23 May 2023 in Talks
An invited research sharing at Wellcome Sanger Institute. Multi-domain alignment, LLMs, and generative AI (text-to-image).
Key advances in multi-domain alignment, LLMs, and generative AI:
Conditioning dropout, as a classifier-free guidance/conditioning. Guidance weight: to control the strength of guidance/alignment. Dr. (Amos) Xinshao Wang: Data + Modelling.
Dr. (Amos) Xinshao Wang: Data + Modelling Summary of research backgrounds, interest, projects.
Dr. (Amos) Xinshao Wang: Data + Modelling Summary of research backgrounds, interest, projects.
Research seminar on Deep Critical Learning (i.e., Deep Robustness): Example weighting and label correction.
Research seminar on Robust Deep Learning: Understanding real-world data and data-centric AI.
Summary of research progress on Synthetic Biology powered by Deep Learning.
In general, robust deep learning covers: missing labels (semisupervised learning); noisy labels (noise detection and correction); regularisation techniques; sample imbalance (long-tailed class distribution); adversarial learning; and so on.