Samira Shabanian
5 papers · 2016–2024 · 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
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(13)
🐣
Hot Topic Early Bird
Top co-authors
Research topics
Keywords
reinforcement learning
(2)
model pruning
(2)
language model
(2)
gender bia
(2)
token probability distribution
(1)
generative model
(1)
variational autoencoder
(1)
dead-end analysis
(1)
successor feature
(1)
attention head
(1)
demographic parity
(1)
toxic discourse
(1)
controllable text generation
(1)
bidirectional model
(1)
large language model
(1)
counterfactual example
(1)
memory efficient
(1)
helmholtz machine
(1)
computationally efficient
(1)
approximate inference
(1)
Papers
Fairness-Aware Structured Pruning in Transformers
AAAI 2024
Successor Features for Efficient Multi-Subject Controlled Text Generation
ICML 2024
Deep Learning on a Healthy Data Diet: Finding Important Examples for Fairness
AAAI 2023
Systematic Rectification of Language Models via Dead-end Analysis
ICLR 2023
Bidirectional Helmholtz Machines
ICML 2016