| Pretraživanje | Osvježi |
|
David W. Romero
@DavidWRomero1
|
22. pro |
|
Really exciting to have my first paper accepted at @iclr_conf #ICLR2020! It provides the first group theoretical approach towards equivariant visual attention. Nice things coming up next! @erikjbekkers @jmtomczak @Mark.
Co-Attentive Equivariant Nets: openreview.net/forum?id=r1g6o… pic.twitter.com/jppwAD8NJy
|
||
|
||
|
Ben Poole
@poolio
|
5. stu |
|
peer review in machine learning is broken #ICLR2020
|
||
|
|
||
|
Simon Osindero
@sindero
|
20. pro |
|
Really pleased that our paper "Multiplicative Interactions and Where to Find Them" was accepted to #ICLR2020.
openreview.net/forum?id=rylnK…
We present a unifying picture of several different neural net architectural motifs, that all involve multiplicative interactions...
1/3 pic.twitter.com/G8qetMMidx
|
||
|
||
|
Maha Elbayad
@melbayad
|
20. pro |
|
Happy to share that my @facebookai internship work "Depth-adaptive Transformer" has been accepted to #ICLR2020 . TL;DR: We dynamically adjust the computation per input and match the accuracy of a baseline Transformer with only 1/4 the decoder layers. openreview.net/forum?id=SJg7K…
|
||
|
|
||
|
Shao-Hua Sun
@shaohua0116
|
24. pro |
|
#ICLR2020 authors with > 5 submissions:
32 Sergey Levine
20 Yoshua Bengio
16 Cho-jui Hsieh
14 Pieter Abbeel
13 Liwei Wang, Tom Goldstein, Chelsea Finn, Bo Li, Jun Zhu
# of accepted papers:
13 Sergey Levine
7 Le Song, Jun Zhu
6 Cho-jui Hsieh, Jimmy Ba, Liwei Wang, Pushmeet Kohli pic.twitter.com/FzIfcojhhx
|
||
|
||
|
Guodong Zhang.
@Guodzh
|
20. pro |
|
Finally ...... our paper on "foresight pruning" just got accepted by @iclr_conf. We introduced a simple, yet effective pruning criterion for pruning networks before training and related the criterion to recent NTK analysis. #ICLR2020
openreview.net/forum?id=SkgsA…
|
||
|
|
||
|
Stephen Mayhew
@mayhewsw
|
20. pro |
|
Our paper studying the emergent cross-lingual properties
of multilingual BERT is accepted to #ICLR2020! Lots of dedicated work from (undergrads) Karthikeyan K and Zihan Wang. tl;dr it's network depth, not wordpiece overlap. openreview.net/forum?id=HJeT3…
|
||
|
|
||
|
Christian Szegedy
@ChrSzegedy
|
14. sij |
|
Mathematical Reasoning in Latent Space openreview.net/forum?id=Ske31… will be featured at #iclr2020.
Multiple step reasoning can be performed on embedding vectors of mathematical formulas.
|
||
|
|
||
|
ICLR 2020
@iclr_conf
|
20. pro |
|
Decisions released 🎉 Congratulations to accepted papers; to those who we could not accommodate, we wish you success in your ongoing research. See our blog for the first of our reflections. See you soon in Ethiopia. #ICLR2020 #OurHatata 🇪🇹🌍link.medium.com/ysHgHxoLy2
|
||
|
|
||
|
Kenta Oono
@delta2323_
|
20. pro |
|
Our paper (joint work with my supervisor
@btreetaiji ) has been accepted as a spotlight (48 long talks and 108 spotlights out of 2594 submissions) at #ICLR2020 !!
openreview.net/forum?id=S1ldO…
|
||
|
|
||
|
Danilo J. Rezende
@DeepSpiker
|
25. pro |
|
Some #ICLR2020 outcomes:
Accepted (spotlight): Hamiltonian Generative Networks, openreview.net/forum?id=HJenn…
Rejected: Causally Correct Partial Models for Reinforcement Learning openreview.net/forum?id=HyeG9…
Congrats to all my collaborators on both, independently of acceptance!
|
||
|
|
||
|
Marlos C. Machado
@MarlosCMachado
|
20. pro |
|
We're pleased to let you know that your submission, Exploration in Reinforcement Learning with Deep Covering Options, has been accepted at #ICLR2020!
openreview.net/forum?id=SkeIy…
This work was led by @DINDIN92, with Jee Won Park and George Konidaris.
More👇🏼
|
||
|
|
||
|
Keyulu Xu
@KeyuluXu
|
26. pro |
|
Our #ICLR2020 paper "What can neural networks reason about?" in 3 slides, presented at Winter Festa Episode 5 on Christmas. Great discussion with researchers from all over Japan! See Stefanie's talks for more detail bit.ly/2t7n2Nu (NeurIPS), bit.ly/2PYBd0u (IAS) pic.twitter.com/Zc2Rb5nl4E
|
||
|
||
|
Prashnna K Gyawali
@pkgyawali
|
20. pro |
|
Our paper ‘Progressive Learning and Disentanglement of Hierarchical Representations’ spearheaded by Zhiyuan has been accepted at #ICLR2020 (oral).
TL;DR: strategy to progressively learn disentangled hierarchical representations+new disentanglement metric! openreview.net/forum?id=SJxps…
|
||
|
|
||
|
Brendan O'Donoghue
@bodonoghue85
|
21. pro |
|
Our submission to #ICLR2020 was accepted as a spotlight, in it we try to clear up some confusion about Bayesian inference in RL, read it if you want to understand how Bayes and Bellman can get along! twitter.com/IanOsband/stat…
|
||
|
|
||
|
Yaron Lipman
@lipmanya
|
22. pro |
|
Accepted to @iclr_conf #ICLR2020: Settling permutation equivariance universality for popular deep models including DeepSets and some versions of PointNet. @SegolNimrod openreview.net/forum?id=HkxTw…
|
||
|
|
||
|
Urvashi Khandelwal
@ukhndlwl
|
20. pro |
|
Our work on nearest neighbor language models has been accepted to #ICLR2020 Woohoo!! Code coming in the new year! twitter.com/ukhndlwl/statu…
|
||
|
|
||
|
Jade Abbott
@alienelf
|
21. sij |
|
Excited to invite NLP researchers working in African Languages (or relevant NLP techniques) to submit to the @iclr_conf workshop in Addis:
"AfricaNLP - Unlocking Local Languages" 🌍
2-page extended abstracts!
Deadline: 14th Feb
#ICLR2020 #masakhane🔥
africanlp-workshop.github.io/cfp.html
|
||
|
|
||
|
Jia-Bin Huang
@jbhuang0604
|
20. pro |
|
In ICLR last year, we show that existing few-shot classification methods perform poorly across different domains (bit.ly/34GzQrl).
This year in #ICLR2020, we show how we can make few-shot learners generalize better to unseen domains (bit.ly/35HJATL)!
|
||
|
|
||
|
Adrien Gaidon
@adnothing
|
20. pro |
|
Self-supervised FTW! 2/2 papers from the team @ToyotaResearch accepted at #ICLR2020 🎉 Neural Outlier Rejection for Self-Supervised Keypoint Learning openreview.net/forum?id=Skx82… Semantically-Guided Representation Learning for Self-Supervised Monocular Depth openreview.net/forum?id=ByxT7… pic.twitter.com/ebeBLFsMn8
|
||
|
||