Yue Zhou
66 posts
@DataFleuret
PhD Student in NLP@UIC. #NLProc for Social Good, Healthcare #NLP #DeepLearning Amateur Foil Fencing Player. Classical Guitar. Snowboarding.
New open-source language model from Google AI: Flan-T5 🍮 Flan-T5 is instruction-finetuned on 1,800+ language tasks, leading to dramatically improved prompting and multi-step reasoning abilities. Public models: bit.ly/3sbNPDJ Paper: arxiv.org/abs/2210.11416
🎉 #StableDiffusion can be fine-tuned to generate medical images, and the outputs can be controlled using natural language text prompts! In our latest work, we use SD to create synthetic chest xrays and insert pathologies like pleural effusions. 🧵 #Radiology #AI #StanfordAIMI
Happy to share our work on Controllable Text Generation with NeurAlly-Decomposed Oracle (NADO) accepted at #Neurips2022! Looks like our model is excited about NeurIPS as much as we do. See more in arxiv.org/abs/2205.14219
I was a bit short on research ideas, so I decided to ask @chrmanning (as simulated by @huggingface 's BLOOM huggingface.co/bigscience/blo…) for some inspiration. The advice was...
Neural networks often pack many unrelated concepts into a single neuron – a puzzling phenomenon known as 'polysemanticity' which makes interpretability much more challenging. In our latest work, we build toy models where the origins of polysemanticity can be fully understood.
This morning, Mark Zuckerberg announced that @PyTorch is moving to a new, independent #PyTorchFoundation as part of the #LinuxFoundation umbrella. Learn what’s next for one of the leading platforms for #AI research and production applications. bit.ly/3RY99HW
The biggest game-changer for my research recently has been using @HelloSurgeAI for human data collection. With Surge, the workflow for collecting human data now looks closer to “launching a job on a cluster” which is wild to me. 🧵 of examples:
