Salman Abdullah
Hi, I'm a joint BS/MS student in Computer Science (2025) at Stanford University, focusing on Artificial Intelligence.
I conduct research in Machine Learning and Natural Language Processing at Stanford AI Lab. My main focus is factuality in language models and information retrieval. Notably, I contributed to the development of RAPTOR, a state-of-the-art retrieval system, which got accepted to ICLR 2024.
Currently, I'm building a domain-specific retriever to enhance the performance of medical foundation models under the guidance of Dr. Michael Moor and Professor Jure Leskovec. I am actively seeking industry experience to expand my horizons and to contribute to exciting AI projects.
Publications
-
Parth Sarthi, Salman Abdullah, Aditi Tuli, Shubh Khanna, Anna Goldie, Christopher D. Manning.
RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval.
ICLR 2024
[pdf] [code]
Projects
- VariFastSpeech: Variational Inference for Non-Autoregressive Text to Speech
- Reply to emails with AI
- AI-based custom cover letter generator.
- RAG based student assistance chatbot to answer questions based on uploaded documents
Highlight Courses
- CS 149: Parallel Computing
- CS 236: Deep Generative Models
- CS 229: Machine Learning
- CS 224n: Natural Language Processing with Deep Learning
- CS 131: Computer Vision: Foundations and Applications
- CS 161: Design & Analysis of Algorithms
- CS 111: Operating Systems Principles
Excited to introduce RAPTOR 🦖 at #ICLR2024:
— Salman Abdullah (@salmanabdullah_) February 2, 2024
RAPTOR is a tree-based retrieval approach that navigates between granular details and a holistic understanding of documents. It sets a new SoTA on 3 benchmarks.
Read the paper here: https://t.co/MQ0FEXfNCc https://t.co/JGZXTYy1R3