Over the weekend, I played with fine-tuning GPT-2 and XLNet (on Colab). Super applause to Huggingface Transformers, it makes all sorts of pre-trained LM extremely accessible. The framework has evolved a lot from a wrapper of pre-trained BERT. It now unifies all models with AutoModel* with different capabilities, so that we only have to know the key and not care about the API. The repo also contains very handy fine-tuning and inference scripts.
Our team TOAD ranked #1 in Terminal Live @ UIUC, sponsored by Correlation One and Citadel. We will be sharing a cash prize of $12,000!
Our paper Phrase Grounding by Soft-Label Chain Conditional Random Field is accepted as long paper in EMNLP-IJCNLP 2019! arXiv link
Recently I played with neural networks, changing the matrix multiplication in NN’s propagation into a convolution, with FFT to speed up computation. This architecture allows for training neural networks with larger layer sizes, given that we allow weights to be reused in a certain way. Preliminary experiments shows 93% accuracy on MNIST dataset.
In virtual reality, when a 360 monocular video canvas surrounds virtual objects, there will be depth mismatch that creates artifacts. In this scenario, monocular depth cues provided by the canvas will override binocular depth cues on the virtual object. In this paper, I propose an algorithm to geometrically transform the virtual object in order to compensate for the mismatch. This allows natural fusion of virtual objects and 360 environments in virtual reality.
subscribe via RSS