Papers › Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding,...

Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following

1 Sep 2023arXiv:2309.00615archive 2025-07-28

Ziyu Guo, Renrui Zhang, Xiangyang Zhu, Yiwen Tang, Xianzheng Ma, Jiaming Han, Kexin Chen, Peng Gao, Xianzhi Li, Hongsheng Li, Pheng-Ann Heng

We introduce Point-Bind, a 3D multi-modality model aligning point clouds with 2D image, language, audio, and video. Guided by ImageBind, we construct a joint embedding space between 3D and multi-modalities, enabling many promising applications, e.g., any-to-3D generation, 3D embedding arithmetic, and 3D open-world understanding. On top of this, we further present Point-LLM, the first 3D large language model (LLM) following 3D multi-modal instructions. By parameter-efficient fine-tuning techniques, Point-LLM injects the semantics of Point-Bind into pre-trained LLMs, e.g., LLaMA, which requires no 3D instruction data, but exhibits superior 3D and multi-modal question-answering capacity. We hope our work may cast a light on the community for extending 3D point clouds to multi-modality applications. Code is available at https://github.com/ZiyuGuo99/Point-Bind_Point-LLM.

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="2309.00615")

Code

Syntology Ran 13 of 20 code samples harvested from 3 repositories linked to this paper; 7 have no recorded run. Of those that ran: 2 ran · honoured contract; 1 ran · violated contract; 1 ran · our draft was wrong; 3 ran · fixture could not drive it; 6 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 10 ran; community (archive-listed): 8 samples from 2 repositories, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ziyuguo99/point-bind_point-llm officialmentioned in papermentioned on GitHubpytorchMIT report
Pointcept/GPT4Point mentioned on GitHubpytorchMIT report
openrobotlab/pointllm mentioned on GitHubpytorch report
qizekun/ShapeLLM mentioned on GitHubpytorchApache-2.0 report
zrrskywalker/point-bind mentioned on GitHubpytorchMIT 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

20 samples harvested; 13 ran; 2 honoured the contract we drafted; 7 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.

2ran · honoured contract
1ran · violated contract
1ran · our draft was wrong
3ran · fixture could not drive it
6ran
7unverified

Licence: 7 of the 20 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.

adjust_learning_rate ziyuguo99/point-bind_point-llm/Point-LLM/util/lr_sched.py official repository ran · honoured contract MIT (permissive) · bd3578806ecf5ac2 · report
apply_rotary_emb ziyuguo99/point-bind_point-llm/Point-LLM/llama/llama.py official repository ran · fixture could not drive it MIT (permissive) · b47d48e431b34acd · report
cast_if_src_dtype ziyuguo99/point-bind_point-llm/Point-LLM/ImageBind/models/helpers.py official repository ran · fixture could not drive it MIT (permissive) · 751b1c8ccbe160c4 · report
format_prompt ziyuguo99/point-bind_point-llm/Point-LLM/llama/utils.py official repository ran fingerprinted MIT (permissive) · b58b8fd28d0ff117 · report
get_clip_timepoints ziyuguo99/point-bind_point-llm/Point-LLM/ImageBind/data.py official repository ran MIT (permissive) · 432c312da80537d6 · report
get_sinusoid_encoding_table ziyuguo99/point-bind_point-llm/Point-LLM/ImageBind/models/multimodal_preprocessors.py official repository ran · honoured contract fingerprinted MIT (permissive) · 35a743e50e17e66d · report
load_and_transform_vision_data ziyuguo99/point-bind_point-llm/Point-LLM/ImageBind/data.py official repository ran MIT (permissive) · e1e69d9ba9ffcb24 · report
precompute_freqs_cis ziyuguo99/point-bind_point-llm/Point-LLM/llama/llama.py official repository ran · violated contract MIT (permissive) · 14a84c2cbfebc413 · report
reshape_for_broadcast ziyuguo99/point-bind_point-llm/Point-LLM/llama/llama.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 70bf6ebaafd266c4 · report
sample_top_p ziyuguo99/point-bind_point-llm/Point-LLM/llama/utils.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 8845976729f4c4ee · report
interpolate_pos_encoding ziyuguo99/point-bind_point-llm/Point-LLM/ImageBind/models/multimodal_preprocessors.py official repository unverified MIT (permissive) · 71227efe6a7df1d2 · report
interpolate_pos_encoding_2d ziyuguo99/point-bind_point-llm/Point-LLM/ImageBind/models/multimodal_preprocessors.py official repository unverified MIT (permissive) · ddd2e52e6b0956b5 · report
get_dataloader openrobotlab/pointllm/pointllm/eval/eval_objaverse.py community (archive-listed) ran no licence file found · pointer only · 54c57c8a80bfc38f · report
get_dataloader openrobotlab/pointllm/pointllm/eval/eval_modelnet_cls.py community (archive-listed) ran no licence file found · pointer only · e06417c6e0f712f1 · report
merge_new_config openrobotlab/pointllm/pointllm/utils.py community (archive-listed) ran no licence file found · pointer only · d65f58435eedf5a5 · report
build_logger openrobotlab/pointllm/pointllm/utils.py community (archive-listed) unverified no licence file found · pointer only · 51310aa3870aaa30 · report
cfg_from_yaml_file openrobotlab/pointllm/pointllm/utils.py community (archive-listed) unverified no licence file found · pointer only · 10302c30cf1214c5 · report
get_missing_parameters_message openrobotlab/pointllm/pointllm/model/pointbert/checkpoint.py community (archive-listed) unverified no licence file found · pointer only · 79cfc5c7bcc39b7b · report
get_unexpected_parameters_message openrobotlab/pointllm/pointllm/model/pointbert/checkpoint.py community (archive-listed) unverified no licence file found · pointer only · f45b84cf72162235 · report
imagebind_huge zrrskywalker/point-bind/Point-LLM/ImageBind/models/imagebind_model.py community (archive-listed) unverified MIT (permissive) · 71c517c59227454e · report

Tasks

3D Generation3D Question Answering (3D-QA)Generative 3D Object ClassificationInstruction FollowingLanguage ModelingLanguage ModellingLarge Language ModelQuestion Answeringparameter-efficient fine-tuning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Question Answering (3D-QA) 3D MM-Vet Point-Bind & Point-LLM Overall Accuracy 23.5 #5 of 5 Archive leaderboard report
Generative 3D Object Classification ModelNet40 Point-Bind LLM ModelNet40 (Average) 45.81 #6 of 6 Archive leaderboard report
Generative 3D Object Classification Objaverse Point-Bind LLM Objaverse (Average) 5.25 #7 of 7 Archive leaderboard report
Generative 3D Object Classification Objaverse Point-Bind LLM Objaverse (C) 4.50 #7 of 7 Archive leaderboard report
Generative 3D Object Classification Objaverse Point-Bind LLM Objaverse (I) 6.00 #7 of 7 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