Srishti
ELLIS PhD Fellow @belongielab.org | @aicentre.dk | University of Copenhagen | @amsterdamnlp.bsky.social | @ellis.eu
Multi-modal ML | Alignment | Culture | Evaluations & Safety| AI & Society
Web: srishti.dev
- Reposted by Srishti[Not loaded yet]
- Reposted by Srishti[Not loaded yet]
- Reposted by Srishti[Not loaded yet]
- Reposted by Srishti[Not loaded yet]
- Reposted by SrishtiCongratulations Andrew Rabinovich (PhD ‘08) on winning the Longuet-Higgins Prize at #CVPR2025! (1/2)
- Reposted by Srishti[Not loaded yet]
- Reposted by Srishti[Not loaded yet]
- Reposted by Srishti[Not loaded yet]
- Reposted by Srishti[Not loaded yet]
- Reposted by Srishti[Not loaded yet]
- Reposted by Srishti[Not loaded yet]
- Reposted by SrishtiWould you present your next NeurIPS paper in Europe instead of traveling to San Diego (US) if this was an option? Søren Hauberg (DTU) and I would love to hear the answer through this poll: (1/6)
- Reposted by Srishti[Not loaded yet]
- Reposted by Srishti[Not loaded yet]
- Reposted by Srishti[Not loaded yet]
- Reposted by Srishti[Not loaded yet]
- Reposted by Srishti[Not loaded yet]
- Reposted by Srishti[Not loaded yet]
- I am excited to announce our latest work 🎉 "Cultural Evaluations of Vision-Language Models Have a Lot to Learn from Cultural Theory". We review recent works on culture in VLMs and argue for deeper grounding in cultural theory to enable more inclusive evaluations. Paper 🔗: arxiv.org/pdf/2505.22793
- Modern Vision-Language Models (VLMs) often fail at cultural understanding. But culture isn’t just recognizing things like food, clothes, rituals etc. It's how meaning is made and understood; it also about symbolism, context, and how these things evolve over time.
- Reposted by SrishtiThis morning at P1 a handful of lucky of lab members got to see the telescope while centre secretary Björg had the dome open for a building tour 🔭 (1/7)
- Reposted by Srishti🚀New Preprint🚀 Can Multimodal Retrieval Enhance Cultural Awareness in Vision-Language Models? Excited to introduce RAVENEA, a new benchmark aimed at evaluating cultural understanding in VLMs through RAG. arxiv.org/abs/2505.14462 More details:👇
- When you have a lot of work before the deadline push, you keep thinking of others things (distractions) you’d like to do. The day you get free, those things suddenly don’t seem important anymore. And kind of miss work! 🙄
- Reposted by Srishti[Not loaded yet]
- Reposted by Srishti[Not loaded yet]
- Reposted by SrishtiI will present our #ICLR2025 Spotlight paper MM-FSS this week in Singapore! Curious how MULTIMODALITY can enhance FEW-SHOT 3D SEGMENTATION WITHOUT any additional cost? Come chat with us at the poster session — always happy to connect!🤝 🗓️ Fri 25 Apr, 3 - 5:30 pm 📍 Hall 3 + Hall 2B #504 More follow
- Reposted by SrishtiToday, we share the tech report for SmolVLM: Redefining small and efficient multimodal models. 🔥 Explaining how to create a tiny 256M VLM that uses less than 1GB of RAM and outperforms our 80B models from 18 months ago! huggingface.co/papers/2504....
- Starting on a new social media is like moving to a new country and starting all over again. Find new friends, staying in touch with old ones, find what you would like (again!) and finding if you would fit in a new place (again!) 🙄
- Reposted by Srishti[Not loaded yet]
- When we read the news, images can convey different things than text itself. Unlike other works which look at text, we study this as a “multimodal” framing problem & analyze where text and images communicate different “frames”. Checkout our paper here: arxiv.org/abs/2503.20960 @aicentre.dk
- Using simple, small models with the goal of usability and scalability of the task, we hope social scientists, journalists and researchers use this as a first step in studying multimodal framing and its intended/unintended effects. More here: bsky.app/profile/mari...
- Reposted by Srishti[Not loaded yet]
- Reposted by Srishti[Not loaded yet]
