Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/ShapeLLM-13B

ShapeLLM-13B

Reported on 18 benchmarks across 9 tasks · 1 paper · 4 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision13 results

3D Object CaptioningonObjaverse
Sentence-BERT· 2024-02-27
48.52
best: 49.54 (MiniGPT-3D)
SOTA
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Object CaptioningonObjaverse
GPT-4· 2024-02-27
48.94
best: 57.06 (MiniGPT-3D)
SOTA
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Object CaptioningonObjaverse
SimCSE· 2024-02-27
49.98
best: 51.39 (MiniGPT-3D)
SOTA
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
Shape Representation Of 3D Point CloudsonObjaverse
Objaverse (Average)· 2024-02-27
54
best: 60.25 (MiniGPT-3D)
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
Shape Representation Of 3D Point CloudsonModelNet40
ModelNet40 (Average)· 2024-02-27
52.96
best: 60.86 (MiniGPT-3D)
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Object ClassificationonObjaverse
Objaverse (Average)· 2024-02-27
54
best: 60.25 (MiniGPT-3D)
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Object ClassificationonModelNet40
ModelNet40 (Average)· 2024-02-27
52.96
best: 60.86 (MiniGPT-3D)
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud ClassificationonObjaverse
Objaverse (Average)· 2024-02-27
54
best: 60.25 (MiniGPT-3D)
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud ClassificationonModelNet40
ModelNet40 (Average)· 2024-02-27
52.96
best: 60.86 (MiniGPT-3D)
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud ReconstructiononObjaverse
Objaverse (Average)· 2024-02-27
54
best: 60.25 (MiniGPT-3D)
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud ReconstructiononModelNet40
ModelNet40 (Average)· 2024-02-27
52.96
best: 60.86 (MiniGPT-3D)
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
Generative 3D Object ClassificationonObjaverse
Objaverse (Average)· 2024-02-27
54
best: 60.25 (MiniGPT-3D)
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
Generative 3D Object ClassificationonModelNet40
ModelNet40 (Average)· 2024-02-27
52.96
best: 60.86 (MiniGPT-3D)
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766

Methodology2 results

3DonObjaverse
Objaverse (Average)· 2024-02-27
54
best: 60.25 (MiniGPT-3D)
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3DonModelNet40
ModelNet40 (Average)· 2024-02-27
52.96
best: 60.86 (MiniGPT-3D)
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766

Medical2 results

3D ClassificationonObjaverse
Objaverse (Average)· 2024-02-27
54
best: 60.25 (MiniGPT-3D)
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D ClassificationonModelNet40
ModelNet40 (Average)· 2024-02-27
52.96
best: 60.86 (MiniGPT-3D)
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766

Natural Language Processing1 result

Visual Question Answering (VQA)on3D MM-Vet
Overall Accuracy· 2024-02-27
53.1
SOTA
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766