Inbar Gat retweeted
Even today, with powerful image editing models, making fine-grained structural changes to 3D shapes remains a major challenge.
In our new #SIGGRAPH2026 paper, Prox-E, we use primitive-based abstraction to leverage VLMs for precise, reasoning-based 3D editing!
👇
Inbar Gat retweeted
1/7
When rewards conflict, what should RL post-training of diffusion models optimize?
In visual generation, objectives are often in tension:
Prompt adherence can conflict with source preservation.
Photorealism can conflict with stylization.
In our new paper, ParetoSlider, we introduce a multi-objective RL framework that trains a single diffusion model for continuous control over competing reward objectives 🧵
ShapeUP beats both trained and training-free baselines on unedited regions preservation and edit fidelity, across all edit types. More importantly, the formulation scales with data and compute.
Work with @DanaCohenBar , @guy1levy , @EladRichardson , @DanielCohenOr1 🙏
Project page: inbar-2344.github.io/ShapeUp… Paper: arxiv.org/abs/2602.05676
Inbar Gat retweeted
🔔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-…