Jacob Kahn
Jacob Kahn has 2 papers in our library, in 2023–2024, most of them on Language models & pretraining, Information retrieval & search, Vision & language; often with Luke Zettlemoyer, Arun Babu, Chunting Zhou.
No OpenAlex profile matched yet.
📄 2 works in our library · 🔗 Cited 213 times in our library · ⭐ Paper Stars ranking: #6134
Fields, topics and concepts
📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 2 worksComputer Science · 2 worksArtificial Intelligence · 2 worksComputer Vision and Pattern Recognition · 2 worksLanguage and Linguistics · 2 worksInformation Systems · 1 work
🧭 Topics 3Research subjects and languages the work is about.Vision & language · 1 workInformation retrieval & search · 1 workLanguage models & pretraining · 1 work
Works by year
2020s
Papers
- RA-DIT: Retrieval-Augmented Dual Instruction Tuning (2023 · 149 citations)
Large language models store knowledge only in their weights, so they handle rare facts poorly and are costly to update. - Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model (2024 · 83 citations)
Generative models usually handle text with next-token prediction and images with diffusion. Combining the two typically means either attaching a separate diffusion model to a language model or quantizing images into discrete tokens, which loses information. Transfusion trains a single transformer on mixed text–image…
Co-authors here
- Luke Zettlemoyer ×2
- Arun Babu
- Chunting Zhou
- Gergely Szilvasy
- Kushal Tirumala
- Lili Yu
- Maria Lomeli
- Michihiro Yasunaga
- Mike Lewis
- Mingda Chen
- Omer Levy
- Pedro Rodriguez
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/jacob-kahn/