An incredible paper! This could really change the game for deepfake detection! Check it out: vision.huji.ac.il/ladeda/

Today we released JASCO 🥁🎵🪇! JASCO uses time-aligned conditions (e.g. drums, melody) as guiding controls for text-to-music generation. 📜Full Paper: arxiv.org/abs/2406.10970 🔊Samples: pages.cs.huji.ac.il/adiyoss-lab/JA… Alon Ziv Itai Gat Felix Kreuk Yossi Adi Stay tuned for updates.

1/ Commonsense reasoning needs multimodal knowledge, yet current LLMs focus mostly on text, limiting their integration of crucial visual information. We introduce vLMIG, a method that enhances LLMs' visual commonsense by integrating images into the decision-making process

ObjectDrop is accepted to #ECCV2024! 🥳 In this work from Google AI we tackle photorealistic object removal and insertion. Congrats to the team: Matan Cohen Shlomi Fruchter Yael Pritch  Alex Rav-Acha Yedid Hoshen Checkout our project page: objectdrop.github.io

🎊 Excited to share our latest work: “DGD: Dynamic 3D Gaussians Distillation”! 🚀 To appear at #ECCV2024. DGD distills 2D semantic features into dynamic 3D Gaussians, enabling the reconstruction and semantic segmentation of dynamic objects in 3D using only a user click. 🔗

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 🧵

Submitted an ML security paper to USENIX? Why not submit it to our workshop as well? 🪩🎉 Submission deadline September 14! Call for papers can be found on our website: redteaming-gen-ai.github.io Hope to see you in Vancouver ☃️

[1/8] Recent work has shown impressive Image-to-Video (I2V) generation results. However, accurately articulating multiple interacting objects and complex motions remains challenging. In our new work, we take a step toward addressing this challenge.

Release Announcement!📢💣 🥁🎷JASCO 🎶🪇 training & inference code + model weights are out! Paper📜: arxiv.org/abs/2406.10970 Samples🔊: pages.cs.huji.ac.il/adiyoss-lab/JA… Code🐍: github.com/facebookresear… Models🤗: huggingface.co/facebook/jasco… Alon Ziv Itai Gat Felix Kreuk Yossi Adi

[1/10]🚨 Introducing RewardSDS! 🚨 Standard SDS-based text-to-3D methods struggle with fine-grained alignment to user intent, often leading to artifacts or misaligned generations. Our solution 👇

🚨 New paper alert! 🚨 Millions of neural networks now populate public repositories like Hugging Face 🤗, but most lack documentation. So, we decided to build an Atlas 🗺️ Project: horwitz.ai/model-atlas Demo: huggingface.co/spaces/Eliahu/… 🧵👇🏻 Here's what we found:

Iran: Weeks away from having nuclear weapons since 1995