We've partnered with Ari Folman, the Oscar nominated and two time Golden Globe winning director, on the first ever project created with the help of LTX Studio. As you can see, we’re all about bringing dreams to life and experience storytelling transformed.

Thanks Dan Roth for an inspiring talk on LLMs and reasoning DaSH #NAACL2024. Looking forward to hearing more at our panel discussion later today.

Done with the conference NAACL HLT 2024 ✅ Back to travel ✈️ 📍Mexico city ->📍Cancun

🚨🚨 Check out our new paper for a new ICL method that greatly boosts LLMs in long contexts! >> arxiv.org/abs/2406.13632

One week ago today, I was at #NAACL in Mexico City 🇲🇽 presenting a poster on our work about the Llammas🐑language model. Taking part in such a large event for the first time was an exciting experience, and I hope there will be more to come!😊 #NAACL24 #NAACL2024

🚀 Excited to introduce EvoAgent! A generic method to automatically extend expert agents to multi-agent systems via the evolutionary algorithm! Paper📄: arxiv.org/pdf/2406.14228 Website🌐: evo-agent.github.io Code💻: github.com/siyuyuan/evoag… [1/6]

Greetings from Fort Lauderdale, USA 🇺🇸 Last destination for my post conference trip! Soon to be back in Tel Aviv, Israel 🇮🇱

1/7 🚨 What do LLMs do when they are uncertain? We found that the stronger the LLM, the more it hallucinates and the less it loops! This pattern extends to sampling methods and instruction tuning. 🧵👇 Mor Geva Jonathan Berant Ori Yoran

📊📈🎯Happy to share a new benchmark: SEAM 🤐 - A Stochastic Evaluation Approach for Multi-document tasks Paper arxiv.org/pdf/2406.16086 Website seam-benchmark.github.io Code github.com/seam-benchmark… w/ Avi Caciularu Arie Cattan Shahar Levy Ori Shapira Gabriel Stanovsky

1/ 🎉 Our paper "Protein Language Models Expose Viral Mimicry and Immune Escape" is accepted at #ICML2024. We delve into how machine learning can help us understand tricky viruses better! 🦠 openreview.net/forum?id=gGnJB… #ICML #ML4LMS #science #bioinformatics #ML #virus #LLM

Human feedback is critical for language models development 💬, but collecting it is costly 🤑 We find that users naturally include feedback when interacting with chat models, and we can automatically extract it! arxiv.org/abs/2407.10944 W Leshem Choshen 🤖🤗 Omri Abend 🧵👇

Which is better, running a 70B model once, or a 7B model 10 times? The answer might be surprising! Presenting our new Conference on Language Modeling paper: "The Larger the Better? Improved LLM Code-Generation via Budget Reallocation" arxiv.org/abs/2404.00725 1/n

נתניהו, אני מושך בדש מעילך. עצור את הטירוף או תיזכר כמחולל שלו. זאת ההזדמנות האחרונה לעשות סיבוב פרסה ובמקום לקרוע את ישראל - לדאוג לעתידה

1/4 🧩 Excited to share our new paper "Visual Riddles"! We explore how small visual details can greatly impact understanding, providing a rigorous test for both visual comprehension and world knowledge factuality. 🧵

Exciting news! I'll present my poster at #ACL2024 about unsupervised document structure extraction tomorrow (Aug. 12th) at 12:45 PM 🕒 Come say hi and let's chat over the paper! arxiv.org/pdf/2402.13906 More details below ⬇️ w/ Gabriel Stanovsky (((ل()(ل() 'yoav))))👾 Ai2 HUJI NLP

Remember when we partnered with award-winning filmmaker Ari Folman? Check out how he used LTX Studio throughout his project to visualize his concept in the thread below 🧵⬇️ Make sure to follow our posts later today for a big announcement coming soon 👀 x.com/LTXStudio/stat…

סליחה, כרמלי. סליחה שלא עצרנו כשעוד היה אפשר. סליחה שנתנו להם להרוג אותך. הלוואי שראית ושמעת אותנו. הלוואי שלמרות שראית בעיניים את הרצח הנורא של אמא כנרת, גילית שאבא אשל ואחייך אלון ואור, הגיסה שלך ירדן והאחיינית שלך גפן, שרדו. הלוואי שראית איך החברות שלך נאבקו כדי שתחזרי

[1/7] 📜 I can finally share that our recent @NVIDIA project DiffUHaul --- A Training-Free Method for Object Dragging in Images has been accepted to #SIGGRAPHAsia2024 🎉. Project Page: omriavrahami.com/diffuhaul/

Human feedback is critical for aligning LLMs, so why don’t we collect it in the open ecosystem?🧐 We (15 orgs) gathered the key issues and next steps. Envisioning a community-driven feedback platform, like Wikipedia alphaxiv.org/abs/2408.16961 🧵