Papers › LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based...

LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment

3 Oct 2023arXiv:2310.01852archive 2025-07-28

Bin Zhu, Bin Lin, Munan Ning, Yang Yan, Jiaxi Cui, Hongfa Wang, Yatian Pang, Wenhao Jiang, Junwu Zhang, Zongwei Li, Wancai Zhang, Zhifeng Li, Wei Liu, Li Yuan

The video-language (VL) pretraining has achieved remarkable improvement in multiple downstream tasks. However, the current VL pretraining framework is hard to extend to multiple modalities (N modalities, N>=3) beyond vision and language. We thus propose LanguageBind, taking the language as the bind across different modalities because the language modality is well-explored and contains rich semantics. Specifically, we freeze the language encoder acquired by VL pretraining, then train encoders for other modalities with contrastive learning. As a result, all modalities are mapped to a shared feature space, implementing multi-modal semantic alignment. While LanguageBind ensures that we can extend VL modalities to N modalities, we also need a high-quality dataset with alignment data pairs centered on language. We thus propose VIDAL-10M with Video, Infrared, Depth, Audio and their corresponding Language, naming as VIDAL-10M. In our VIDAL-10M, all videos are from short video platforms with complete semantics rather than truncated segments from long videos, and all the video, depth, infrared, and audio modalities are aligned to their textual descriptions. LanguageBind has achieved superior performance on a wide range of 15 benchmarks covering video, audio, depth, and infrared. Moreover, multiple experiments have provided evidence for the effectiveness of LanguageBind in achieving indirect alignment and complementarity among diverse modalities. Code address: https://github.com/PKU-YuanGroup/LanguageBind

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 14 code samples harvested from 2 repositories linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 5 samples from 1 repository, 5 ran (5 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 9 samples from 1 repository, 5 ran (4 with no instrument failure; 1 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.

No sample is linked to this paper from 3 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

pku-yuangroup/languagebind officialmentioned in papermentioned on GitHubpytorchMITSyntology: 5 samples, 5 ran (0 instrument-failed) · 0 unverified report
PKU-YuanGroup/LLMBind mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Video-LLaVA: Learning United Visual Representation by Alignment Before Projection (arXiv:2311.10122; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
PKU-YuanGroup/MoE-LLaVA mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Visual Instruction Tuning (arXiv:2304.08485; that paper's own run record: 16 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 8 where Syntology's instrument failed) · 35 unverified); nothing checks that they implement this paper's method. report
PKU-YuanGroup/Video-LLaVA mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to arXiv:2507.15504 (its page on Syntology; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
pku-yuangroup/video-bench mentioned on GitHubSyntology: not harvested report
zhihaozhang97/ru-ai mentioned on GitHubpytorchMITSyntology: 9 samples, 5 ran (1 instrument-failed) · 4 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

14 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 4 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.

3ran · honoured contract
1ran; the contract check could not run
6ran
4unverified

Licence: 3 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 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 2 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.

pku-yuangroup/languagebind official repository 5 samples, 5 ran (0 instrument-failed) · 0 unverified
get_depth_transform languagebind/depth/processing_depth.py ran MIT (permissive) · ac6a026c5d4ff47b · report fixture: signature config:MockConfig/0/? · returned Compose · level recorded 2026-09-24
int16_to_float32_torch in 5 papers languagebind/audio/processing_audio.py ran · honoured contract fingerprinted MIT (permissive) · 20a58a8c04ccda43 · report fixture: signature x:Tensor/2/int · returned Tensor · level recorded 2026-09-22
make_list_of_images languagebind/audio/processing_audio.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 852e87ab903330a7 · report fixture: signature x:Tensor/2/float · returned list · level recorded 2026-09-25
opencv_loader languagebind/depth/processing_depth.py ran MIT (permissive) · 5530423121ac4757 · report fixture: signature path:str/0/str · returned ndarray · level recorded 2026-09-24
stack_dict model/languagebind.py ran MIT (permissive) · 833effea5806a36e · report fixture: signature x:list/1/dict, device:device/0/? · returned dict · level recorded 2026-09-24
zhihaozhang97/ru-ai community (archive-listed) 9 samples, 5 ran (1 instrument-failed) · 4 unverified
cast_if_src_dtype in 6 papers imagebind/models/helpers.py ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only · 751b1c8ccbe160c4 · report fixture: signature tensor:Tensor/2/float, src_dtype:dtype/0/?, tgt_dtype:dtype/0/? · returned tuple · level recorded 2026-09-22
combine_parts download_all.py ran MIT (permissive) · 81763ce5edd977e6 · report fixture: signature base_name:str/0/str, parts:list/1/str · returned str · level recorded 2026-09-24
get_clip_timepoints in 7 papers imagebind/data.py ran MIT (permissive) · 432c312da80537d6 · report fixture: signature clip_sampler:callable/0/?, duration:float/0/float · returned list · level recorded 2026-09-24
get_sinusoid_encoding_table in 51 papers imagebind/models/multimodal_preprocessors.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 35a743e50e17e66d · report fixture: signature n_position:int/0/int, d_hid:int/0/int · returned Tensor · level recorded 2026-09-22
load_and_transform_vision_data in 9 papers imagebind/data.py ran MIT (permissive) · 3b8a9225053af887 · report fixture: signature image_paths:list/1/str, device:str/0/str · returned Tensor · level recorded 2026-09-24
get_deposition_files download_all.py unverified MIT (permissive) · 67710298891367de · report
imagebind_huge in 7 papers imagebind/models/imagebind_model.py unverified MIT (permissive) · bee2c9fa238a8b73 · report
interpolate_pos_encoding in 11 papers imagebind/models/multimodal_preprocessors.py unverified MIT (permissive) · 71227efe6a7df1d2 · report
interpolate_pos_encoding_2d in 6 papers imagebind/models/multimodal_preprocessors.py unverified MIT (permissive) · ddd2e52e6b0956b5 · report

