Reasoning paths with reference objects elicit quantitative spatial reasoning in large vision-lang...

[Free GPT-4]
[PDF] arxiv.org

Sparkle: Mastering basic spatial capabilities in vision language models elicits generalization to composite spatial reasoning

Y Tang, A Qu, Z Wang, D Zhuang, Z Wu, W Ma… - arxiv preprint arxiv …, 2024 - arxiv.org
Vision language models (VLMs) have demonstrated impressive performance across a wide
range of downstream tasks. However, their proficiency in spatial reasoning remains limited …
Zapisz Cytuj Cytowane przez 2 Powiązane artykuły Wszystkie wersje 2 Wersja HTML
[Free GPT-4]
[PDF] arxiv.org

LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models

Z Wang, J Lorraine, Y Wang, H Su, J Zhu… - arxiv preprint arxiv …, 2024 - arxiv.org
This work explores expanding the capabilities of large language models (LLMs) pretrained
on text to generate 3D meshes within a unified model. This offers key advantages of (1) …
Zapisz Cytuj Cytowane przez 1 Powiązane artykuły Wszystkie wersje 2 Wersja HTML