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 View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 17 code samples harvested from 3 repositories linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 5 honoured, 1 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 2 samples from 1 repository, 2 ran (2 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 15 samples from 2 repositories, 12 ran (4 with no instrument failure; 8 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 14 samples that ran has no recorded date.

qizekun/ShapeLLM officialmentioned on GitHubpytorchApache-2.0Syntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
qizekun/ReCon pytorchMITSyntology: 9 samples, 7 ran (5 instrument-failed) · 2 unverified report
runpeidong/act pytorchMITSyntology: 6 samples, 5 ran (3 instrument-failed) · 1 unverified 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: 14 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 5 honoured, 1 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

5ran · honoured contract
1ran · violated contract
5ran · our draft was wrong
3ran; the contract check could not run
3unverified

Licence: 8 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. For 8 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. 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; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

qizekun/ShapeLLM official repository 2 samples, 2 ran (0 instrument-failed) · 0 unverified
get_iou in 34 papers llava/eval/eval_gapartnet.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 6a27d2ea085ab083 · report fixture: signature bbox1:ndarray/2/float, bbox2:ndarray/2/float · returned float32 · level recorded 2026-09-24
pc_normalize in 81 papers
census: 2 implementations from 6 papers, 1 distinct output on one shared input
ReConV2/datasets/ModelNetDataset.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · f6148d58020c40ae · report fixture: signature pc:ndarray/2/float · returned ndarray · level recorded 2026-09-24
qizekun/ReCon community (archive-listed) 9 samples, 7 ran (5 instrument-failed) · 2 unverified
basic_clean in 217 papers clip/simple_tokenizer.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 98f385d847636a3e · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-22
farthest_point_sample in 64 papers datasets/ModelNetDataset.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · f80066a00e7156a2 · report fixture: signature point:ndarray/2/float, npoint:int/0/int · returned ndarray · level recorded 2026-09-25
get_pairs in 260 papers clip/simple_tokenizer.py ran · our draft was wrong MIT (permissive) · d919ae32e5e4e616 · report fixture: signature word:tuple/1/str · returned set · level recorded 2026-09-22
pc_normalize in 81 papers
census: 2 implementations from 6 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
datasets/ModelNetDataset.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 4783fbece52f500e · report fixture: signature pc:ndarray/2/float · returned ndarray · level recorded 2026-09-22
square_distance in 89 papers
census: 11 implementations from 18 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 3, kind float, dtype float32 · arg 2: rank 3, kind float, dtype float32
segmentation/pointnet_util.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 74c3fe06cea2f553 · report fixture: signature src:Tensor/3/float, dst:Tensor/3/float · returned Tensor · level recorded 2026-09-22
timeit in 59 papers segmentation/pointnet_util.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · b1227ddb721e2999 · report fixture: signature tag:str/0/str, t:float/0/float · returned float · level recorded 2026-09-26
whitespace_clean in 230 papers clip/simple_tokenizer.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 9542161e9640b858 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-22
build_model in 469 papers clip/model.py unverified MIT (permissive) · d996b25c2413180a · report
load in 392 papers clip/clip.py unverified MIT (permissive) here; the stored copy is pointer only · f6f30e41636ae569 · report
runpeidong/act community (archive-listed) 6 samples, 5 ran (3 instrument-failed) · 1 unverified
build_2d_sincos_posemb utils/transformer_layers.py ran · honoured contract MIT (permissive) · 10442b2d555aff2d · report fixture: signature h:int/0/int, w:int/0/int, embed_dim:int/0/int, temperature:float/0/float · returned Tensor · level recorded 2026-09-24
knn_point in 23 papers
census: 4 implementations from 5 papers, 2 distinct outputs on one shared input
models/dvae.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 55397203c1d5dac1 · report fixture: signature nsample:int/0/int, xyz:Tensor/3/float, new_xyz:Tensor/3/float · returned Tensor · level recorded 2026-09-25
pair in 101 papers utils/transformer_layers.py ran · violated contract fingerprinted MIT (permissive) · 6ba8cee9f5daea41 · report fixture: signature t:int/0/int · returned tuple · level recorded, date not recorded
square_distance in 89 papers
census: 11 implementations from 18 papers, 4 distinct outputs across 2 buckets, one shared input per bucket
models/dvae.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 6ddec81b1d23c787 · report fixture: signature src:Tensor/3/float, dst:Tensor/3/float · returned Tensor · level recorded 2026-09-25
trunc_normal_ in 154 papers
census: 37 implementations from 54 papers, 4 distinct outputs on one shared input
utils/transformer_layers.py ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only · 5436174f8c0e64e0 · report fixture: signature tensor:Tensor/2/float, mean:float/0/float, std:float/0/float, a:float/0/float, b:float/0/float · returned Tensor · level recorded 2026-09-26

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