{"task":"3D Object Captioning","dataset":"Objaverse","metric_names":["GPT-4"," Sentence-BERT","SimCSE","Precision","Correctness","Hallucination"],"rows":[{"id":146498,"task":"3D Object Captioning","parent_task":null,"dataset":"Objaverse","model_name":"MiniGPT-3D","metrics":{" Sentence-BERT":"49.54","Correctness":"3.50","GPT-4":"57.06","Hallucination":"0.71","Precision":"83.14","SimCSE":"51.39"},"paper_url":"https://arxiv.org/abs/2405.01413v1","paper_title":"MiniGPT-3D: Efficiently Aligning 3D Point Clouds with Large Language Models using 2D Priors","paper_date":"2024-05-02","code_links":[{"title":"tangyuan96/minigpt-3d","url":"https://github.com/tangyuan96/minigpt-3d"}],"metrics_order":"[\"GPT-4\", \" Sentence-BERT\", \"SimCSE\", \"Precision\", \"Correctness\", \"Hallucination\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146499,"task":"3D Object Captioning","parent_task":null,"dataset":"Objaverse","model_name":"ShapeLLM-13B","metrics":{" Sentence-BERT":"48.52","GPT-4":"48.94","SimCSE":"49.98"},"paper_url":"https://arxiv.org/abs/2402.17766v3","paper_title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction","paper_date":"2024-02-27","code_links":[{"title":"qizekun/ShapeLLM","url":"https://github.com/qizekun/ShapeLLM"},{"title":"qizekun/ReCon","url":"https://github.com/qizekun/ReCon"},{"title":"runpeidong/act","url":"https://github.com/runpeidong/act"}],"metrics_order":"[\"GPT-4\", \" Sentence-BERT\", \"SimCSE\", \"Precision\", \"Correctness\", \"Hallucination\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146500,"task":"3D Object Captioning","parent_task":null,"dataset":"Objaverse","model_name":"PointLLM-13B V1.2","metrics":{" Sentence-BERT":"47.91","Correctness":"3.10","GPT-4":"48.15","Hallucination":"0.84","Precision":"78.75","SimCSE":"49.12"},"paper_url":"https://arxiv.org/abs/2308.16911v3","paper_title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","paper_date":"2023-08-31","code_links":[{"title":"openrobotlab/pointllm","url":"https://github.com/openrobotlab/pointllm"},{"title":"Pointcept/GPT4Point","url":"https://github.com/Pointcept/GPT4Point"},{"title":"qizekun/ShapeLLM","url":"https://github.com/qizekun/ShapeLLM"}],"metrics_order":"[\"GPT-4\", \" Sentence-BERT\", \"SimCSE\", \"Precision\", \"Correctness\", \"Hallucination\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146501,"task":"3D Object Captioning","parent_task":null,"dataset":"Objaverse","model_name":"ShapeLLM-7B","metrics":{" Sentence-BERT":"48.20","GPT-4":"46.92","SimCSE":"49.23"},"paper_url":"https://arxiv.org/abs/2402.17766v3","paper_title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction","paper_date":"2024-02-27","code_links":[{"title":"qizekun/ShapeLLM","url":"https://github.com/qizekun/ShapeLLM"},{"title":"qizekun/ReCon","url":"https://github.com/qizekun/ReCon"},{"title":"runpeidong/act","url":"https://github.com/runpeidong/act"}],"metrics_order":"[\"GPT-4\", \" Sentence-BERT\", \"SimCSE\", \"Precision\", \"Correctness\", \"Hallucination\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146502,"task":"3D Object Captioning","parent_task":null,"dataset":"Objaverse","model_name":"PointLLM-7B V1.2","metrics":{" Sentence-BERT":"47.47","Correctness":"3.04","GPT-4":"44.85","Hallucination":"0.66","Precision":"82.14","SimCSE":"48.55"},"paper_url":"https://arxiv.org/abs/2308.16911v3","paper_title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","paper_date":"2023-08-31","code_links":[{"title":"openrobotlab/pointllm","url":"https://github.com/openrobotlab/pointllm"},{"title":"Pointcept/GPT4Point","url":"https://github.com/Pointcept/GPT4Point"},{"title":"qizekun/ShapeLLM","url":"https://github.com/qizekun/ShapeLLM"}],"metrics_order":"[\"GPT-4\", \" Sentence-BERT\", \"SimCSE\", \"Precision\", \"Correctness\", \"Hallucination\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146503,"task":"3D Object Captioning","parent_task":null,"dataset":"Objaverse","model_name":"3D-LLM","metrics":{" Sentence-BERT":"44.48","Correctness":"1.77","GPT-4":"33.42","Hallucination":"1.16","Precision":"60.39","SimCSE":"43.68"},"paper_url":"https://arxiv.org/abs/2307.12981v1","paper_title":"3D-LLM: Injecting the 3D World into Large Language Models","paper_date":"2023-07-24","code_links":[{"title":"umass-foundation-model/3d-llm","url":"https://github.com/umass-foundation-model/3d-llm"},{"title":"openrobotlab/pointllm","url":"https://github.com/openrobotlab/pointllm"},{"title":"Pointcept/GPT4Point","url":"https://github.com/Pointcept/GPT4Point"},{"title":"qizekun/ShapeLLM","url":"https://github.com/qizekun/ShapeLLM"},{"title":"Yui010206/CREMA","url":"https://github.com/Yui010206/CREMA"}],"metrics_order":"[\"GPT-4\", \" Sentence-BERT\", \"SimCSE\", \"Precision\", \"Correctness\", \"Hallucination\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}