Nabeel Shan
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Advanced LLM Adaptation: From Supervised Fine-Tuning to Reinforcement Learning for Dialogue SummarizationSaved credit: MaintainerExplore people connected to this work →
- End-to-End Reinforcement Learning from Human Feedback (RLHF)Saved credit: CreatorExplore people connected to this work →
- The Transformer Adaptation PlaybookSaved credit: CreatorExplore people connected to this work →
- GPT-Forge: A From-Scratch Transformer for Text GenerationSaved credit: CreatorExplore people connected to this work →
- Math VLM Pipeline: Handwritten Math to LaTeXSaved credit: CreatorExplore people connected to this work →