ICLR

The International Conference on Learning Representations, a yearly spring meeting whose name reflects the deep-learning view that the central problem is learning good internal representations of data (representation learningrepresentation learning, n.: Letting a computer work out for itself how best to describe its data, such as the edges and shapes in images or the meanings of words, instead of relying on descriptions people design by hand.); it now ranks with NeurIPSNeurIPS, prop. n.: The largest yearly scientific conference on artificial intelligence and machine learning, held each December, where many of the field's landmark papers were first presented. and ICMLICML, prop. n.: A leading machine learning conference, first held as a workshop in 1980, where researchers gather each summer to present new learning methods and theory. among the most prestigious machine learning venues. Its distinguishing practice, kept since the first meeting, is public peer review on OpenReviewOpenReview, prop. n.: A website where conference papers are submitted and peer reviewed; for some conferences, anyone can read the reviews and the authors' replies.: anyone can read the submissions, reviews, author replies and decisions, and add comments. Landmark ICLR papers include the variational autoencodervariational autoencoder, n.: A neural network that learns to squeeze data into a compact, slightly fuzzy code and rebuild it, arranged so that decoding random codes produces new, plausible examples. (2014), the AdamAdam, prop. n.: The most widely used method for training neural networks. It smooths the direction of updates over time and automatically sets a separate step size for each setting based on how large its recent changes have been. optimizer and attentionattention, n.: A way for an AI model to choose what to focus on. For each word it processes, the model scores how relevant every other word is and draws information mostly from the relevant ones.-based machine translation (both 2015), and the vision transformervision transformer, n.: A way of applying the transformer, the design behind chatbots, to pictures: the image is cut into small square tiles that the model reads like words in a sentence. (2021); an early word2vecword2vec, prop. n.: A 2013 Google technique that learns a list of numbers for each word by training a very small network to predict which words appear near it across billions of words of text. paper appeared in its 2013 workshop track. Because its record is public, ICLR is a common dataset for research on peer review, including on reviews drafted with AI assistance.

You can read every ICLR review, including the harsh ones, on OpenReview.