Akhil Mathur
@akhilmathurs
Followers
492
Following
411
Media
46
Statuses
176
Research Scientist in Generative AI @MetaAI | ex-@BellLabs
London, England
Joined August 2017
Itβs here! Meet Llama 3, our latest generation of models that is setting a new standard for state-of-the art performance and efficiency for openly available LLMs. Key highlights. β’ 8B and 70B parameter openly available pre-trained and fine-tuned models. β’ Trained on more
0
0
7
RT @spdimitris: π€Ώ What is latent masking and why is it relevant to multimodal learning?. In our paper in ML4MHD at #ICML2023 we presented Cβ¦.
0
4
0
RT @ylecun: This is huge: Llama-v2 is open source, with a license that authorizes commercial use!. This is going to change the landscape ofβ¦.
0
3K
0
So happy to see this important work published. Model fairness should be a key consideration when we optimize machine learning pipelines for edge devices. Our paper offers a framework to approach on-device ML fairness, along with extensive experimental findings for speech models.
0
0
6
Great progress towards efficient and adaptive FL on ultra-constrained devices. Work led by @VincentMo6 during his internship at @BellLabs.
Federated Learning for constrained edge devices need to become more efficient and adaptive. In this preprint, we offer Centaur: a framework that adaptively partitions FL training across multiple clients owned by each user. PDF: 1/4
0
1
19
RT @AnupriyaTuli: π₯π₯ Join us for ACM SIGCHI Symposium for πππ ππ§π π
π«π’ππ§ππ¬ at IIT Bombay, India, 9-11 December 2022!π§΅. Speakers: https://t.β¦.
0
23
0
All train services between London and Cambridge are delayed because there is a swan π¦’ sitting on the track π€·π»ββοΈπ€¦ββοΈ.
1
0
16
Charlie Dean was outside the crease for more than 85% of all balls she started at the non-striker's end. "Spirit of cricket!" π.
Went back to the full match replay. Charlie Dean was leaving her crease early starting with her 2nd ball at the non-striker's end in the 18th over. Ball still in bowler's hand. Dean is never looking at the bowler to see if/when the ball has been released. Basic lack of awareness.
0
0
5
Shohreh Deldari (@ShohrehDeldari) from RMIT is now presenting her super cool work on cross modal self supervised learning. #UbiComp2022
1
5
41
Hyunsung Cho (@hciresearcher) is presenting her work FLAME π₯ which shows how to make federated learning work in multi-device environments #UbiComp2022
0
2
34
Brilliant talk today by @IanTangC on our collaborative self-supervised work aimed at making HAR training data-efficient. #UbiComp2022 @ubicomp
In our upcoming paper at #IMWUT @ubicomp, we present ColloSSL: a technique for collaborative self-supervised learning among a group of devices. 𧡠(1/n)
0
3
27
"At the stroke of the midnight hour, when the world sleeps, India will awake to life and freedom. Happy 75th Independence Day! The journey has just begun #IndiaAt75
0
1
16
Looking forward to presenting our work and learning more about ML efficiency @ Deep Learning Indaba. Kudos to the incredible organizing team for putting this event together.
The exciting part is the incredible in-person talks and lineups we have planned in Tunis. Including:. - @KateKallot, Head of emerging areas at NVIDIA.- @akhilmathurs, Principal Research Scientist at Bell Labs.- @zngu, Associate Professor, University of Edinburgh
0
3
16
If you are attending #ICML2022, please join our spotlight talk on self-supervised FL on July 19 and poster presentation on July 21. Please feel free to DM if you are up for a chat on FL, self-supervision, and embedded ML.
Very happy to share that our work on self-supervised federated learning in resource-constrained settings has been accepted at #ICML 2022. A fantastic outcome for the internship work by @EkdeepL in collaboration with .@IanTangC @raswak. Arxiv link and more details are coming soon.
0
3
22
Glad to share that our work FLAME has been accepted to IMWUT '22. We explore algorithmic & system challenges for federated learning in the presence of multiple data-generating devices on a user. Proud of our intern @hciresearcher who led this work. @raswak
1
1
41
An excellent summary of our upcoming ICML paper on unsupervised FL. The paper is out on arXiv Also, a big thank you to the Flower framework which helped us scale our FL experiments.
flower.ai
A unified approach to federated learning, analytics, and evaluation. Federate any workload, any ML framework, and any programming language.
Hello, world! We present to you πΆOrchestraπΆ, an unsupervised framework for federated learning! The paper was recently accepted at #ICML. Abs:
1
3
11
RT @raswak: We have met some terrific talents lately and we want to meet more. Shout out to lateral thinkers and bright engineers to join aβ¦.
0
10
0
In addition to the technical contributions, I'm very proud of how seamlessly this work was done in remote collaboration with two brilliant students: @jinga_lala1 @IanTangC and my teammates @ChulhongM @raswak.
0
0
3