Research Focus

Exploring the intersection of neural networks and symbolic reasoning

NeuroSymbolic AI

Bridging neural networks and symbolic reasoning to build hybrid, interpretable systems that combine structured knowledge with deep learning.

Source Attribution

Developing reliable citation techniques and evidence selection methods that ensure every statement in generated text is traceable to its origin.

Trustworthy AI

Building AI systems that are transparent, robust and fair, focusing on interpretability, safety and user confidence in automated decisions.

Information Retrieval

Designing efficient retrieval and ranking algorithms to fetch relevant documents and passages that power retrieval-augmented generation.

NLP

Exploring natural language processing from sentiment analysis to language generation, with a focus on large language models and reasoning.

Technical Skills

Retrieval & RAG
  • Chunking & query reformulation
  • Dense & sparse retrieval
  • FAISS / HNSW indexing
LLM Tuning
  • Instruction tuning (SFT)
  • Preference tuning (PPO, DPO, GRPO)
  • PEFT (LoRA / QLoRA)
Tools & Libraries
  • PyTorch, Hugging Face (Transformers, PEFT)
  • LlamaIndex, LangChain
  • FAISS, SQL, Git