Shengcai Liu
4 papers · 2019–2025 · 2 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)
🚀
Conference Pioneer
Top co-authors
Research topics
Keywords
combinatorial optimization
(1)
learning theory
(1)
adversarial robustness
(1)
hyperparameter optimization
(1)
algorithm selection
(1)
parameter tuning
(1)
adversarial attack
(1)
theoretical bound
(1)
robustness evaluation
(1)
fine tuning
(1)
algorithm configuration
(1)
performance estimation
(1)
large language model
(1)
automatic configuration
(1)
attack ensemble
(1)
parallel portfolio
(1)
instance grouping
(1)
automatic algorithm configuration
(1)
parallel solver
(1)
safety degradation
(1)
Papers
Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets
ICML 2025
Reliable Robustness Evaluation via Automatically Constructed Attack Ensembles
AAAI 2023
On Performance Estimation in Automatic Algorithm Configuration
AAAI 2020
Automatic Construction of Parallel Portfolios via Explicit Instance Grouping
AAAI 2019