Tasks

Audio ClassificationContrastive LearningMultimodal Deep LearningScene Classification (unified classes)Temporal Relation ExtractionText RetrievalVideo-Text RetrievalZero-Shot Action RecognitionZero-Shot Environment Sound ClassificationZero-Shot Video RetrievalZero-shot Audio ClassificationZero-shot Classification (unified classes)Zero-shot Scene Classification (unified classes)Zero-shot Text RetrievalZero-shot Text to Audio Retrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Temporal Relation Extraction Vinoground LanguageBind Group Score 1.2 #23 of 24 Archive leaderboard report
Temporal Relation Extraction Vinoground LanguageBind Text Score 10.6 #23 of 24 Archive leaderboard report
Temporal Relation Extraction Vinoground LanguageBind Video Score 5 #23 of 24 Archive leaderboard report
Zero-Shot Action Recognition Kinetics LanguageBind Top-1 Accuracy 64.1 #10 of 20 Archive leaderboard report
Zero-Shot Action Recognition Kinetics LanguageBind Top-5 Accuracy 85.7 #10 of 20 Archive leaderboard report
Zero-Shot Video Retrieval ActivityNet LanguageBind(ViT-H/14) text-to-video R@1 41.0 #6 of 12 Archive leaderboard report
Zero-Shot Video Retrieval ActivityNet LanguageBind(ViT-H/14) text-to-video R@10 80.0 #6 of 12 Archive leaderboard report
Zero-Shot Video Retrieval ActivityNet LanguageBind(ViT-H/14) text-to-video R@5 68.4 #6 of 12 Archive leaderboard report
Zero-Shot Video Retrieval ActivityNet LanguageBind(ViT-H/14) video-to-text R@1 39.1 #6 of 12 Archive leaderboard report
Zero-Shot Video Retrieval ActivityNet LanguageBind(ViT-H/14) video-to-text R@10 81.1 #6 of 12 Archive leaderboard report
Zero-Shot Video Retrieval ActivityNet LanguageBind(ViT-H/14) video-to-text R@5 69.8 #6 of 12 Archive leaderboard report
Zero-Shot Video Retrieval ActivityNet LanguageBind(ViT-L/14) text-to-video R@1 38.4 #7 of 12 Archive leaderboard report
Zero-Shot Video Retrieval ActivityNet LanguageBind(ViT-L/14) text-to-video R@10 77.9 #7 of 12 Archive leaderboard report
Zero-Shot Video Retrieval ActivityNet LanguageBind(ViT-L/14) text-to-video R@5 66.6 #7 of 12 Archive leaderboard report
Zero-Shot Video Retrieval ActivityNet LanguageBind(ViT-L/14) video-to-text R@1 35.7 #7 of 12 Archive leaderboard report
Zero-Shot Video Retrieval ActivityNet LanguageBind(ViT-L/14) video-to-text R@10 77.8 #7 of 12 Archive leaderboard report
Zero-Shot Video Retrieval ActivityNet LanguageBind(ViT-L/14) video-to-text R@5 65.8 #7 of 12 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo LanguageBind(ViT-H/14) text-to-video Median Rank 2 #9 of 26 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo LanguageBind(ViT-H/14) text-to-video R@1 39.9 #9 of 26 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo LanguageBind(ViT-H/14) text-to-video R@10 74.6 #9 of 26 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo LanguageBind(ViT-H/14) text-to-video R@5 66.1 #9 of 26 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo LanguageBind(ViT-H/14) video-to-text R@1 39.8 #9 of 26 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo LanguageBind(ViT-H/14) video-to-text R@10 76.2 #9 of 26 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo LanguageBind(ViT-H/14) video-to-text R@5 67.8 #9 of 26 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo LanguageBind(ViT-L/14) text-to-video Median Rank 2.0 #10 of 26 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo LanguageBind(ViT-L/14) text-to-video R@1 39.7 #10 of 26 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo LanguageBind(ViT-L/14) text-to-video R@10 73.8 #10 of 26 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo LanguageBind(ViT-L/14) text-to-video R@5 65.5 #10 of 26 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo LanguageBind(ViT-L/14) video-to-text R@1 38.4 #10 of 26 