Recent Posts
Two Years of MLC: My Protests
A little over a year ago, I wrote a 6000-word retrospective, A Year of MLC: Selfish Takes Only, reflecting on building ML Collective, the non-profit and non-traditional researchers community, for a full year.
I Write ✍️
It probably doesn’t surprise you that I write.
Behind the Talk
As my narrowness talk accumulated 10k views in 3 days, I feel like clarifying a few behind-the-scene facts.
Recent Publications
- Character-Aware Models Improve Visual Text Rendering
ACL 2023 arXiv Twitter thread - Extremely Simple Activation Shaping for Out-of-Distribution Detection
ICLR 2023 arXiv Website Video Code Twitter thread - What does a platypus look like? Generating customized prompts for zero-shot image classification
ICCV 2023 arXiv Code Twitter thread - Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
TMLR arXiv Code Twitter thread - When less is more: Simplifying inputs aids neural network understanding
arXiv Twitter thread - Natural Adversarial Objects
Data Centric AI, NeurIPS 2021 arXiv Twitter thread - Language Models are Few-shot Multilingual Learners
EMNLP 2021 MRL Workshop arXiv