Filip Sondej
2 papers · 2025–2025 · 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
❓
The Questioner
Top co-authors
Research topics
Keywords
direct preference optimization
(1)
neural network analysis
(1)
ai safety
(1)
mechanistic interpretability
(1)
safety fine-tuning
(1)
activation editing
(1)
defense mechanism
(1)
neuron analysis
(1)
toxicity reduction
(1)
language model safety
(1)
multi-agent system
(1)
agent compromise
(1)
malicious prompt
(1)
security trade-off
(1)
collaboration capability
(1)
malicious instruction
(1)