Praveen Chandar retweeted
I’m excited to share our recent research and achievements around LLMs to create personalized narratives at Spotify!
Work done w many of my colleagues including the Prolific Team, @DivitaVohra @pchandarr @TonyJebara @mounialalmas ai.meta.com/blog/spotify-per…
Praveen Chandar retweeted
We are looking for research scientist interns in the fields of AI, ML, economics, LLMs, recommender systems, speech processing, NLP, or IR. These internships are based in our London office.
Apply at lifeatspotify.com/jobs/2024-…
Praveen Chandar retweeted
We are hiring summer interns to join us
@SpotifyResearch
. If you are a PhD student in AI (LLMs in particular) and would like to work on cutting edge research, apply to these openings. lifeatspotify.com/jobs/2024-…
Praveen Chandar retweeted
I will be presenting our paper "A is for Adele: An Offline Evaluation Metric for Instant Search" w/ @claclarke @BenCarterette @pchandarr @CharlotteHase today at 13:30 in room 105 on evaluation and classification session. Come join us if you are attending @acm_ictir ! #SIGIR2023
Praveen Chandar retweeted
Our paper is officially out! "Scoping Fairness Objectives and Identifying Fairness Metrics for Recommender Systems: The Practitioners’ Perspective" w/ @lexkbeattie & @hsmcramer 🎉 I'm presenting this paper at @TheWebConf tomorrow if you're around! 1/n
dl.acm.org/doi/10.1145/35435…
Praveen Chandar retweeted
I'm organizing a workshop on Machine Learning for Streaming Media at the #webconf2023 along with my colleagues - @pchandarr, Vladan Radosavljevic, Amit Goyal and Lan Luo.
#MachineLearning #Research
Praveen Chandar retweeted
Later this week, I'll present "A Probabilistic Position Bias Model for Short-Video Recommendation Feeds" at the Machine learning for Streaming Media workshop at #TheWebConf2023.
Here's a video detailing our contributions. See you in Austin! @TheWebConf
youtube.com/watch?v=iH8JzbtO…
Praveen Chandar retweeted
"Our goal for Spotify’s ML Platform has always been to create a seamless user experience for ML practitioners who want to take an ML application from development to production..."
And so, we introduced @raydistributed to our @Spotify ecosystem. engineering.atspotify.com/20…
Praveen Chandar retweeted
I’m so proud of the work we’re doing at Spotify, and even more proud of the team I get to grow with through it all.
Check out how we’re unleashing ML innovation at Spotify! @daikeshi @davidxia_ @pchandarr
BIG shoutout to the @anyscalecompute team for being awesome partners.
"Our goal for Spotify’s ML Platform has always been to create a seamless user experience for ML practitioners who want to take an ML application from development to production..."
And so, we introduced @raydistributed to our @Spotify ecosystem. engineering.atspotify.com/20…
Praveen Chandar retweeted
more evidence that metrics matter, folks. for more on on how to design metrics grounded in real tasks, check out these tutorials w @ChristineHosey5, @BrianStathomas, @pchandarr, @scinoise.
github.com/pchandar/beyond-a…
kdd2021-mixedmethods.github.…
github.com/jeanigarcia/recsy…
✨New preprint✨
Zero-shot GPT-3 does *better* at news summarization than any of our fine-tuned models. Humans like these summaries better. But all of our metrics think they’re MUCH worse.
Work/ w/ @jessyjli, @gregd_nlp. Check it out here: arxiv.org/abs/2209.12356
[1/6]
Praveen Chandar retweeted
A write-up on "Choice of Implicit Signal Matters: Accounting for User Aspirations in Podcast Recommendations" presented last week at #TheWebConf2022, work led by @ZahraNazari1 with @pchandarr @ghazalfazelnia Catie Edwards @BenCarterette & @mounialalmas.
research.atspotify.com/choic…
Praveen Chandar retweeted
Happy to see the momentum growing. If you are working on Human-AI interaction aspects & implications of generative AI, consider submitting your paper to @michael_muller 's workshop @acm_chi : generativeaiandhci.github.io… Deadline: Feb 24
Praveen Chandar retweeted
"Estimating Long-Term Engagement in Online Experiments using Survival Models" with @pchandarr, Brian St. Thomas, @lucasmaystre, Vijay Pappu, Roberto Sanchis Ojeda, Tiffany Wu, @BenCarterette @mounialalmas and @TonyJebara @TheWebConf #WWW2022 (2/4)
Praveen Chandar retweeted
Choice of Implicit Signal Matters: Accounting for User Aspirations in Podcast Recommendations from @ZahraNazari1, @pchandarr, @ghazalfazelnia, Catie Edwards, @BenCarterette and @mounialalmas @TheWebConf #WWW2022 (4/4)
Praveen Chandar retweeted
Interested in knowing how podcast categories affect user listening? Presenting `Understanding user podcast consumption using sequential treatment effect estimation' done with @SpotifyResearch at the #NeurIPS2021 workshop: Causal Inference Challenges in Sequential Decision Making.
Praveen Chandar retweeted
Many thanks to @pchandarr, Christine Hosey, and @BrianStathomas of Spotify for their excellent presentation and extensive discussion of their work on Mixed Methods Evaluation of Search and Recommendation. An @AdmsCentre Tech Talk, thanks to @danulaera for organising.
Praveen Chandar retweeted
Applications for summer 2022 internships @SpotifyResearch are open! Apply here or reach out if you have questions lifeatspotify.com/jobs/summe…
Praveen Chandar retweeted
Check our blog post about a recently presented paper at #KDD2021 on "Neural Instant Search for Music and Podcast" from @HashemiHelia (@SpotifyResearch intern), @aasishp, Mi Tian, @pchandarr, @mounialalmas & @BenCarterette.
research.atspotify.com/neura…
Praveen Chandar retweeted
📢 SEA is back after the summer break and will be about recommendation!
w/ @olivierjeunen (U. Antwerp) about advances in bandit learning for recommendation & @BenCarterette (@SpotifyResearch) about measuring listener delight.
Sign up for the Zoom link:
meetup.com/nl-NL/SEA-Search-…




















