Víctor Campos

Research Scientist at Deepmind

[Víctor Campos @vcampos7]

@creus_roger @iclr_conf Congratulations!!

[Sundar Pichai @sundarpichai]

Today developers can start building with our first version of Gemini Pro through Google AI Studio at https://t.co/rCsWHcHvEe. 

Developers have a free quota and access to a full range of features including function calling, embeddings, semantic retrieval, custom knowledge grounding, chat functionality and more. It supports 38 languages across 180+ countries. Gemini Ultra is coming early next year. We’re excited to see what you build! https://t.co/6rUrrgKvKe

[Google DeepMind @GoogleDeepMind]

We’re excited to announce 𝗚𝗲𝗺𝗶𝗻𝗶: @Google’s largest and most capable AI model.

Built to be natively multimodal, it can understand and operate across text, code, audio, image and video - and achieves state-of-the-art performance across many tasks. 🧵 https://t.co/mwHZTDTBuG

[Nemanja Rakicevic @nrkcv]

Thrilled to announce that
"Human-level Atari 200x faster"
has been accepted to @iclr_conf !

Main contributions:
- faster propagation of learning signals
- handling differing value scales
- efficient NN architecture
- robust policy updates

[paper]: https://t.co/fsITl5hULE

[Damian Borth @damianborth]

If you are interested in representation learning from a population of neural network models, have a look at our @NeurIPSConf paper today at the poster session. Konstantin @schurholt is happy to answer all of your questions - @DocXavi @spcl_eth @rengglic @vcampos7

[Míriam Bellver @miriambellver]

If you are in Barcelona this December, you cannot miss the DL Bcn Symposium! Call for talks and posters is now open. Looking forward to it (my first on-site conference since pandemic🤯)

[Wojciech Czarnecki @wojczarnecki]

Are you interested in open-ended learning? Reinforcement learning, multi-agent, neuroscience or learning dynamics design are close to your heart? Or maybe you have unique background/skills that you think are relevant? Lets make beautiful plots together https://t.co/7hMX9MLxRl!

[Pau Rodríguez @prlz77]

A nice blog post on Seasonal Contrast is out 😀@oscmansan explains how to do self-supervised learning on satellite images by leveraging seasonal changes. Very simple and elegant implementation with @PyTorchLightnin
https://t.co/SOX1soj9Cz

[Gergely Neu @neu_rips]

SPREAD THE WORD:
I'M HIRING PHD STUDENTS FOR FALL 2021 AT @UPFBarcelona / @DTIC_UPF!!

The project is about reinforcement learning theory and is funded by my recent @ERC_Research Starting Grant. (#ERCStG)

Details: https://t.co/fhoAwmLJGQ

Deadline: Feb 12, 2021

[Joan Serrà @serrjoa]

Two #internship opportunities to work with the @Dolby Barcelona #AI team!

Want to pursue research on learnable #speech representations for different downstream tasks? Let's do it under the supervision of @santty128 and me. Check https://t.co/tDCm2NLPLu

[Víctor Campos @vcampos7]

@icmlconf I was unable to access the Zoom meeting for my poster (6014) today, it was stuck at "waiting for the host to start this meeting" during the whole session. I tried to contact helpdesk but the channel would not even load. Who am I supposed to contact about this?

[Xavi Giró @DocXavi]

Víctor Campos (@vcampos7) will present "Explore, Discover and Learn (EDL)" for unsupervised RL at #ICML2020:

1) Tue Jul 14 11am. PDT / 8pm CEST
2) Tue Jul 14 11pm PDT / Wed July 15 8am CEST

If you registered, find him at: https://t.co/kOnqqKH5RQ

@BSC_CNS @SFResearch @IdeaiUpc

[Felix Hill @FelixHill84]

During my PhD (In 2014), with @kchonyc I worked on un / self / semi-supervised learning of sentence representations. We evaluated these reps by training a *linear* classifier on low-data tasks.

https://t.co/IZKzWkLti2

I always wondered if doing this made any sense?

1/N

[Google DeepMind @GoogleDeepMind]

Interested in playing around with RL? We’re happy to announce the release of Acme, a light-weight framework for building and running novel RL algorithms.

We also include a range of pre-built, state-of-the-art agents to get you started. Enjoy! https://t.co/2wzpK3nCKp

[Richard Socher @RichardSocher]

Excited to introduce the AI Economist: Extends ideas from Reinforcement Learning for tackling inequality through learned tax policy design.
The framework optimizes productivity and equality.
Blog: https://t.co/5xferEiUkg
Paper: https://t.co/CEbX79SROD
Q&A: https://t.co/kzSrlMCvM7

[John Langford @JohnCLangford]

ICML 2020 (https://t.co/Z7CaAZ4KEb) will be a virtual conference. We've been having discussions with ICLR folks about their plans, and will be learning from their experience (they are up first). We hope to enable as much of the normal ICML experience as possible, virtually.

[Cesare Cugnasco @cugni]

CATALUNYA.-Barcelona Activa reconoce a @Qbeast_io con un premio al mejor proyecto de alto impacto tecnológico. @BSC_CNS https://t.co/IJQDQtz574

[Xavi Giró @DocXavi]

We present Explore, Discover and Learn (EDL), a novel paradigm for unsupervised skill discovery in RL.

Work by Víctor Campos (@vcampos7) from @BSC_CNS.

Co-authored with @alexrtrott, @CaimingXiong @RichardSocher @SFResearch, & @JordiTorresAI @BSC_CNS.

https://t.co/ujBX4kQr4j

[Víctor Campos @vcampos7]

@DocXavi @BSC_CNS @alexrtrott @CaimingXiong @RichardSocher @SFResearch @JordiTorresAI Code is now available at https://t.co/sGWzwM6oqT

[Deep Learning Barcelona Symposium @dlbcnai]

New video from #DLBCN 2018 published:

Víctor Campos (@vcampos7) from @BSC_CNS @la_UPC "Skip RNN: learning to skip state updates in recurrent neural networks", presented in #ICLR2018

https://t.co/NafFMerJ1h