I am a Staff ML Researcher at Qualcomm AI. 🔭
I am currently working on LLM efficiency and Agentic AI. 💬
I previously worked on:
- LLM agents and function calling:
- Dynamic Tool Dependency Retrieval for Efficient Function Calling (AAAI 2026 workshop, Oral presentation)
- LLM sparsity and cache efficiency:
- Machine Learning for GNSS localisation:
- Personalization and test-time adaptation of Face anti-spoofing models:
- Online Adaptive Personalization for Face Anti-spoofing (ICIP 2022)
- A Personalized Benchmark for Face Anti-spoofing (WACV 2022 workshop)
- Image-to-Graph Generative models:
- Image-Conditioned Graph Generation for Road Network Extraction (NeurIPS 2019 workshop)
- Generative vision models for medical imaging:
- Chest X-ray Inpainting with Deep Generative Models (2018 arXiv preprint)
- Context encoding chest X-rays (2018 arXiv preprint)
- Object detection in visual question answering:
- Adding Object Detection Skills to Visual Dialogue Agents (ECCV 2018 workshop)
Note: the repositories in this GitHub profile are 6+ years old, covering research and coursework projects from my MSc and BSc. They are not representative of my current coding skills and practices.