9 papers · 1 filter
CADENA: Stepwise CAD Reverse Engineering
Soslan Kabisov, Gennadiy Savrasov, Maksim Elistratov +9
Computer-Aided Design (CAD) underpins modern engineering, yet converting existing shapes into editable models still demands substantial expert effort. Most AI systems emit the enti…
SHIFT: Steering Hidden Intermediates in Flow Transformers
Nina Konovalova, Andrey Kuznetsov, Aibek Alanov
Diffusion models have become leading approaches for high-fidelity image generation. Recent DiT-based diffusion models, in particular, achieve strong prompt adherence while producin…
T-LoRA: Single Image Diffusion Model Customization Without Overfitting
Vera Soboleva, Aibek Alanov, Andrey Kuznetsov +1
While diffusion model fine-tuning offers a powerful approach for customizing pre-trained models to generate specific objects, it frequently suffers from overfitting when training s…
Heeding the Inner Voice: Aligning ControlNet Training via Intermediate Features Feedback
Nina Konovalova, Maxim Nikolaev, Andrey Kuznetsov +1
Despite significant progress in text-to-image diffusion models, achieving precise spatial control over generated outputs remains challenging. ControlNet addresses this by introduci…
Inverse-and-Edit: Effective and Fast Image Editing by Cycle Consistency Models
Ilia Beletskii, Andrey Kuznetsov, Aibek Alanov
Recent advances in image editing with diffusion models have achieved impressive results, offering fine-grained control over the generation process. However, these methods are compu…
ImageReFL: Balancing Quality and Diversity in Human-Aligned Diffusion Models
Dmitrii Sorokin, Maksim Nakhodnov, Andrey Kuznetsov +1
Recent advances in diffusion models have led to impressive image generation capabilities, but aligning these models with human preferences remains challenging. Reward-based fine-tu…