P Shravan Nayak
@PShravannayak
Master's student at Mila & Université de Montréal | Former SDE 2 at Microsoft | Passionate about pushing the boundaries of vision-language understanding 🚀
At ICML next few days presenting recent works! Hoping to reconnect. Get in touch if you are working on multimodal AI or post-training 📍Today 11am: West Exb Hall B2 (#W-400) presenting UI-Vision 🧠Also presenting @ Assessing World Models (18th) and Computer use Agents workshops
Looking forward to kicking off the day2 at #ACL2025NLP with my keynote! We'll be tackling new frontiers of AI alignment. 🗓️ Tuesday, 9:00 AM 🗣️ "Who's Gold? Re-imagining Alignment for Truly Beneficial AI" Here's a sneak peek of the talk. #AI #AIAlignment #NLProc #ACL2025NLP
Excited to be in Vienna this week for ACL 2025 where I will be prresenting ChartQAPro! 📊 Come by my poster on Tuesday from 4:00 to 5:30 PM if you're into VLMs, charts, or document understanding. Feel free to DM if you'd like to meet up during the conference! #ACL2025
🚨 New Benchmark Alert Our popular ChartQA📊benchmark is now saturated⚠️ Recent ones like CharXiv fall short in visual & question diversity. 🔥 Say hello to ChartQAPro: A more diverse & challenging benchmark for Chart Question Answering! 🧵👇 📄 arxiv.org/abs/2504.05506…
Meet me and @EdwardJian2 presenting later today our work on benchmarking agents in desktop GUIs at #ICML2025 Venue: West Exhibition Hall B2-B3 Poster No: 400
🚀 Super excited to announce UI-Vision: the largest and most diverse desktop GUI benchmark for evaluating agents in real-world desktop GUIs in offline settings. 📄 Paper: arxiv.org/abs/2503.15661 🌐 Website: uivision.github.io 🧵 Key takeaways 👇
Heading to #ICML2025 in Vancouver next week! Thrilled to present: 🖥️ UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction @ Main Conference 📆 Mon, July 15 | 🕑 2:00–4:30 PM 📍 West Hall B2–B3 | Poster W-400 We introduce a large-scale benchmark to…
Excited to be at #ICML2025 presenting 3 papers! 📌 UI-Vision (Poster, July 15, Hall B2-B3) 📌 LIVS (Poster, July 16, Hall B2-B3) 📌 CulturalFrames @ MoFA Workshop (July 18) If you're around and want to chat about agents, alignment, or cultural understanding, let's connect!
Started a new podcast with @tvergarabrowne ! Behind the Research of AI: We look behind the scenes, beyond the polished papers 🧐🧪 If this sounds fun, check out our first "official" episode with the awesome @gauthier_gidel from @Mila_Quebec: open.spotify.com/episode/7oTcqr…
Mila researchers are heading to @CVPR! Join @aagrawalAA and members of her lab to know more about learning language-compatible visual representations, building culturally-aware vision language models and more at poster sessions, workshops and talks in Nashville.
My lab’s contributions at #CVPR2025: -- Organizing @vlms4all workshop (with 2 challenges) sites.google.com/corp/view/vlms… -- 2 main conference papers (1 highlight, 1 poster) cvpr.thecvf.com/virtual/2025/p… (highlight) cvpr.thecvf.com/virtual/2025/p… (poster) -- 4 workshop papers (2 spotlight talks, 2…
"Build the web for agents, not agents for the web" This position paper argues that rather than forcing web agents to adapt to UIs designed for humans, we should develop a new interface optimized for web agents, which we call Agentic Web Interface (AWI).
Negar Rostamzadeh talking about meaningful cultural inclusion in VLMs @vlms4all workshop now in room 104E at #CVPR2025 !
Shravan Nayak (@PShravannayak) presenting the CulturalVQA challenge @vlms4all workshop (room: 104E). He will announce the winners soon and present some interesting analyses from the challenge results!
We'd love to hear your thoughts and feedback! 👋 I'm at #CVPR2025 until June 15th! Catch me presenting a highlight paper on language-compatible visual representations. 🗓️ Saturday, June 14th, at 10:30 AM 📍 ExHall D, Poster #379. If you're into VLMs, come say hi!
Excited to share our paper "Learning What Matters: Prioritized Concept Learning via Relative Error-driven Sample Selection"with an amazing co-lead Shivam Chandhok @ShivamChandhok2! We introduce PROGRESS, a data&compute-efficient framework for training VLMs!arxiv.org/abs/2506.01085
Sara Hooker speaking about Aya: Optimization under Severe Constraints @vlms4all workshop in room 104 E now! We also have swag: mugs, buttons and stickers! So stop-by!
Pitikorn Khlaisamniang receiving one of the awards of the CulturalVQA challenge! Congratulations! 🎆 #CVPR25
We have mugs, stickers and buttons at the @vlms4all workshop taking place now at #CVPR2025! Do stop-by!
A great lineup of talks ahead. Don’t miss them if you are at CVPR!
Our VLMs4All workshop is taking place today! 📅 on Thursday, June 12 ⏲️ from 9AM CDT 🏛️in Room 104E Join us today at @CVPR for amazing speakers, posters, and a panel discussion on making VLMs more geo-diverse and culturally aware! #CVPR2025
Excited to be a speaker at the #CVPR2025 workshop on Demographic Diversity in CV! My talk is at 2PM in Room 213 on June 11th (Title: "Tennessee == Smoky Mountains? Detecting stereotypes and measuring diversity through localization efforts"). I will talk about our recent work…
Join us at #CVPR2025 Demographic Diversity in Computer Vision workshop tomorrow! 📅 Wednesday, June 11, 9am-6pm 📍 room 213 (main session) + Hall D (poster sessions), the Music City Center We have an amazing lineup of speakers and panelists! Can't wait to meet you all there :)
Excited to be at my first #CVPR2025 this week and organising a workshop for the first time! Come join us at the @vlms4all workshop on June 12 (Thursday) in Room 104E, Music City Centre, Nashville. 📅 Workshop schedule: sites.google.com/view/vlms4all/…
I will be speaking at the Demographic Diversity in CV workshop tomorrow at 2.30pm. I will present the latest work from my group on Benchmarking Diverse Cultural Understanding in Vision-Language Models. So stop-by if you are at #CVPR2025!
Join us at #CVPR2025 Demographic Diversity in Computer Vision workshop tomorrow! 📅 Wednesday, June 11, 9am-6pm 📍 room 213 (main session) + Hall D (poster sessions), the Music City Center We have an amazing lineup of speakers and panelists! Can't wait to meet you all there :)
Les membres de Mila vont à @CVPR! Rejoignez @aagrawalAA et les membres de son laboratoire pour en savoir plus sur l'apprentissage de représentations visuelles compatibles avec le langage, la construction de modèles de vision et de langage sensibles à la culture et plus encore…
My lab’s contributions at #CVPR2025: -- Organizing @vlms4all workshop (with 2 challenges) sites.google.com/corp/view/vlms… -- 2 main conference papers (1 highlight, 1 poster) cvpr.thecvf.com/virtual/2025/p… (highlight) cvpr.thecvf.com/virtual/2025/p… (poster) -- 4 workshop papers (2 spotlight talks, 2…