InkMind-AI/Dyn-3D

TempoVista is the official implementation of Dyn-3D, a benchmark and training pipeline for 3D spatial reasoning in vision-language models. The release contains frame-selection tools, SFT and Kinematic-GSPO training code, benchmark evaluation scripts, Dyn-3D annotations, and checkpoints for Qwen3-VL and InternVL3.5.

语言：Python · GitHub 星标：99 · Fork：12

在 GitHub 上查看原仓库