3d scene generation 1diffusion models 1image editing 1interactive editing 1latent noise inversion 1progressive reasoning 1prompt inversion 1reinforcement learning 1text-to-image generation 1vision-language models 1
From the 2 of 2 linked papers with an AI index.
2 papers
cs.CV2026
Dual Inversion for Text-to-Image Diffusion Models: From Both Prompt and Noise Perspectives
Xiaolong Liu, Junjian Li, Yuan Xiao +4
The paper introduces Dualin, a two‑stage method that simultaneously recovers a human‑readable text prompt and the latent noise of a target image to improve prompt inversion for tex…
cs.CV2026
ThinkBLOX: 3D Indoor Scene Generation with Progressive Reasoning
Yuan Xiao, Can Wang, Xiangyu Kong +1
ThinkBLOX is a vision‑language model framework that generates and refines 3D indoor scenes step‑by‑step, using chain‑of‑thought reasoning and a tiered reinforcement learning scheme…