Shaona Ghosh
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Nemotron-4 340B Technical ReportSaved credit: Contributor · 2024Explore people connected to this work →
- AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM ExpertsSaved credit: First author · 2024Explore people connected to this work →
- AEGIS2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM GuardrailsSaved credit: First author · 2025Explore people connected to this work →
- A Simple Yet Effective Method for Non-Refusing Context Relevant Fine-grained Safety Steering in LLMsSaved credit: First author · 2025Explore people connected to this work →
- A Safety and Security Framework for Real-World Agentic SystemsSaved credit: First author · 2025Explore people connected to this work →