Papers › LLaRA: Supercharging Robot Learning Data for Vision-Language Policy

LLaRA: Supercharging Robot Learning Data for Vision-Language Policy

28 Jun 2024arXiv:2406.20095archive 2025-07-28

Xiang Li, Cristina Mata, Jongwoo Park, Kumara Kahatapitiya, Yoo Sung Jang, Jinghuan Shang, Kanchana Ranasinghe, Ryan Burgert, Mu Cai, Yong Jae Lee, Michael S. Ryoo

Vision Language Models (VLMs) have recently been leveraged to generate robotic actions, forming Vision-Language-Action (VLA) models. However, directly adapting a pretrained VLM for robotic control remains challenging, particularly when constrained by a limited number of robot demonstrations. In this work, we introduce LLaRA: Large Language and Robotics Assistant, a framework that formulates robot action policy as visuo-textual conversations and enables an efficient transfer of a pretrained VLM into a powerful VLA, motivated by the success of visual instruction tuning in Computer Vision. First, we present an automated pipeline to generate conversation-style instruction tuning data for robots from existing behavior cloning datasets, aligning robotic actions with image pixel coordinates. Further, we enhance this dataset in a self-supervised manner by defining six auxiliary tasks, without requiring any additional action annotations. We show that a VLM finetuned with a limited amount of such datasets can produce meaningful action decisions for robotic control. Through experiments across multiple simulated and real-world tasks, we demonstrate that LLaRA achieves state-of-the-art performance while preserving the generalization capabilities of large language models. The code, datasets, and pretrained models are available at https://github.com/LostXine/LLaRA.

PaperPDFCodeCode Syntology ranMethod as code

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 15 code samples harvested from 1 repository linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 13 ran (8 with no instrument failure; 5 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. 2 of the 13 samples that ran have no recorded date.

lostxine/llara officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 15 samples, 13 ran (5 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

15 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 2 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 · our draft was wrong
4ran
2unverified

Licence: 0 of the 15 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 lostxine/llara. “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.

lostxine/llara official repository 15 samples, 13 ran (5 instrument-failed) · 2 unverified
action_to_text eval/eval-rt2.py ran Apache-2.0 (permissive) · ca12919c16b4a4f5 · report fixture: signature action:dict/0/?, tokenizer:SimpleTokenizer/0/? · returned str · level recorded 2026-09-24
all_gather in 119 papers maskrcnn/utils.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 91dc40b44121e385 · report fixture: signature data:Tensor/2/float · returned list · level recorded 2026-09-24
collate_fn in 500 papers train-llava/llava/eval/model_vqa_loader.py ran · our draft was wrong Apache-2.0 (permissive) · 20e4f665698a3d18 · report fixture: signature batch:list/1/tuple · returned tuple · level recorded 2026-09-22
collate_fn in 500 papers maskrcnn/utils.py ran · our draft was wrong Apache-2.0 (permissive) · 0ec4ff97dc3a732e · report fixture: signature batch:list/1/tuple · returned tuple · level recorded 2026-09-24
get_bounding_box in 8 papers eval/vima_utils.py ran · honoured contract Apache-2.0 (permissive) · b77412266f910afa · report fixture: signature mask:ndarray/2/bool · returned tuple · level recorded 2026-09-24
get_chunk in 197 papers train-llava/llava/eval/model_vqa.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 42a46570620cd9fa · report fixture: signature lst:list/1/int, n:int/0/int, k:int/0/int · returned list · level recorded, date not recorded
load_image in 273 papers train-llava/predict.py ran · honoured contract Apache-2.0 (permissive) · 9b3c1cb391672ccb · report fixture: signature image_file:str/0/str · returned Image · level recorded 2026-09-22
pix2pos_front eval/vima_utils.py ran Apache-2.0 (permissive) · c072147381d37e39 · report fixture: signature px:int/0/int, py:int/0/int · returned tuple · level recorded 2026-09-24
pos2pix_front eval/vima_utils.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 67c19efa51776cee · report fixture: signature i:int/0/int, j:int/0/int · returned tuple · level recorded 2026-09-24
quantize_float_to_text eval/eval-rt2.py ran Apache-2.0 (permissive) · 7b583a6159d6539d · report fixture: signature num:ndarray/1/float, tokenizer:MockTokenizer/0/?, token_pool_start:int/0/int, token_num:int/0/int · returned str · level recorded 2026-09-24
reduce_dict in 73 papers maskrcnn/utils.py ran · our draft was wrong Apache-2.0 (permissive) · d4ff7353113eadb2 · report fixture: signature input_dict:dict/0/?, average:bool/0/bool · returned dict · level recorded 2026-09-24
split_list in 223 papers train-llava/llava/eval/model_vqa.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 076c252c52cbb161 · report fixture: signature lst:list/1/int, n:int/0/int · returned list · level recorded, date not recorded
text_to_float eval/eval-rt2.py ran Apache-2.0 (permissive) · 2c1424966e072851 · report fixture: signature s:str/0/str, tokenizer:MockTokenizer/0/?, token_pool_start:int/0/int, token_num:int/0/int · returned list · level recorded 2026-09-24
LlavaLlamaForCausalLM in 15 papers train-llava/llava/model/language_model/llava_llama.py unverified Apache-2.0 (permissive) · e8b1d3f3b543afbc · report
LlavaMetaForCausalLM in 16 papers train-llava/llava/model/language_model/llava_llama.py unverified Apache-2.0 (permissive) · 6106e117d2c9317b · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for LLaRA (graph method: LLaRA). 13 bricks; individually on a fixture: 7 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

  1. LlavaLlamaForCausalLM entry · level 0 · unverified · e8b1d3f3b543afbc
  2. LlavaConfig helper · level 1 · ran · f01242335a1498b3
  3. LlavaLlamaModel model · level 0 · unverified · 9707b7b56a48db85
  4. LlavaMetaForCausalLM helper · level 0 · unverified · 6106e117d2c9317b
  5. LlavaMetaModel helper · level 0 · unverified · 0bfdaed6a43a5263
  6. get_anyres_image_grid_shape helper · level 1 · ran; the contract check could not run · 2ff0d742a84cb8e2
  7. unpad_image helper · level 1 · ran; the contract check could not run · 55c32993da87759b
  8. build_vision_projector helper · level 1 · ran · our draft was wrong · ef4db0da176c674c
  9. build_vision_tower helper · level 0 · unverified · 3ee345b55cc88a11
  10. select_best_resolution helper · level 1 · ran; the contract check could not run · 3999ff487573f32c
  11. IdentityMap helper · level 1 · ran · 9f0f5d62445adabe
  12. CLIPVisionTower helper · level 1 · ran · ee3792b1ae45cbb6
  13. CLIPVisionTowerS2 helper · level 0 · unverified · 5d1c9ab7042cee8d

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2406.20095") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Vision-Language-ActionWorld Knowledge

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