Top Tweets for #Neurips2018
😆Happy to release OpenSphere, a PyTorch-based deep face recognition library.
👀It implements all our related work (SphereFace #CVPR2017, SphereFace+ #NeurIPS2018, SphereFace-R #TPAMI2022, SphereFace2 #ICLR2022)!
Web: https://t.co/aZBOYXeCcF
Code: https://t.co/S5rELLrz6L
1/4

A good moment, to celebrate those of us who toiled away as interns in pursuit of our dreams @pimdehaan #NeurIPS2018

7/ You can find more analyses and a comparison to our #NeurIPS2018 paper on context length manipulation in the paper!
tl;dr By adding interpretability to LSTMs through explicit timescale control, we were able to effectively estimate voxel timescales in the cortex!
Agree. This was one of the only things that really really bothered me at #NeurIPS2018 and #NeurIPS2019. Maybe omitting institution logos from posters (e. g. by providing a style template) would be something we can keep for when things go back to normal...
Typically you see big crowds around the posters with DeepMind/Google logos, regardless of topic
Typically people look at your name tag before deciding whether to talk to you
Sure, people can google you easily, but thats often after they've seen what you have to say! 😍#ICLR2020
Our pick of the week: Logeswaran et al. #NeurIPS2018 paper "Content preserving text generation with attribute controls". By @karakanta
https://t.co/KZ6C7kIozE
#nlproc @lajanugen @honglaklee
As undergrads, we sometimes played the game of translating texts in different ways using the weirdest attributes, e.g. Greek cooking recipes by Shakespeare. There's a system that can do a a similar thing.
https://t.co/sX3BA1JrnH
@fbk_mt

Special JSTAT issue on selected conference papers interfacing ML and physics: https://t.co/wjp7jQFPX2
Includes our extended #NeurIPS2018 paper on solving constraint satisfaction problems (e.g., SAT) using variational inference (w/ @tachim @ermonste) and many other cool works!

Powerful self-reflection this year about mistakes in last year's best paper #NeurIPS2018
https://t.co/ljvqOnlRLM
‘Bullshit’ talk by @DavidDuvenaud is a real #NeurIPS2019 masterpiece with honest and eye-opening insights on Neural ODEs. It reveals core problems in research itself after the hype he received for his #NeurIPS2018 award-winning paper.
Check it out!
https://t.co/5sn2btHSpC
Refreshingly honest take on hype cycle around the Neural ODE paper by one of authors presented this year at #NeurIPS2019, which won a best paper award at #NeurIPS2018 last year.
Video: https://t.co/NhmNr4mJGh

Pick up the Alchemy with Friends expansion pack during #NeurIPS2019 at the Microsoft booth!
Packs from #NeurIPS2018 are also available or you can print your own set: https://t.co/PMOU2Nw1Oe #AlchemyFriends
Gracias a la @utppanama por el reconocimiento a la mejor tesis de pregrado y publicación de @utpfisc. El trabajo https://t.co/iBUrcsbIMv se presento en el workshop @_LXAI en #NeurIPS2018. Ahora Carlos estudia su Maestría en #MachineLearning en @georgiatech. Felicidades colegas!

And will then go into applications in control/RL, starting with our #NeurIPS2018 paper on differentiable MPC
https://t.co/70GDsfESTe
Excited to share our #nips2018 paper on differentiable MPC and our standalone @PyTorch control package!
Joint work with Jimenez, Sacks, Boots, and @zicokolter.
Paper: https://t.co/uJXVAqi04l
@PyTorch MPC Solver: https://t.co/fnx5PQ5VXw
Experiments: https://t.co/kTzlDVpQy6

NeurIPS decisions are out, and my paper on unsupervised segmentation got accepted! See you soon, Canada! https://t.co/vxElK4QL9q
#neurips2018 #neurips

What does #reinforcementlearning actually look like? See how it works in this video explaining an #intelAI framework from the #NeurIPS2018 “AI for Prosthetics Challenge.” https://t.co/eilAWsZkiA
At #NeurIPS2018's “AI for Prosthetics Challenge, @IntelAIResearch presented a new framework, CERL, which trains learning devices to execute optimal actions for a task. Watch the full video to learn more: https://t.co/NOl95G6lIW #intelAI
Can neural networks understand performance and semantics of code? Our work on neural code comprehension takes a first step! #HPC #deeplearning #neurips2018
Though she's only finished her second year, she's already done tons of great work. There's our paper (https://t.co/6XXX7xugIl), but also results on private learning of halfspaces (https://t.co/OZtu0mnCzp) and collaborative PAC learning (https://t.co/j7EfK9ILAb, in #NeurIPS2018)
Insightful talk about BatchNorm by @andrew_ilyas In addition, there are some really nice tricks to inspect the learning landscape
Talk: https://t.co/8ayRVDpf2e
Paper: https://t.co/LDhq5P80di
#DeepLearning #computervision #NeurIPS2018
Last Seen Hashtags on Sotwe
Unexpected
Seen from Chile
عمتكم
Seen from Saudi Arabia
MGAI
Seen from United States
bleached
Seen from United Kingdom
二次絵ぶっかけ
Seen from Japan
mgai or ipcam filter:videos
Seen from Netherlands
batikenttraveſti
Seen from Turkey
stripchat
Seen from Turkey
bengali
Seen from Singapore
femboy
Seen from United States
Most Popular Users

Elon Musk 
@elonmusk
240.8M followers

Barack Obama 
@barackobama
118.7M followers

Cristiano Ronaldo 
@cristiano
114.5M followers

Donald J. Trump 
@realdonaldtrump
111.9M followers

Narendra Modi 
@narendramodi
107M followers

Rihanna 
@rihanna
98.7M followers

NASA 
@nasa
92.3M followers

Justin Bieber 
@justinbieber
91.8M followers

KATY PERRY 
@katyperry
90M followers

Taylor Swift 
@taylorswift13
84M followers

Lady Gaga 
@ladygaga
75.5M followers

Virat Kohli 
@imvkohli
73.4M followers

Kim Kardashian 
@kimkardashian
70.8M followers

YouTube 
@youtube
68.7M followers

Neymar Jr 
@neymarjr
66.4M followers

Bill Gates 
@billgates
65.2M followers

Selena Gomez 
@selenagomez
63.1M followers

The Ellen Show
@theellenshow
62.2M followers

CNN 
@cnn
61.7M followers

X 
@x
60.6M followers




























