Lead AI Researcher at Google DeepMind https://xitter.cf/t.co/eh6D79dSp0 Views are personal
United Kingdom
Joined November 2011
- Tweets49
- Following46
- Followers126
- Likes40
Pushkar Mishra retweeted
📜 💡**New paper & dataset** Our paper [to be presented as a spotlight at NeurIPS’25] presents DIVE, a novel dataset for aligning GenAI models to pluralistic viewpoints. DIVE and accompanying experiments advocate for a shift in both: alignment strategies and safety evaluations.
Pushkar Mishra retweeted
🤔🤖Most AI systems assume there’s just one right answer—but many tasks have reasonable disagreement. How can we better model human variation? 🌍✨
We propose modeling at the individual-level using open-ended, textual value profiles! 🗣️📝
arxiv.org/abs/2503.15484
(1/?)
Read our paper here:
ai.meta.com/research/publica…
This is huge: Llama-v2 is open source, with a license that authorizes commercial use!
This is going to change the landscape of the LLM market.
Llama-v2 is available on Microsoft Azure and will be available on AWS, Hugging Face and other providers
Pretrained and fine-tuned models are available with 7B, 13B and 70B parameters.
Llama-2 website: ai.meta.com/llama/
Llama-2 paper: ai.meta.com/research/publica…
A number of personalities from industry and academia have endorsed our open source approach: about.fb.com/news/2023/07/ll…
Pushkar Mishra retweeted
This is huge: Llama-v2 is open source, with a license that authorizes commercial use!
This is going to change the landscape of the LLM market.
Llama-v2 is available on Microsoft Azure and will be available on AWS, Hugging Face and other providers
Pretrained and fine-tuned models are available with 7B, 13B and 70B parameters.
Llama-2 website: ai.meta.com/llama/
Llama-2 paper: ai.meta.com/research/publica…
A number of personalities from industry and academia have endorsed our open source approach: about.fb.com/news/2023/07/ll…
Pushkar Mishra retweeted
Check out this super interesting @NeurIPSConf paper! #NeurIPS22
Paper: arxiv.org/abs/2207.09980
Poster: 👇
From the amazing @yihong_thu @ImPushMish Luca Pontus @riedelcastro at @ai_ucl @uclcs @MetaAI
REFACTOR GNNS: Revisiting Factorisation-based Models from a Message-Passing Perspective
ai.papers.bar/paper/ebc65b78…
Factorisation-based Models (FMs) often outperform Graph Neural Networks (GNNs) FMs struggle to...
🧵 👇
Pushkar Mishra retweeted
Come and join us at @AmsterdamNLP! We have a PhD position in #NLProc with a focus on modelling the spread of misinformation, in collaboration with Meta AI. Looking for students with an NLP/ML background and an interest in language and society. vacatures.uva.nl/UvA/job/PhD…
Pushkar Mishra retweeted
Attending my first #NeurIPS2021🤩
I'll be presenting our work
"Towards a robust experimental framework & benchmark for lifelong language learning"
my #AI Master thesis with
@HYannakoudakis @Nithin_Holla @ImPushMish @KatiaShutova
📢1430-1800 GMT Dec 7
🔗 neurips.cc/virtual/2021/post…
Some #ContinualLearning experiments leak task IDs & produce misleading gradients...
which actually results in #CatastrophicForgetting!🤯
In a #NeurIPS2021 paper
we design an Experimental Framework for #lifelonglearning in #NLP with a suite of benchmarks
openreview.net/forum?id=yJyI…
Pushkar Mishra retweeted
Excited to share that our paper on lifelong language learning got accepted at #NeurIPS2021 datasets and benchmarks track. A great collaboration with Aman Hussain @Nithin_Holla @ImPushMish @KatiaShutova openreview.net/pdf?id=yJyIjW… #MachineLearning #NLProc
Pushkar Mishra retweeted
Keeping @Facebook users safe from policy violating content like hate speech, misinformation or child exploitation, is a top priority for @facebookai. This paper surveys the AI techniques we have developed and used to preserve integrity on our platform arxiv.org/pdf/2009.10311.pdf
See you in Minneapolis :D
#NAACL2019
Modelling online communities using graph neural networks for abusive language detection. Our #naacl2019 paper is now on arXiv! arxiv.org/abs/1904.04073 #NLProc with @pushkarmishra96 @marcodeltredici @KatiaShutova
:)
“Abusive language detection using graph convolutional networks” with @pushkarmishra96 @marcodeltredici Katia Shutova accepted at #naacl2019! See you in Minneapolis!
Pushkar Mishra retweeted
Huge congratulations to Professor Caucher Birkar, one of four recipients of the 2018 Fields Medals. cam.ac.uk/research/news/camb…
Pushkar Mishra retweeted
Croatia, you have my heart. ♥️ #FrancevsCroatia #FifaWorldCup2018
Try out our new browser extensions for automated #abusive language detection on #Twitter using deep neural networks: clean-inter.net #ArtificialIntelligence #NLProc
This should have been initiated quite a while ago. Many students are misled into false sense of achievement by... fb.me/GajPdoD1