Papers › Latent Action Pretraining from Videos

Latent Action Pretraining from Videos

15 Oct 2024arXiv:2410.11758archive 2025-07-28

Seonghyeon Ye, Joel Jang, Byeongguk Jeon, Sejune Joo, Jianwei Yang, Baolin Peng, Ajay Mandlekar, Reuben Tan, Yu-Wei Chao, Bill Yuchen Lin, Lars Liden, Kimin Lee, Jianfeng Gao, Luke Zettlemoyer, Dieter Fox, Minjoon Seo

We introduce Latent Action Pretraining for general Action models (LAPA), an unsupervised method for pretraining Vision-Language-Action (VLA) models without ground-truth robot action labels. Existing Vision-Language-Action models require action labels typically collected by human teleoperators during pretraining, which significantly limits possible data sources and scale. In this work, we propose a method to learn from internet-scale videos that do not have robot action labels. We first train an action quantization model leveraging VQ-VAE-based objective to learn discrete latent actions between image frames, then pretrain a latent VLA model to predict these latent actions from observations and task descriptions, and finally finetune the VLA on small-scale robot manipulation data to map from latent to robot actions. Experimental results demonstrate that our method significantly outperforms existing techniques that train robot manipulation policies from large-scale videos. Furthermore, it outperforms the state-of-the-art VLA model trained with robotic action labels on real-world manipulation tasks that require language conditioning, generalization to unseen objects, and semantic generalization to unseen instructions. Training only on human manipulation videos also shows positive transfer, opening up the potential for leveraging web-scale data for robotics foundation model.

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 36 code samples harvested from 3 repositories linked to this paper: 30 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 4 honoured, 5 violated, 9 with no contract checked; 12 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 9 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: community (archive-listed): 14 samples from 1 repository, 12 ran (10 with no instrument failure; 2 where Syntology's instrument failed); found in paper text by Syntology: 22 samples from 2 repositories, 18 ran (8 with no instrument failure; 10 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 30 samples that ran have no recorded date.

LatentActionPretraining/LAPA mentioned on GitHubjaxMITSyntology: 14 samples, 12 ran (2 instrument-failed) · 2 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

36 samples harvested: 30 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 4 honoured, 5 violated, 9 with no contract checked; 12 where Syntology's instrument failed) · 6 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.

4ran · honoured contract
5ran · violated contract
9ran · our draft was wrong
3ran; the contract check could not run
9ran
6unverified

Licence: 4 of the 36 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 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.

