Large Language Models, LLM Reasoning, Instruction Tuning, RLHF, DPO
2024 – Present
Model Evaluation, Safety Benchmarking, Intent Drift Detection, Multi-turn Dialogue Evaluation
2024 – Present
Multi-Agent Systems, Agentic AI, Planning with LLMs, Collective Intelligence
2024 – Present
Efficient Inference, KV Cache Optimization, Speculative Decoding, Model Compression
2024 – Present
Retrieval-Augmented Generation, RAG Evaluation, GraphRAG, MCP Tools
2024 – Present
Alignment, Preference Modeling, Reward Modeling, Human Feedback Learning
2024 – Present