Generating Heterogeneous 3D Geological Microstructures from 2D Images via a Stable Diffusion-Adversarial Model
Google Research Introduces Retrieve-for-Train (R4T): An RL-Compiled Diffusion Retriever for 12× to 20× Faster Query Fan-Out
4 min1
Refinement Is Inherently Editable: Training-Free Prompt-to-Prompt Image Editing with Generative Refinement Network
Comprehensive reconstruction of collider events with hypergraph representation learning and graph-conditioned diffusion
RAPID: A Real-Time Defense Against Unauthorized Model Distillation for Text-to-Image Services
1
Dynin-Robotics: Omnimodal Unified Diffusion Vision-Language-Action Model
1
Diffusion Models and Concept Formation
Forging Tree-Ring: Reproducing and Instrumenting Black-Box Semantic Watermark Forgery
Model-Aware Schedules Improve Generation via Fiberwise Optimal Transport
DRIFT: Removing Diffusion Watermarks by Deflecting the Generative Trajectory
Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout
Foundation Models for Generalizable Semantic and Goal-Oriented Communication
Decomposition-Guided Diffusion Language Models for Inertial Confinement Fusion Prediction
TransNormal-2: Geometry-Grounded Rectified Flow with Edge-Aware Decoding for Precise Normal Estimation
1
Diffusion TV: Experiencing Diffusion Models through Tangible, Embodied Interaction
Why AI food looks like that
6 min
Srijika: OpenType-Layout-Reusing Font Restyling for Nine Indic Scripts
The Attention Triangle in Audio-Video Models