LatentActionPretraining/LAPA community (archive-listed) 14 samples, 12 ran (2 instrument-failed) · 2 unverified
identity in 174 papers
census: 11 implementations from 39 papers, 3 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
laq/laq_model/data.py ran · honoured contract MIT (permissive) · 7f1040f5e3991d5e · report fixture: signature t:Tensor/2/float, args:tuple/1/Tensor, kwargs:dict/0/? · returned Tensor · level recorded, date not recorded
accum_log laq/laq_model/laq_trainer.py ran MIT (permissive) · 5d19651094278e5c · report fixture: signature log:dict/0/?, new_logs:dict/0/? · returned dict · level recorded 2026-09-24
default in 430 papers laq/laq_model/attention.py ran · violated contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 60fff7c3c400d7ff · report fixture: signature val:int/0/int, d:int/0/int · returned int · level recorded, date not recorded
encode_images in 6 papers latent_pretraining/data.py ran MIT (permissive) · 9056e6d6fdefa088 · report fixture: signature vqgan:MockVQGAN/0/?, images:ArrayImpl/4/float · returned ndarray · level recorded 2026-09-24
exists in 528 papers
census: 5 implementations from 103 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int64
laq/laq_model/attention.py ran · violated contract MIT (permissive) here; the stored copy is pointer only · aa5486a3650902d8 · report fixture: signature val:Tensor/1/int · returned bool · level recorded, date not recorded
get_optimizer in 228 papers laq/laq_model/optimizer.py ran MIT (permissive) · 93576b1f69752368 · report fixture: signature params:list/1/Tensor, lr:float/0/float, wd:float/0/float, betas:tuple/1/float, eps:float/0/float, filter_by_requires_grad:bool/0/bool, group_wd_params:bool/0/bool · returned AdamW · level recorded 2026-09-24
get_preprocessor latent_pretraining/data.py ran MIT (permissive) · bf465416561b7be4 · report fixture: signature image_aug:bool/0/bool · returned Compose · level recorded 2026-09-24
leaky_relu in 24 papers laq/laq_model/attention.py ran · our draft was wrong MIT (permissive) · f11bef5e87ce3904 · report fixture: signature p:float/0/float · returned LeakyReLU · level recorded 2026-09-22
load_image in 273 papers laq/inference_sthv2.py ran MIT (permissive) · 0ca8f8ec94f51579 · report fixture: returned tuple · level recorded 2026-09-24
pair in 101 papers laq/laq_model/latent_action_quantization.py ran · honoured contract fingerprinted MIT (permissive) · 6d5ab71931a90677 · report fixture: signature val:int/0/int · returned tuple · level recorded 2026-09-22
pair in 101 papers laq/laq_model/data.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 9270ed2833cf3467 · report fixture: signature val:int/0/int · returned tuple · level recorded 2026-09-24
separate_weight_decayable_params in 9 papers laq/laq_model/optimizer.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · fdc11aefc97f3abb · report fixture: signature params:list/1/Tensor · returned tuple · level recorded 2026-09-24
get_model in 368 papers laq/laq_model/t5.py unverified MIT (permissive) · feff9391629f5643 · report
get_tokenizer in 156 papers laq/laq_model/t5.py unverified MIT (permissive) · cbdf413e88112af9 · report
google-research/language-table found in paper text by Syntology 12 samples, 8 ran (4 instrument-failed) · 4 unverified
add_debug_info_to_image language_table/environments/language_table.py ran Apache-2.0 (permissive) · dbc74cddc2c0fb0a · report fixture: signature image:ndarray/3/int, info_dict:dict/0/?, pos:tuple/1/int, font:int/0/int, font_scale:int/0/int, font_thickness:int/0/int, text_color:tuple/1/int · returned ndarray · level recorded 2026-09-24
crop_test_image language_table/eval/wrappers.py ran Apache-2.0 (permissive) · 155c970270f7efea · report fixture: signature images:EagerTensor/4/float, random_crop_factor:float/0/float · returned EagerTensor · level recorded 2026-09-24
flattened_traversal language_table/train/bc.py ran · our draft was wrong Apache-2.0 (permissive) · 0eb50fb69cca4ed3 · report fixture: signature fn:callable/0/? · returned function · level recorded 2026-09-24
get_hyper in 8 papers language_table/train/configs/language_table_resnet_sim_local.py ran · our draft was wrong Apache-2.0 (permissive) · 9c310e911f805732 · report fixture: signature h:MockHyperparameter/0/? · returned list · level recorded 2026-09-24
normalize_image_resnet language_table/train/networks/lava.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 0b15aed1f08da820 · report fixture: signature images:ArrayImpl/4/float · returned ArrayImpl · level recorded 2026-09-24
positional_encoding2d language_table/train/networks/lava.py ran Apache-2.0 (permissive) · c212071abd4e5321 · report fixture: signature d_model:int/0/int, height:int/0/int, width:int/0/int, flatten:bool/0/bool · returned ndarray · level recorded 2026-09-24
resize_images in 9 papers language_table/eval/wrappers.py ran fingerprinted Apache-2.0 (permissive) · 98869bb596d5d642 · report fixture: signature images:EagerTensor/4/float, target_height:int/0/int, target_width:int/0/int · returned EagerTensor · level recorded 2026-09-24
sinusoidal_init language_table/train/networks/lava.py ran · our draft was wrong Apache-2.0 (permissive) · 02dbbb5108872c5d · report fixture: signature max_len:int/0/int, max_timescale:float/0/float · returned function · level recorded 2026-09-24
get_all_block_pairs language_table/environments/blocks.py unverified Apache-2.0 (permissive) · cbf0a809513fd118 · report
get_all_block_subsets language_table/environments/blocks.py unverified Apache-2.0 (permissive) · c30c34bf7965a040 · report
get_block_set language_table/environments/blocks.py unverified Apache-2.0 (permissive) · 86c900797b149647 · report
tokenize_text in 8 papers language_table/common/clip_tokenizer.py unverified Apache-2.0 (permissive) · f38cfe2cf5433ba8 · report
simpler-env/SimplerEnv found in paper text by Syntology 10 samples, 10 ran (6 instrument-failed) · 0 unverified
construct_unordered_trial_results simpler_env/utils/metrics.py ran · violated contract MIT (permissive) · 2291e98cc51d78b6 · report fixture: signature n_trials_per_ckpt:int/0/int, success:list/1/float · returned ndarray · level recorded 2026-09-24
dataset2path simpler_env/utils/debug/google_robot_test_dataset_inference_rollout_gt_traj_in_sim.py ran · our draft was wrong fingerprinted MIT (permissive) · b473600d9d00e657 · report fixture: signature dataset_name:str/0/str · returned str · level recorded 2026-09-24
default in 430 papers simpler_env/policies/octo/octo_server_model.py ran · our draft was wrong fingerprinted MIT (permissive) · 3abdec7a01649789 · report fixture: signature obj:ndarray/2/float · returned dict · level recorded 2026-09-24
is_path simpler_env/utils/io.py ran · violated contract MIT (permissive) · 1d86046b8135d67a · report fixture: signature path:str/0/str · returned bool · level recorded 2026-09-24
load_image_arrays simpler_env/utils/io.py ran; the contract check could not run (RAISES) MIT (permissive) · 2b562af5f9efa42f · report fixture: signature image_paths:ndarray/3/int · returned tuple · level recorded 2026-09-24
load_image_pils simpler_env/utils/io.py ran · our draft was wrong MIT (permissive) · 1a0db059d2e3b91b · report fixture: signature image_paths:str/0/str · returned tuple · level recorded 2026-09-24
mean_maximum_rank_violation simpler_env/utils/metrics.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 441fe6ea8aeea865 · report fixture: signature perf_sim:list/1/float, perf_real:list/1/float · returned float64 · level recorded 2026-09-24
object_hook simpler_env/policies/octo/octo_server_model.py ran · honoured contract MIT (permissive) · 8cd74b85e5838b36 · report fixture: signature dct:dict/0/? · returned ndarray · level recorded 2026-09-24
parse_range_tuple simpler_env/evaluation/argparse.py ran · our draft was wrong MIT (permissive) · 05c86bc7ce4ad9dc · report fixture: signature t:tuple/1/float · returned ndarray · level recorded 2026-09-24
pearson_correlation in 15 papers simpler_env/utils/metrics.py ran · violated contract MIT (permissive) · 9dbd294d9713950c · report fixture: signature perf_sim:list/1/float, perf_real:list/1/float · returned int · level recorded 2026-09-24

Tasks

QuantizationRobot ManipulationVision-Language-Action

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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