Papers › TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation

TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation

19 Sep 2024arXiv:2409.12514archive 2025-07-28

Junjie Wen, Yichen Zhu, Jinming Li, Minjie Zhu, Kun Wu, Zhiyuan Xu, Ning Liu, Ran Cheng, Chaomin Shen, Yaxin Peng, Feifei Feng, Jian Tang

Vision-Language-Action (VLA) models have shown remarkable potential in visuomotor control and instruction comprehension through end-to-end learning processes. However, current VLA models face significant challenges: they are slow during inference and require extensive pre-training on large amounts of robotic data, making real-world deployment difficult. In this paper, we introduce a new family of compact vision-language-action models, called TinyVLA, which offers two key advantages over existing VLA models: (1) faster inference speeds, and (2) improved data efficiency, eliminating the need for pre-training stage. Our framework incorporates two essential components to build TinyVLA: (1) initializing the policy backbone with robust, high-speed multimodal models, and (2) integrating a diffusion policy decoder during fine-tuning to enable precise robot actions. We conducted extensive evaluations of TinyVLA in both simulation and on real robots, demonstrating that our approach significantly outperforms the state-of-the-art VLA model, OpenVLA, in terms of speed and data efficiency, while delivering comparable or superior performance. Additionally, TinyVLA exhibits strong generalization capabilities across various dimensions, including language instructions, novel objects, unseen positions, changes in object appearance, background variations, and environmental shifts, often matching or exceeding the performance of OpenVLA. We believe that \methodname offers an interesting perspective on utilizing pre-trained multimodal models for policy learning. Our project is at https://tiny-vla.github.io.

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 13 code samples harvested from 1 repository linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 13 samples from 1 repository, 13 ran (13 with no instrument failure; 0 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 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

liyaxuanliyaxuan/TinyVLA mentioned on GitHubpytorchMITSyntology: 13 samples, 13 ran (0 instrument-failed) · 0 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

13 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

13ran

Licence: 0 of the 13 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 liyaxuanliyaxuan/TinyVLA. “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.

liyaxuanliyaxuan/TinyVLA community (archive-listed) 13 samples, 13 ran (0 instrument-failed) · 0 unverified
find_all_hdf5 data_utils/datasets.py ran fingerprinted MIT (permissive) · 31dac2af91c0a769 · report fixture: signature dataset_dir:str/0/str, skip_mirrored_data:bool/0/bool · returned list · level recorded 2026-09-25
flatten_list in 30 papers data_utils/datasets.py ran MIT (permissive) · 94398091c12cbe1c · report fixture: signature l:list/1/list · returned list · level recorded 2026-09-25
get_image in 52 papers eval_real_franka.py ran MIT (permissive) · 05b9e2bfc9908f24 · report fixture: signature ts:MockObservation/0/?, camera_names:list/1/str, rand_crop_resize:bool/0/bool · returned Tensor · level recorded 2026-09-24
get_sinusoid_encoding_table in 51 papers policy_heads/models/detr_vae.py ran fingerprinted MIT (permissive) · 35f9adf6c1ae4bbd · report fixture: signature n_position:int/0/int, d_hid:int/0/int · returned Tensor · level recorded 2026-09-25
get_torch_device in 7 papers torch_utils.py ran MIT (permissive) · 34e8df99936714a4 · report fixture: signature try_to_use_cuda:bool/0/bool · returned device · level recorded 2026-09-25
mlp in 108 papers policy_heads/models/detr_vae.py ran MIT (permissive) · 6fc99436fb828638 · report fixture: signature input_dim:int/0/int, hidden_dim:int/0/int, output_dim:int/0/int, hidden_depth:int/0/int · returned Sequential · level recorded 2026-09-25
optimizer_from_optim_params torch_utils.py ran MIT (permissive) · 67d4b0869d24a6b6 · report fixture: signature net_optim_params:dict/0/?, net:callable/0/? · returned Adam · level recorded 2026-09-25
position_encoding_1d policy_heads/models/position_encoding.py ran fingerprinted MIT (permissive) · 5e0589832288a99e · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
pre_process in 11 papers eval_real_franka.py ran MIT (permissive) · 709c3b3855421181 · report fixture: signature robot_state_value:Tensor/2/float, key:str/0/str, stats:dict/0/? · returned Tensor · level recorded 2026-09-24
recursive_dict_list_tuple_apply data_utils/rlds_to_h5py.py ran MIT (permissive) · 94fb70891b0086e7 · report fixture: signature x:dict/0/?, type_func_dict:dict/0/? · returned dict · level recorded 2026-09-24
reparameterize in 38 papers
census: 12 implementations from 17 papers, 5 distinct outputs across 4 buckets, one shared input per bucket
torch_utils.py ran fingerprinted MIT (permissive) · cf0310bb83608134 · report fixture: signature mu:Tensor/2/float, logvar:Tensor/2/float · returned Tensor · level recorded 2026-09-25
reparametrize in 22 papers
census: 6 implementations from 8 papers, 1 distinct output on one shared input
policy_heads/models/detr_vae.py ran fingerprinted MIT (permissive) · 59dd02364e4bbf60 · report fixture: signature mu:Tensor/2/float, logvar:Tensor/2/float · returned Tensor · level recorded 2026-09-24
to_numpy in 103 papers
census: 24 implementations from 29 papers, 2 distinct outputs across 2 buckets, one shared input per bucket
data_utils/rlds_to_h5py.py ran MIT (permissive) · eae96a7561f37089 · report fixture: signature x:dict/0/? · returned dict · level recorded 2026-09-24

Tasks

Vision-Language-Action

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DiffusionSPEED

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