Harm de Vries

Visually Grounded Interaction and Language: accepted works together with spotlights are available: nips2017vigil.github.io at #nips2017 #nips

#NIPS2017 Vis-Grounded Interaction & Lang wrkshp deadline Nov 17! Consider submitting your #ICLR2018 / #CVPR2018 drafts + other recent wrk

Extended version of our paper on tackling visual reasoning with conditional linear transformations is out: arxiv.org/abs/1709.07871

Code: github.com/ethanjperez/fi…. Extended analysis includes examining the compositional nature of learned question embeddings.

Please consider submitting your work to our NIPS17 workshop on Visually-Grounded Interaction and Language! nips2017vigil.github.io x.com/abhshkdz/statu…

New paper with @univ_lille & @UMontreal uses RL to learn grounded natural language via image-based game 'Guess What' arxiv.org/abs/1703.05423

CVPR paper on dialogue with images accepted! Congrats to @harm_devries, @apsarathchandar, @AaronCourville et al. guesswhat.ai

Rise of the machines can make life better. The Times, excellent article by Emma Duncan on universal income @1843mag thetimes.co.uk/article/rise-o…

Nice article by @laurent_dinh on posterior inference for samples from Gumbel-Max trick laurent-dinh.github.io/2016/11/22/gum…

Best company party at #nips2016: definitely #rocketai

Proud to have been part of the #RocketAI launch tonight. Sorry all the seed funding will be going to legal fees.

Best party of #nips2016 award goes to #rocketai (rocketai.org). Definitely a company to watch closely.

@mopatel @hugo_larochelle @Miles_Brundage The dataset will be released on January 28th. Website with more info will follow later.

"GuessWhat?! Visual object discovery through multi-modal dialogue," de Vries et al.: arxiv.org/abs/1611.08481

@ilijabogunovic @saaayeee I think your Alexa is smarter than Amazon's. Just send her in and win 500K.

@kastnerkyle haha

@kastnerkyle Cool! Curious why the LSTMs you've trained do not sound like this one.

@kastnerkyle what's the trick that makes this one work?