Twitter | Pretraživanje | |
Pretraživanje Osvježi
David W. Romero 22. pro
Really exciting to have my first paper accepted at ! It provides the first group theoretical approach towards equivariant visual attention. Nice things coming up next! . Co-Attentive Equivariant Nets:
Reply Retweet Označi sa "sviđa mi se"
Ben Poole 5. stu
peer review in machine learning is broken
Reply Retweet Označi sa "sviđa mi se"
Simon Osindero 20. pro
Really pleased that our paper "Multiplicative Interactions and Where to Find Them" was accepted to . We present a unifying picture of several different neural net architectural motifs, that all involve multiplicative interactions... 1/3
Reply Retweet Označi sa "sviđa mi se"
Maha Elbayad 20. pro
Happy to share that my internship work "Depth-adaptive Transformer" has been accepted to . TL;DR: We dynamically adjust the computation per input and match the accuracy of a baseline Transformer with only 1/4 the decoder layers.
Reply Retweet Označi sa "sviđa mi se"
Shao-Hua Sun 24. pro
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
Reply Retweet Označi sa "sviđa mi se"
Guodong Zhang. 20. pro
Finally ...... our paper on "foresight pruning" just got accepted by . We introduced a simple, yet effective pruning criterion for pruning networks before training and related the criterion to recent NTK analysis.
Reply Retweet Označi sa "sviđa mi se"
Stephen Mayhew 20. pro
Our paper studying the emergent cross-lingual properties of multilingual BERT is accepted to ! Lots of dedicated work from (undergrads) Karthikeyan K and Zihan Wang. tl;dr it's network depth, not wordpiece overlap.
Reply Retweet Označi sa "sviđa mi se"
Christian Szegedy 14. sij
Mathematical Reasoning in Latent Space will be featured at . Multiple step reasoning can be performed on embedding vectors of mathematical formulas.
Reply Retweet Označi sa "sviđa mi se"
ICLR 2020 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. 🇪🇹🌍
Reply Retweet Označi sa "sviđa mi se"
Kenta Oono 20. pro
Our paper (joint work with my supervisor ) has been accepted as a spotlight (48 long talks and 108 spotlights out of 2594 submissions) at !!
Reply Retweet Označi sa "sviđa mi se"
Danilo J. Rezende 25. pro
Some outcomes: Accepted (spotlight): Hamiltonian Generative Networks, Rejected: Causally Correct Partial Models for Reinforcement Learning Congrats to all my collaborators on both, independently of acceptance!
Reply Retweet Označi sa "sviđa mi se"
Marlos C. Machado 20. pro
We're pleased to let you know that your submission, Exploration in Reinforcement Learning with Deep Covering Options, has been accepted at ! This work was led by , with Jee Won Park and George Konidaris. More👇🏼
Reply Retweet Označi sa "sviđa mi se"
Keyulu Xu 26. pro
Our 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 (NeurIPS), (IAS)
Reply Retweet Označi sa "sviđa mi se"
Prashnna K Gyawali 20. pro
Our paper ‘Progressive Learning and Disentanglement of Hierarchical Representations’ spearheaded by Zhiyuan has been accepted at (oral). TL;DR: strategy to progressively learn disentangled hierarchical representations+new disentanglement metric!
Reply Retweet Označi sa "sviđa mi se"
Brendan O'Donoghue 21. pro
Our submission to 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!
Reply Retweet Označi sa "sviđa mi se"
Yaron Lipman 22. pro
Accepted to : Settling permutation equivariance universality for popular deep models including DeepSets and some versions of PointNet.
Reply Retweet Označi sa "sviđa mi se"
Urvashi Khandelwal 20. pro
Our work on nearest neighbor language models has been accepted to Woohoo!! Code coming in the new year!
Reply Retweet Označi sa "sviđa mi se"
Jade Abbott 21. sij
Excited to invite NLP researchers working in African Languages (or relevant NLP techniques) to submit to the workshop in Addis: "AfricaNLP - Unlocking Local Languages" 🌍 2-page extended abstracts! Deadline: 14th Feb 🔥
Reply Retweet Označi sa "sviđa mi se"
Jia-Bin Huang 20. pro
In ICLR last year, we show that existing few-shot classification methods perform poorly across different domains (). This year in , we show how we can make few-shot learners generalize better to unseen domains ()!
Reply Retweet Označi sa "sviđa mi se"
Adrien Gaidon 20. pro
Self-supervised FTW! 2/2 papers from the team accepted at 🎉 Neural Outlier Rejection for Self-Supervised Keypoint Learning Semantically-Guided Representation Learning for Self-Supervised Monocular Depth
Reply Retweet Označi sa "sviđa mi se"