Reading list
Every paper is linked to its publisher or arXiv page. PDFs are not stored in this repository; use the links (UF Libraries access may be needed for some journals).
Week 1 is an instructor-led model session. All other sessions are student-led; the instructor assigns papers and groups, posted on Canvas by Friday, January 15.
Further reading (not assigned)
- Oquab et al., DINOv2: Learning Robust Visual Features without Supervision, TMLR, 2024
- Zhou et al., A foundation model for generalizable disease detection from retinal images (RETFound), Nature, 2023
- Li et al., LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day, NeurIPS, 2023
- Acosta et al., Multimodal biomedical AI, Nature Medicine, 2022
- Hu et al., LoRA: Low-Rank Adaptation of Large Language Models, ICLR, 2022 (Week 5)
- Tu et al., Towards conversational diagnostic artificial intelligence (AMIE), Nature, 2025 (Week 9)
- Lång et al., AI-supported screen reading versus standard double reading in the MASAI trial, The Lancet Oncology, 2023 (Week 12)
- Gichoya et al., AI recognition of patient race in medical imaging: a modelling study, The Lancet Digital Health, 2022 (Week 12)
LLM architectures (Weeks 4 and 5)
- Raschka, A Visual Guide to Attention Variants in Modern LLMs, Ahead of AI, 2026
- Raschka, Recent Developments in LLM Architectures: KV Sharing, mHC, and Compressed Attention, Ahead of AI, 2026
- Raschka, A Dream of Spring for Open-Weight LLMs: 10 Architectures from Jan-Feb 2026, Ahead of AI, 2026
- Raschka, LLMs-from-scratch (code, Apache 2.0): GQA, MLA, sliding-window attention, and Llama, Qwen3.5, and Gemma 4 from scratch