🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Now accepted to COLM! 🦙Conference on Language Modeling

🚀 Excited to be part of this extremely cool benchmark! SEAM 🤐 is setting the new standard for evaluating LLMs on multi-document tasks. SEAM is also a dynamic benchmark generator for reporting more rigorous statistical performance measures. Check out Gili Lior's 🧵👇

I will be in Vienna at ICML Conference next week! DM or email me if you want to chat (: Together with Shashwat Singh, I will present our work, which provides a theoretical justification for steering vectors and improves upon them. Come to the Tue 11:30 AM poster session to learn more!

Our paper on description-based similarity has (finally) been accepted to Conference on Language Modeling! A joint work with Valentina Pyatkin, Amir DN Cohen, Avshalom Manevich, and (((ل()(ل() 'yoav))))👾. (1/6) arxiv.org/pdf/2305.12517

שירות הביטחון הכללי צריך לפתוח בחקירה לגבי מידת המעורבות של צמרת המשטרה, ח"כים ושרים בממשלה בניסיון ההפיכה המשטרית שבוצע אתמול. גורמים בכירים בצה"ל מאשרים הבוקר שהמחוז הדרומי במשטרה נמנע מלשלוח תגבור משטרתי לשדה תימן במשך 3 שעות. מדובר במחדל חמור או במעורבות חתרנית של גורמים

ACL folks: come check out our poster for LCD: Language Contrastive Decoding, today @ ACL Findings poster session ll 🐻 arxiv.org/abs/2408.04664

Honored to share that our work received an outstanding paper award at ACL2024! 🎉 Co-authored with my brilliant collaborators Alon Jacoby (equal contributor) and (((ل()(ل() 'yoav))))👾, our supervisor.

We released the #Jamba 1.5 open model family: - 256K #contextwindow - Up to 2.5X faster on #longcontext in its size class - Native support for structured JSON output, function calling, digesting doc objects & generating citations twtr.to/giIEE #AI #LLM #AI21Jamba

🐳Introducing Knowledge Navigator🐳: A new way to explore scientific literature! Our paper shows how LLMs can transform information overload into structured, navigable knowledge. paper: arxiv.org/pdf/2408.15836 page (with demo): knowledge-navigators.github.io 🧵/9

🚨🚨🚨cool new paper alert 😎 We study the ability of text-to-image models (SD) to learn copyrighted concepts and find the Imitation Threshold—the number of times a model has to “see” a concept during training to learn to generate it

🎉Excited to share our paper has been accepted to EMNLP 2024!

Attending 🌴#EMNLP2024 or interested in what people are working on these days? We organized it all for you with Knowledge Navigator! Explore all EMNLP 2025 accepted papers mapped by themes and subtopics—giving you a bird’s-eye view of the conference knowledge-navigators.github.io/emnlp_presenta…

The horse is the white of the eyes, and dark within RIP David Lynch 🤍

Excited to share that our paper, Jamba: Hybrid Transformer-Mamba Language Models, has been accepted to ICLR 2025! We’re honored to contribute to this important platform and the collective knowledge of the AI community by sharing our work openly and submitting it for peer review.

קח לך אשה וקנה לה buyme

Started a new role as Core Team Engineer at H working on multimodal LLM inference. Today we're launching Runner H, Holo-1, and Tester H! Grateful for my time at AI21 Labs on model serving. Up next: moving to Paris with my family 🇫🇷