04:00
2026-05-29
arxiv.org
generative-ai
GAP3D: Generative Alignment of VLM Latents to Patch-Level Embeddings for 3D Generation
Researchers have developed GAP3D, a diffusion-based method that aligns vision-language model latents directly to patch-level image embeddings, enabling frozen generative models to use VLMs as prompt e…