How does TensorFlow compare to Torch7 (http://torch.ch)? They look very similar to me.

Actually, this looks much more like Theano to me. It's all symbolic, it has symbolic differentiation, it's Python and it even seems to have a similar API like Theano.

In the Whitepaper (http://download.tensorflow.org/paper/whitepaper2015.pdf), it's compared to Theano, Torch and others.

That might be a strong advantage in its favor, though. Building a better version of a proven concept with similar usage/API's often gets more market uptake. Might get more use.

TensorFlow seems to emphasise the distributed computing aspects a lot more compared to Torch7. Also, TensorFlow is made for deploying machine learning pipelines in general, whereas Torch7 focuses on deep neural networks specifically.

I don't think NeuFlow is being actively developed anymore as most of the team is now working on the 'nn_X' co-processor out of Purdue and the startup teradeep. Clement Farabet (of Madbits/Twitter fame) and Yann LeCun are listed as consultant on the teradeep website (www.teradeep.com).