causal-gen

Tromp binary lambda calculus less hardware dependent.[0] CFR[] makes for more dimensional programming.[9] Sectorlisp blinking lights demo[10] Adding unicode support / ansi escape color escape sequences to/with 'mov' would make for a single 'extended typed' mov[8] 64bit instruction set. Nature uses coded color color blocks. So, use ELVM[1] with LinearLisp[2] to do picturesqe tile programming[3] with Piet[4] or other suitable 'make brain hurt less' esolang[5]? Although, diy direct brain programming is less of a reality today, may still 'make brain hurt' [6]. Adding some abstraction does make for easier comprehension.[7] --------- [0] : a) https://news.ycombinator.com/item?id=4666562 b) https://en.wikipedia.org/wiki/One-instruction_set_computer [1] elvm : https://github.com/shinh/elvm [2] linear lisp : https://github.com/ys

Ever wondered how we can make our deep generative models respect causal structure? This is key to creating authentic "what if" scenarios in our images! In our latest research, we deal with high-fidelity image counterfactuals, the generation of images based on "what if" scenarios that align with a specified causal graph. Why is this important? Causality gives us the tools to carry out principled counterfactual inference, which - among other things - is useful for maintaining subject identity in image counterfactuals. Principled counterfactuals of structured variables like images have great potential for: (i) Generating causal explanations (ii) Providing targeted data augmentation (iii) Evaluating fairness & robustness (iv) Protecting your privacy and more... Check out the paper, code, and Huggingface demo! https://arxiv.org/abs/230