Papers › ShapeLLM: Universal 3D Object Understanding for Embodied Interaction

ShapeLLM: Universal 3D Object Understanding for Embodied Interaction

27 Feb 2024arXiv:2402.17766archive 2025-07-28

Zekun Qi, Runpei Dong, Shaochen Zhang, Haoran Geng, Chunrui Han, Zheng Ge, Li Yi, Kaisheng Ma

This paper presents ShapeLLM, the first 3D Multimodal Large Language Model (LLM) designed for embodied interaction, exploring a universal 3D object understanding with 3D point clouds and languages. ShapeLLM is built upon an improved 3D encoder by extending ReCon to ReCon++ that benefits from multi-view image distillation for enhanced geometry understanding. By utilizing ReCon++ as the 3D point cloud input encoder for LLMs, ShapeLLM is trained on constructed instruction-following data and tested on our newly human-curated benchmark, 3D MM-Vet. ReCon++ and ShapeLLM achieve state-of-the-art performance in 3D geometry understanding and language-unified 3D interaction tasks, such as embodied visual grounding. Project page: https://qizekun.github.io/shapellm/

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2402.17766")

Code

Syntology Ran 9 of 17 code samples harvested from 3 repositories linked to this paper; 8 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · violated contract; 4 ran · our draft was wrong; 3 ran with no contract checked.

By repository: official repository: 2 samples from 1 repository, 2 ran; community (archive-listed): 15 samples from 2 repositories, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

qizekun/ShapeLLM officialmentioned on GitHubpytorchApache-2.0 report
qizekun/ReCon pytorchMIT report
runpeidong/act pytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

17 samples harvested; 9 ran; 1 honoured the contract we drafted; 8 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
1ran · violated contract
4ran · our draft was wrong
3ran
8unverified

Licence: 0 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

get_iou qizekun/ShapeLLM/llava/eval/eval_gapartnet.py official repository ran fingerprinted Apache-2.0 (permissive) · 6a27d2ea085ab083 · report
pc_normalize qizekun/ShapeLLM/ReConV2/datasets/ModelNetDataset.py official repository ran fingerprinted Apache-2.0 (permissive) · f6148d58020c40ae · report
basic_clean qizekun/ReCon/clip/simple_tokenizer.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · 98f385d847636a3e · report
build_2d_sincos_posemb runpeidong/act/utils/transformer_layers.py community (archive-listed) ran MIT (permissive) · 10442b2d555aff2d · report
get_pairs qizekun/ReCon/clip/simple_tokenizer.py community (archive-listed) ran · our draft was wrong MIT (permissive) · d919ae32e5e4e616 · report
pair runpeidong/act/utils/transformer_layers.py community (archive-listed) ran · violated contract fingerprinted MIT (permissive) · 6ba8cee9f5daea41 · report
pc_normalize qizekun/ReCon/datasets/ModelNetDataset.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · 4783fbece52f500e · report
square_distance qizekun/ReCon/segmentation/pointnet_util.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · 74c3fe06cea2f553 · report
whitespace_clean qizekun/ReCon/clip/simple_tokenizer.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · 9542161e9640b858 · report
build_model qizekun/ReCon/clip/model.py community (archive-listed) unverified MIT (permissive) · d996b25c2413180a · report
concat_all_gather runpeidong/act/models/act.py community (archive-listed) unverified MIT (permissive) · 73cecca9f3575f09 · report
farthest_point_sample qizekun/ReCon/datasets/ModelNetDataset.py community (archive-listed) unverified MIT (permissive) · f80066a00e7156a2 · report
knn_point runpeidong/act/models/dvae.py community (archive-listed) unverified MIT (permissive) · 55397203c1d5dac1 · report
load qizekun/ReCon/clip/clip.py community (archive-listed) unverified MIT (permissive) · f6f30e41636ae569 · report
square_distance runpeidong/act/models/dvae.py community (archive-listed) unverified MIT (permissive) · 6ddec81b1d23c787 · report
timeit qizekun/ReCon/segmentation/pointnet_util.py community (archive-listed) unverified MIT (permissive) · b1227ddb721e2999 · report
trunc_normal_ runpeidong/act/utils/transformer_layers.py community (archive-listed) unverified MIT (permissive) · 5436174f8c0e64e0 · report

