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

🔔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

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

Excited to share that our latest paper: "InstanceGen: Image Generation with Instance Level Instructions" was recently accepted to #SIGGRAPH2025! InstanceGen tackles the problem of generating images for complex multi-object prompts tau-vailab.github.io/InstanceGen/ 👇🧵[1/7]

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

Best Paper Award @ SIGGRAPH'25 🥳

Excited to share that TokenVerse won Best Paper Award at SIGGRAPH 2025! 🎉 TokenVerse enables personalization of complex visual concepts, from objects and materials to poses and lighting, each can be extracted from a single image and be recomposed into a coherent result. 👇

Excited to share that TokenVerse won Best Paper Award at SIGGRAPH 25 🥳

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

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 Haim Sawdayee, Chuan Guo, we explore this in our latest work. 🎥 haimsaw.github.io/LoRA-MDM/ 🧵👇

Very excited to introduce our 🌺#ICCV2025 highlight🌺 paper “BlendedPC”! This work sets a new standard in localised semantic editing of point clouds, using purely text as guidance. Project page: tau-vailab.GitHub.io/BlendedPC Wanna hear more? 👇🧵

Just released the code for my final first-author PhD project 😮 I'll be presenting it next week at #SIGGRAPH2025! Not just another attention technique, it's a 𝐍𝐞𝐬𝐭𝐞𝐝 𝐀𝐭𝐭𝐞𝐧𝐭𝐢𝐨𝐧. Built on SDXL, so quality isn't best, but it's super fun to try. Code and demo below👇

Very honored to receive Best Paper Award for TokenVerse at @Siggraph today! Daniel Garibi will be presenting it tomorrow morning, go check it out! token-verse.github.io

Honored to receive the SIGGRAPH Best Paper Award 🏆 omer tov Roni Paiss If you want to know why, come tomorrow at 09:00 in West Building Rooms 118 120 for the “Stabilize and Personalize Your Pixels” session or just visit our project page: token-verse.github.io

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 ⚡️. 🧵

Everyone uses CFG with w = 7.5… but why?? 🤔 For non-trivial prompts, choosing w is hard: too low → weak alignment, too high → artifacts. We show w shouldn’t be fixed — it should adapt! ✨ We present a tiny but smart MLP to adjust w over time → Better images/alignment 🚀 1/n