Saibo Geng

Saibo Geng

PhD student in EPFL

EPFL Data Science Lab

Biography

Hey there! I’m currently a Ph.D. student at EPFL’s Data Science Lab, where I’m advised by Prof. Robert West.

News

  • I will be joining Microsoft(Redmond) as a research intern in the summer of 2024.
  • I have built an open source library for grammar-constrained decoding called Transformers-CFG, feel free to check it out!

About Me

During my time at EPFL, I had the chance to dive into the world of knowledge-graph enhanced LLM with Prof. Antoine Bosseult(NLP lab), text summarization with Diego Antognini(now at Google), language model for law with Rémi Lebret(AI lab), and LLM evaluation with Maxime Peyrard(now professor at CNRS France). Prior to joining EPFL, I received my B.S. in Physics from University Paris-Saclay, France.

My research interests include:

  • Develop new constrained decoding research techniques for increasing LLM inference quality and/or efficiency.
  • Re-imagine the use and construction of context-free grammars (CFG) and beyond to fit Generative AI.
  • Design principled evaluation frameworks and benchmarks for measuring the effects of constrained decoding on a model.
Interests
  • Grammar-constrained Decoding
  • Efficient Decoding methods
  • Domain-Specific Language generation with LLM
Education
  • PhD in Computer Science, 2022-Now

    EPFL

Updates

Transformers-CFG is now available on GitHub
A grammar-constrained decoding library for LLM that supports CFG, EBNF, and unicode grammars
Low-memory Beam Search is merged into Huggingface Transformers
A low-memory beam search implementation that trades off speed for memory