ll220/qwen3d

[NeurIPS 2026 Reviewed (5/4/4 - A/WA/WA)] 3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding

A shift-window based transformer for 3D sparse tasks

[NeurIPS 2026 Spotlight] Official code and checkpoints for OneCanvas: 3D Scene Understanding via Panoramic Reprojection.

[ECCV 2026 Long Oral] Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding

[ICML 2026] ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning

Awesome-LLM-3D: a curated list of Multi-modal Large Language Model in 3D world Resources

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.

[NeurIPS 2026] Official implementation of paper "VLM³: Vision Language Models Are Native 3D Learners".