Tasks

3D Object Captioning3D Point Cloud Classification3D Point Cloud Linear Classification3D Question Answering (3D-QA)3D geometryFew-Shot 3D Point Cloud ClassificationGenerative 3D Object ClassificationInstruction FollowingLanguage ModelingLanguage ModellingLarge Language ModelMultimodal Large Language ModelObjectVisual GroundingZero-Shot Transfer 3D Point Cloud ClassificationZero-shot 3D classification

1 archive task tag without a task page not shown.

Datasets

Introduced by this paper, per the archive.

3D MM-Vet

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Object Captioning Objaverse ShapeLLM-13B Sentence-BERT 48.52 #2 of 6 Archive leaderboard report
3D Object Captioning Objaverse ShapeLLM-13B GPT-4 48.94 #2 of 6 Archive leaderboard report
3D Object Captioning Objaverse ShapeLLM-13B SimCSE 49.98 #2 of 6 Archive leaderboard report
3D Object Captioning Objaverse ShapeLLM-7B Sentence-BERT 48.20 #4 of 6 Archive leaderboard report
3D Object Captioning Objaverse ShapeLLM-7B GPT-4 46.92 #4 of 6 Archive leaderboard report
3D Object Captioning Objaverse ShapeLLM-7B SimCSE 49.23 #4 of 6 Archive leaderboard report
3D Point Cloud Classification ModelNet40 ReCon++ Overall Accuracy 95.0 #3 of 111 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN ReCon++ OBJ-BG (OA) 98.80 #5 of 77 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN ReCon++ OBJ-ONLY (OA) 97.59 #5 of 77 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN ReCon++ Overall Accuracy 95.25 #5 of 77 Archive leaderboard report
3D Point Cloud Linear Classification ModelNet40 ReCon++ Overall Accuracy 93.6 #2 of 20 Archive leaderboard report
3D Question Answering (3D-QA) 3D MM-Vet ShapeLLM-13B Overall Accuracy 53.1 #1 of 5 Archive leaderboard report
3D Question Answering (3D-QA) 3D MM-Vet ShapeLLM-7B Overall Accuracy 47.4 #2 of 5 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (10-shot) ReCon++ Overall Accuracy 94.5 #2 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (10-shot) ReCon++ Standard Deviation 4.1 #2 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (20-shot) ReCon++ Overall Accuracy 96.5 #1 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (20-shot) ReCon++ Standard Deviation 3.0 #1 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (10-shot) ReCon++ Overall Accuracy 98.0 #2 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (10-shot) ReCon++ Standard Deviation 2.3 #2 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (20-shot) ReCon++ Overall Accuracy 99.5 #1 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (20-shot) ReCon++ Standard Deviation 0.8 #1 of 30 Archive leaderboard report
Generative 3D Object Classification ModelNet40 ShapeLLM-7B ModelNet40 (Average) 53.08 #2 of 6 Archive leaderboard report
Generative 3D Object Classification ModelNet40 ShapeLLM-13B ModelNet40 (Average) 52.96 #3 of 6 Archive leaderboard report
Generative 3D Object Classification Objaverse ShapeLLM-7B Objaverse (Average) 54.50 #2 of 7 Archive leaderboard report
Generative 3D Object Classification Objaverse ShapeLLM-13B Objaverse (Average) 54.00 #4 of 7 Archive leaderboard report
Zero-Shot Transfer 3D Point Cloud Classification ModelNet40 ReCon++ Accuracy (%) 87.3 #3 of 16 Archive leaderboard report
Zero-Shot Transfer 3D Point Cloud Classification ScanObjectNN ReCon++ OBJ_ONLY Accuracy(%) 65.4 #1 of 10 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections