The actual paper for DALL-E was released only a few days after we published our episode 2, so in this episode we re-visit DALL-E in its full published glory. Joining us as a special guest for this episode is Aditya Ramesh from OpenAI, the lead author of DALL-E. DALL-E blog post: https://openai.com/blog/dall-e/  DALL-E paper: https://arxiv.org/abs/2102.12092  DALL-E code (encoder/decoder model only, so far): https://github.com/openai/dall-e Deep Learning Deep Dive is also available on YouTube, where we scroll through relevant parts of the paper and code while talking about them: https://www.youtube.com/watch?v=PtdpWC7Sr98 We reached out and collected written consent from all participating audience speakers.

The actual paper for DALL-E was released only a few days after we published our episode 2, so in this episode we re-visit DALL-E in its full published glory. Joining us as a special guest for this episode is Aditya Ramesh from OpenAI, the lead author of DALL-E. DALL-E blog post: <a href="https://www.youtube.com/redirect?event=video_description&amp;redir_token=QUFFLUhqazJYZWFlN1RwSi1QRFdVelNGeVlDMTQxOUVSd3xBQ3Jtc0ttSjd0T3dodUkxMllFOVh6a0R5bnFFSHhmY24xNWpmQno3QTV4bzFIZjRTMDJHQ3B2SmNIcGVXbjE4Y0tLVzF3Qmo1aEZOcDZxS1NPUVZNc29kV1J0ZDVtdHBNQ3RqWnZIVl9NWGMyU2J0UzdtSkZ1RQ&amp;q=https%3A%2F%2Fopenai.com%2Fblog%2Fdall-e%2F" rel="nofollow" target="_blank">https://openai.com/blog/dall-e/</a> DALL-E paper: <a href="https://www.youtube.com/redirect?event=video_description&amp;redir_token=QUFFLUhqbkd0eGthSzd1Rjh4amJidGlvNFVTYUhXSmZNd3xBQ3Jtc0tuNEVqZzVqWmE5ZDlyUnhmOUYxcDdVd1VlXzhRZ3hqVFlpT0NaWFVvLUZFcmtzUFVJcUh6ZlNfUjFrZy1ibkI3LUFjcnowOFNaM3h2X3NNMzloVlVtcXhWbHNxbDlTMHhwMjFyWGZ0WHQ2ZUtBT2ZWMA&amp;q=https%3A%2F%2Farxiv.org%2Fabs%2F2102.12092" rel="nofollow" target="_blank">https://arxiv.org/abs/2102.12092</a> DALL-E code (encoder/decoder model only, so far): <a href="https://www.youtube.com/redirect?event=video_description&amp;redir_token=QUFFLUhqazZTall0Z1Q5ckxzYmYxZEZSbExHdFZKRnhLZ3xBQ3Jtc0tuZmtaUXNFZFp6VmluRmpVWGRDRjVBRWlSejNlZHlXR1R4MjhVei1KN09BZ2ZDbEYyOFBmdnN3Zk5GdGVYSllPaGN6V1RHa3ZGSGx5bXlnU21BQ1EwNGZ3d2c0ZVpqRG53N3lHWnVRVHIwOXV6a2lRNA&amp;q=https%3A%2F%2Fgithub.com%2Fopenai%2Fdall-e" rel="nofollow" target="_blank">https://github.com/openai/dall-e</a> Deep Learning Deep Dive is also available on YouTube, where we scroll through relevant parts of the paper and code while talking about them: <a href="https://www.youtube.com/watch?v=PtdpWC7Sr98" rel="nofollow" target="_blank">https://www.youtube.com/watch?v=PtdpWC7Sr98</a> We reached out and collected written consent from all participating audience speakers.

Episode #3: DALL-E in depth

Andrej Karpathy and Justin Johnson deep dive into OpenAI's DALL-E and use it as an anchor point to recurse into some of the recent work in AI on image generation. Approximate agenda: DALL-E Blog Post: https://openai.com/blog/dall-e/ ImageGPT https://openai.com/blog/image-gpt/ VQ-VAE https://arxiv.org/abs/1711.00937 VQ-VAE-2 https://arxiv.org/abs/1906.00446 Gumbel-Softmax / Concrete Distribution https://arxiv.org/abs/1611.01144 https://arxiv.org/abs/1611.00712 VQGAN https://arxiv.org/abs/2012.09841 Andrej's attempted re-implementation of VQVAE and GumbelSoftmax: https://github.com/karpathy/deep-vector-quantization/blob/main/model.py You can see a video version of this episode on YouTube: https://www.youtube.com/watch?v=gMc90bqHMSM We reached out to all speakers and obtained their written consent to appear in this recording.

Andrej Karpathy and Justin Johnson deep dive into OpenAI's DALL-E and use it as an anchor point to recurse into some of the recent work in AI on image generation. Approximate agenda: DALL-E Blog Post: <a href="https://openai.com/blog/dall-e/" rel="nofollow" target="_blank">https://openai.com/blog/dall-e/</a> ImageGPT <a href="https://openai.com/blog/image-gpt/" rel="nofollow" target="_blank">https://openai.com/blog/image-gpt/</a> VQ-VAE <a href="https://arxiv.org/abs/1711.00937" rel="nofollow" target="_blank">https://arxiv.org/abs/1711.00937</a> VQ-VAE-2 <a href="https://arxiv.org/abs/1906.00446" rel="nofollow" target="_blank">https://arxiv.org/abs/1906.00446</a> Gumbel-Softmax / Concrete Distribution <a href="https://arxiv.org/abs/1611.01144" rel="nofollow" target="_blank">https://arxiv.org/abs/1611.01144</a> <a href="https://arxiv.org/abs/1611.00712" rel="nofollow" target="_blank">https://arxiv.org/abs/1611.00712</a> VQGAN <a href="https://arxiv.org/abs/2012.09841" rel="nofollow" target="_blank">https://arxiv.org/abs/2012.09841</a> Andrej's attempted re-implementation of VQVAE and GumbelSoftmax: <a href="https://github.com/karpathy/deep-vector-quantization/blob/main/model.py" rel="nofollow" target="_blank">https://github.com/karpathy/deep-vector-quantization/blob/main/model.py</a> You can see a video version of this episode on YouTube: <a href="https://www.youtube.com/watch?v=gMc90bqHMSM" rel="nofollow" target="_blank">https://www.youtube.com/watch?v=gMc90bqHMSM</a> We reached out to all speakers and obtained their written consent to appear in this recording.

Episode #2: DALL-E and friends in image generation

Long-form technical deep dives with Andrej Karpathy and Justin Johnson

Deep Learning Deep Dive

The best podcasts about ourselves as well as the world through the lense of Science. Specific topics include things about our brain, emotions to biology, physics and more!

Best Episodes on Science, Humans & The World

The best podcast episodes of the most interesting stories and things. From skyping someone while they're in space, to tracking down and meeting a telephone scammer in person, to the story of a Galapagos. These episodes will keep you and all your friends entertained and captivated for hours. Learn something new in every episode! Add episodes you're interested into your queue below!