Ayesha Imran
Source-listed: Software Engineer - AI · ChipHub
- Language models
- Robotics
- Interpretability
Selected work
5- Persona-Vector Routing: A Lightweight, Interpretable Guardrail for Mitigating LLM HallucinationsContributor · 2025
- Safety Compass: Monitoring Safety-Relevant Concept Directions During LLM Fine-TuningContributor · 2026
- Inoculate or Reflect: Gating vs. Overwriting in Sycophancy ControlMaintainer · 2026
- Hallucination Vector ProjectContributor
- Confidential CopilotContributor · 2025