Rotem Shalev-Arkushin

Thrilled to share that our paper ImageRAG has been accepted to #ICLR2026 🤩🇧🇷 Check it out: rotem-shalev.github.io/ImageRAG/ @RinonGal @ohadf @bermano_h

The GenAI LoRA ecosystem is a dense jungle. 🌿 Introducing CARLoS 🕵️‍♂️ - a system that retrieves LoRAs by how they alter diffusion behavior, and links these metrics to key concepts in copyright law. ⚖️ 🔗 shahar-sarfaty.github.io/CARLoS/ 📄 arxiv.org/abs/2512.08826 🧵[1/6]

Hey @iclr_conf, reverting scores is unnecessary punishment for the majority of the authors who had nothing to do with this incident and had successful rebuttals. Instead of detecting collusions on your end (you have a ton of metadata) why is this everyone’s burden to bear?

(1/4) [HOIDiNi] hoidini.github.io 🧵: Diffusion models are great at generating free-form human motion but tend to break down when objects enter the scene. Human–object interaction demands millimetric precision, and even tiny errors cause hands to float or penetrate surfaces

T2I models excel at realism, but true creativity means generating what doesn't exist yet. How do you prompt for something you can't describe? 🎨 We introduce VLM-Guided Adaptive Negative Prompting: inference time method that promotes creative image generation. 1/6

1/ What if you could animate a face directly from text? 🎭 Meet Express4D - a dataset of expressive 4D facial motions captured from natural language prompts, designed for generative models and animation pipelines. 🔗jaron1990.github.io/Express4D/ 📹👇

1/9 Excited to share EditP23! 🎨 Finally, a single tool for ALL your 3D editing needs: ✅ Pose & Geometry Changes ✅ Object Additions ✅ Global Style Transformations ✅ Local Modifications All driven by one simple 2D image edit. It's mask-free ✨ and works in seconds ⚡️. 🧵

1/ Can we teach a motion model to "dance like a chicken" Or better: Can LoRA help motion diffusion models learn expressive, editable styles without forgetting how to move? Led by @HSawdayee, @chuan_guo92603, we explore this in our latest work. 🎥 haimsaw.github.io/LoRA-MDM/ 🧵👇

Really impressive results for human-object interaction. They use a two-phase process where they optimize the diffusion noise, instead of the motion itself, to get to sub-centimeter precision while staying on manifold 🧠 HOIDiNi - hoidini.github.io

Excited to share that our new work, Be Decisive, has been accepted to SIGGRAPH! We improve multi-subject generation by extracting a layout directly from noise, resulting in more diverse and accurate compositions. Website: omer11a.github.io/be-decisive/ Paper: arxiv.org/abs/2505.21488

Excited to share that "IP-Composer: Semantic Composition of Visual Concepts" got accepted to #SIGGRAPH2025!🥳 We show how to combine visual concepts from multiple input images by projecting them into CLIP subspaces - no training, just neat embedding math✨ Really enjoyed working on this one with the amazing @DanaCohenBar, @RinonGal & @DanielCohenOr1

🔔Excited to announce that #AnyTop has been accepted to #SIGGRAPH2025!🥳 ✅ A diffusion model that generates motion for arbitrary skeletons ✅ Using only a skeletal structure as input ✅ Learns semantic correspondences across diverse skeletons 🌐 Project: anytop2025.github.io/Anytop-page

RefVNLI Towards Scalable Evaluation of Subject-driven Text-to-image Generation

How well LLMs are memorizing obscure details from scientific papers? I created a benchmark for that! Full code, dataset and data creation method included. tl;dr GPT4.5 is a major jump in scientific facts memorization. Thread below 👇

📜 Read our paper for more information: arxiv.org/abs/2502.09411 Work done w/ the amazing @RinonGal @bermano_h and @ohadf [3/3]

Given a text prompt, we utilize a VLM to dynamically identify concepts the models struggle to generate on their own, and retrieve compatible images. We use the images to guide the models to generate the missing concepts. [2/3]

Excited to introduce our new work: ImageRAG 🖼️✨ rotem-shalev.github.io/ImageRAG We enhance off-the-shelf generative models with Retrieval-Augmented Generation (RAG) for unknown concept generation, using a VLM-based approach that’s easy to integrate with new & existing models! [1/3]

🚀 Meet DiP: our newest text-to-motion diffusion model! ✨ Ultra-fast generation ♾️ Creates endless, dynamic motions 🔄 Seamlessly switch prompts on the fly Best of all, it's now available in the MDM codebase: github.com/GuyTevet/motio… [1/3]

🔔🔔Thrilled to share #MoMo [@SIGGRAPHAsia 2024 🥳🎉]: Exploring the attention space of #MotionDiffusionModels. Our training-free method enables cool applications like this motion transfer 🐒🐒. monkeyseedocg.github.io