Yannis Tevissen
@yannistevissenAI Ph.D., Head of Science @moments_lab
Similar User
@VerdySylvain
@lmerabti3131
@_lerner_paul
@sebi113
@Riverjeep58
I'm very happy and proud to share the first official benchmark results of MXT-1.5, the latest video indexing technology developed by @moments_lab MXT-1.5 achieves state-of-the-art results on the Video-MME dataset 🧵
Nous avons le plaisir de vous convier le 3 décembre à un colloque sur les enjeux de citoyenneté et de l'engagement dans la vie politique des personnes handicapées à l'Assemblée Nationale. Sous le haut patronage de la Présidente de l’Assemblée @YaelBRAUNPIVET #Handicap 1/2
Are we still pretending this is "news", at this point?
Un nouveau joujou fait son entrée chez moi! Merci à @RemiCadene, @LeRobotHF et @therobotstudio de rendre la robotique accessible à tous!
I'm so bullish on decoding techniques like this making a huge leap forward for LLMs instead of scaling things 👋🏼 even better that it's released open ✨
We previously shared our research on Layer Skip, an end-to-end solution for accelerating LLMs from researchers at Meta FAIR. It achieves this by executing a subset of an LLM’s layers and utilizing subsequent layers for verification and correction. We’re now releasing inference…
.@lecocqcharlotte @AGenetet : En parcourant des messages dans un groupe pour #AESH sur un autre RS, il est très clair que bcp d'AESH ne comprennent pas leur rôle, qui est d'accompagner les enfants handicapés, pour compenser le handicap, et aider à leur inclusion 1/
Congratulations to our Head of Science @yannistevissen for the "Best Paper Presentation Award "in the Generative AI & NLP track at the Conference on Human System Interaction, 2024!
so we have a leaderboard for LLMs with video input, and most of them are open models 🔥👏 we are so back fam
Apitegromab met the main goal of boosting motor function over a year of treatment in young people with SMA type 2 or 3 in the SAPPHIRE trial. bit.ly/4eHxdKL
BREAKING NEWS The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Chemistry with one half to David Baker “for computational protein design” and the other half jointly to Demis Hassabis and John M. Jumper “for protein structure prediction.”
That’s why I did my PhD in a Physics Department 👀
BREAKING NEWS The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Physics to John J. Hopfield and Geoffrey E. Hinton “for foundational discoveries and inventions that enable machine learning with artificial neural networks.”
Your LLM can't understand videos and images? How sad 😔 Luckily we shipped a new task for video language models 🤗 look for video-text-to-text in left tab at @huggingface /models ⏯️ It also comes with docs in transformers and /tasks! 📖
🎉 Thrilled to announce that our paper “Towards Retrieval Augmented Generation over Large Video Libraries” won Best Presentation Paper in the Generative AI & NLP track at #HSI2024 in Paris! 🙌 📄 Paper: arxiv.org/abs/2406.14938 📝 Blog post: research.momentslab.com/blog-posts/rag…
Nos félicitations à madame @lecocqcharlotte pour sa nomination. Nous espérons que nous pourrons bientôt échanger avec elle sur les enjeux auxquels les personnes handicapées sont quotidiennement confrontées. #handicap #Gouvernement
Available in the EU?
Faire vivre l’héritage de #Paris2024 sur les sujets liés au handicap ? Difficile sans ministre, ministre délégué ou même secrétaire d’État en charge du sujet ! #GouvernenementBarnier
Non, non vous ne rêvez pas. Il n'y a pas de ministre, ni ministre délégué, ni secrétaire d'État au handicap . #GouvernenementBarnier 1😭
Wikimedia Enterprise just dropped full English & French Wikipedia on Hugging Face as structured JSON 🤯 Key points: 1. Parsed articles ready for machine learning pipelines 2. Perfect for AI model development - from pre-training to RAG 3. Includes metadata, Wikidata links, and…
With expanding context lengths, frontier models are able to process longer and longer videos. But how well do they really understand them and what kinds of questions can they answer? Check out our new dataset called Neptune with QADs for long video understanding!
Datasets for evaluation of long video understanding are rare. So with this in mind, today we describe Neptune, an open-source evaluation dataset that includes multiple-choice and open-ended questions for videos of variable lengths up to 15 minutes. More →goo.gle/3B41nZV
100% agree with this. The new models looks impressive but the term « thinking » is very misleading
Once again, an AI system is not "thinking", it's "processing", "running predictions",... just like Google or computers do. Giving the false impression that technology systems are human is just cheap snake oil and marketing to fool you into thinking it's more clever than it is.
Open video datasets are badly missing and slowing down the development of open-source video AI. This is why we're excited to introduce 🎥 FineVideo! 43k+ videos/3.4k hours annotated with rich descriptions, narrative details scene splits and QA pairs. huggingface.co/spaces/Hugging…
United States Trends
- 1. Travis Hunter 12,9 B posts
- 2. Arkansas 27,6 B posts
- 3. Heisman 5.493 posts
- 4. Quinn 14,5 B posts
- 5. Cam Coleman N/A
- 6. Clemson 5.689 posts
- 7. Colorado 67,7 B posts
- 8. #HookEm 3.019 posts
- 9. Isaac Wilson N/A
- 10. Northwestern 6.690 posts
- 11. $CUTO 8.149 posts
- 12. Sark 1.886 posts
- 13. #NWSL N/A
- 14. Sheppard 2.959 posts
- 15. Tulane 2.553 posts
- 16. Carnell Tate 1.714 posts
- 17. Mercer 4.075 posts
- 18. Jeremiah Smith 1.430 posts
- 19. #SkoBuffs 3.773 posts
- 20. Caleb Downs N/A
Something went wrong.
Something went wrong.