Asynchronous Temporal Fields for Action Recognition. Iterative Alternating Neural Attention for Machine Reading. Bilingual Learning of Multi-sense Embeddings with Discrete Autoencoders. Superpixels: An Evaluation of the State-of-the-Art. End to End Learning for Self-Driving Cars. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5 …