Assaf Arbelle
@ArbelleAssaf
Followers
115
Following
605
Media
2
Statuses
159
Father of 3 amazing daughters, Husband, Manager - AI-Vision Grp & Research Scientist @IBMResearch. Mastodon: @[email protected]
Israel
Joined November 2018
Just last week @leokarlin and @Eli_Schwartz presented our BrAD paper at @CVPR, and now we are releasing our first demo for Unsupervised Cross-Domain Image Retrieval on @Huggingface 🤗 with @Gradio!.Come check it out! ❤️.@IBMResearch.
huggingface.co
2
15
31
RT @roeiherzig: 🚨 Rough luck with your #ICCV2025 submission?. We’re organizing the 4th Workshop on What’s Next in Multimodal Foundation Mod….
sites.google.com
News: 🐈 Submissions are on OpenReview (Open Now!): https://openreview.net/group?id=thecvf.com/ICCV/2025/Workshop/MMFM4 MMFM has two paper tracks. More information under Call for Papers. Proceedings...
0
8
0
RT @SivanDoveh: IPLOC accepted to ICCV25 ☺️.Thanks to all the people that were part of it 🩷. The idea for this paper came by a lake during….
0
2
0
RT @mervenoyann: IBM released Granite-Vision-3.1-2B, a small vision LM with impressive performance on different tasks 😮🔥 . it comes with tr….
0
64
0
Very cool work by @chancharikm, Brandon Huang and the team! .We just scratched the surface of what is possible with Sparse Attention Vectors (SAVs).
🎯 Introducing Sparse Attention Vectors (SAVs): A breakthrough method for extracting powerful multimodal features from Large Multimodal Models (LMMs). SAVs enable SOTA performance on discriminative vision-language tasks (classification, safety alignment, etc.)!. Links in replies!
0
0
3
RT @gietema: There are some approaches to improve few-shot performance on VLMs: from simple fine-tuning on more images to using newer tech….
0
3
0
Check out our latest Live Multimodal Dataset!.
Introducing LiveXiv, a new, challenging and maintainable scientific multi-modal live dataset.Paper: Github: Dataset:
0
0
7
RT @roeiherzig: 🚨𝐌𝐮𝐥𝐭𝐢𝐦𝐨𝐝𝐚𝐥 𝐓𝐚𝐬𝐤 𝐕𝐞𝐜𝐭𝐨𝐫𝐬 (MTV) is accepted to @NeurIPSConf!🥳. We show how to perform many-shot ICL in LMMs using MTV repres….
0
17
0
RT @Eli_Schwartz: With the recent widespread discussions on X about OpenAI's newest o1 model🍓arithmetic skills, this feels particularly tim….
0
8
0
RT @AvihuDkl: Tokenization algorithms like BPE are the standard practice in NLP 📚.However, they have been mostly overlooked for discrete ac….
0
10
0
RT @roeiherzig: This fantastic work was done by the outstanding two undergrads, Brandon Huang and Chancharik Mitra, as well as @ArbelleAssa….
0
2
0
RT @SivanDoveh: The MMFM workshop takes place now at @CVPR .I'll be updating from the mmfm account if you want to follow 😁.
0
3
0
RT @_akhaliq: Trans-LoRA. towards data-free Transferable Parameter Efficient Finetuning. Low-rank adapters (LoRA) and their variants are po….
0
20
0
RT @leokarlin: Thanks for the highlight @_akhaliq!.We offer a simple and nearly-data-free way to move (large quantities) of custom PEFT mod….
0
6
0
RT @HildeKuehne: 🚨 @CVPR Challenge alert!🚨. Think you have a good MML for documents, infographics and text-rich images?. Challenge “What is….
sites.google.com
News: The program is set at: Program We are hosting the 🏆MMFM Challenge focused on multimodal document understanding. 🥳New information about the poster session. More information under Call for...
0
9
0
RT @MMFMWorkshop: In case you haven't noticed, we have $10K winner prizes for the top teams! .🤑🤑🤑.Also, we extended the deadlines for Phase….
0
9
0
RT @MMFMWorkshop: The prize for the challenge is revealed🥁🥁🥁submit a model that can find the amount in this infographic 😉 @CVPR @tensorlea….
0
4
0