1)
IJCAI (1)
Top co-authors
Research topics
Keywords
neural network verification
(3)
large language model
(2)
symbolic abstraction
(2)
toxicity detection
(2)
adversarial robustness
(2)
language model
(2)
language model evaluation
(1)
convex relaxation
(1)
constraint solving
(1)
formal verification
(1)
harmful content
(1)
machine learning
(1)
bias mitigation
(1)
text generation
(1)
abstraction refinement
(1)
first-order method
(1)
out-of-distribution detection
(1)
controllable generation
(1)
bayesian neural network
(1)
responsible ai
(1)
Papers
Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models
NIPS 2022
Challenges in Detoxifying Language Models
EMNLP 2021
Make Sure You're Unsure: A Framework for Verifying Probabilistic Specifications
NIPS 2021
Plug and Play Language Models: A Simple Approach to Controlled Text Generation
ICLR 2020
Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming
NIPS 2020
Plug-and-Play Conversational Models
EMNLP 2020
Inverse Abstraction of Neural Networks Using Symbolic Interpolation
AAAI 2019
Counter-example Guided Learning of Bounds on Environment Behavior
CORL 2019
Learning-Based Abstractions for Nonlinear Constraint Solving
IJCAI 2017