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo LanguageBind(ViT-L/14) video-to-text R@10 77.9 #10 of 26 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo LanguageBind(ViT-L/14) video-to-text R@5 66.6 #10 of 26 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT LanguageBind(ViT-H/14) text-to-video Median Rank 2 #9 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT LanguageBind(ViT-H/14) text-to-video R@1 44.8 #9 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT LanguageBind(ViT-H/14) text-to-video R@10 78.7 #9 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT LanguageBind(ViT-H/14) text-to-video R@5 70.0 #9 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT LanguageBind(ViT-H/14) video-to-text Median Rank 2. #9 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT LanguageBind(ViT-H/14) video-to-text R@1 40.9 #9 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT LanguageBind(ViT-H/14) video-to-text R@10 75.7 #9 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT LanguageBind(ViT-H/14) video-to-text R@5 66.4 #9 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT LanguageBind(ViT-L/14) text-to-video Median Rank 2.0 #10 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT LanguageBind(ViT-L/14) text-to-video R@1 42.8 #10 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT LanguageBind(ViT-L/14) text-to-video R@10 76.0 #10 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT LanguageBind(ViT-L/14) text-to-video R@5 67.5 #10 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT LanguageBind(ViT-L/14) video-to-text Median Rank 3.0 #10 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT LanguageBind(ViT-L/14) video-to-text R@1 38.3 #10 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT LanguageBind(ViT-L/14) video-to-text R@10 77.8 #10 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT LanguageBind(ViT-L/14) video-to-text R@5 65.8 #10 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSVD LanguageBind(ViT-L/14) text-to-video Median Rank 1.0 #4 of 14 Archive leaderboard report
Zero-Shot Video Retrieval MSVD LanguageBind(ViT-L/14) text-to-video R@1 54.1 #4 of 14 Archive leaderboard report
Zero-Shot Video Retrieval MSVD LanguageBind(ViT-L/14) text-to-video R@10 88.1 #4 of 14 Archive leaderboard report
Zero-Shot Video Retrieval MSVD LanguageBind(ViT-L/14) text-to-video R@5 81.1 #4 of 14 Archive leaderboard report
Zero-Shot Video Retrieval MSVD LanguageBind(ViT-L/14) video-to-text Median Rank 1.0 #4 of 14 Archive leaderboard report
Zero-Shot Video Retrieval MSVD LanguageBind(ViT-L/14) video-to-text R@1 69.7 #4 of 14 Archive leaderboard report
Zero-Shot Video Retrieval MSVD LanguageBind(ViT-L/14) video-to-text R@10 97.9 #4 of 14 Archive leaderboard report
Zero-Shot Video Retrieval MSVD LanguageBind(ViT-L/14) video-to-text R@5 91.8 #4 of 14 Archive leaderboard report
Zero-Shot Video Retrieval MSVD LanguageBind(ViT-H/14) text-to-video Median Rank 1 #5 of 14 Archive leaderboard report
Zero-Shot Video Retrieval MSVD LanguageBind(ViT-H/14) text-to-video R@1 53.9 #5 of 14 Archive leaderboard report
Zero-Shot Video Retrieval MSVD LanguageBind(ViT-H/14) text-to-video R@10 87.8 #5 of 14 Archive leaderboard report
Zero-Shot Video Retrieval MSVD LanguageBind(ViT-H/14) text-to-video R@5 80.4 #5 of 14 Archive leaderboard report
Zero-Shot Video Retrieval MSVD LanguageBind(ViT-H/14) video-to-text Median Rank 1 #5 of 14 Archive leaderboard report
Zero-Shot Video Retrieval MSVD LanguageBind(ViT-H/14) video-to-text R@1 72.0 #5 of 14 Archive leaderboard report
Zero-Shot Video Retrieval MSVD LanguageBind(ViT-H/14) video-to-text R@10 96.3 #5 of 14 Archive leaderboard report
Zero-Shot Video Retrieval MSVD LanguageBind(ViT-H/14) video-to-text R@5 91.4 #5 of 14 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