Papers › Instruction-Following Agents with Multimodal Transformer

Instruction-Following Agents with Multimodal Transformer

24 Oct 2022arXiv:2210.13431archive 2025-07-28

Hao liu, Lisa Lee, Kimin Lee, Pieter Abbeel

Humans are excellent at understanding language and vision to accomplish a wide range of tasks. In contrast, creating general instruction-following embodied agents remains a difficult challenge. Prior work that uses pure language-only models lack visual grounding, making it difficult to connect language instructions with visual observations. On the other hand, methods that use pre-trained multimodal models typically come with divided language and visual representations, requiring designing specialized network architecture to fuse them together. We propose a simple yet effective model for robots to solve instruction-following tasks in vision-based environments. Our \ours method consists of a multimodal transformer that encodes visual observations and language instructions, and a transformer-based policy that predicts actions based on encoded representations. The multimodal transformer is pre-trained on millions of image-text pairs and natural language text, thereby producing generic cross-modal representations of observations and instructions. The transformer-based policy keeps track of the full history of observations and actions, and predicts actions autoregressively. Despite its simplicity, we show that this unified transformer model outperforms all state-of-the-art pre-trained or trained-from-scratch methods in both single-task and multi-task settings. Our model also shows better model scalability and generalization ability than prior work.

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 20 code samples harvested from 1 repository linked to this paper: 15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 20 samples from 1 repository, 15 ran (15 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.

lhao499/instructrl officialmentioned in papermentioned on GitHubjaxMITSyntology: 20 samples, 15 ran (0 instrument-failed) · 5 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

20 samples harvested: 15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 5 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.

15ran
5unverified

Licence: 2 of the 20 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 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 lhao499/instructrl. “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.

lhao499/instructrl official repository 20 samples, 15 ran (0 instrument-failed) · 5 unverified
build_env_fn instructrl/instructrl_main.py ran MIT (permissive) · 600b55b260ebe0ff · report fixture: signature game_name:str/0/str · returned function · level recorded 2026-09-25
create_test_step instructrl/local_run.py ran MIT (permissive) · 1189ccb694f97474 · report fixture: signature model:MockModel/0/?, env_fn:callable/0/?, episode_length:int/0/int, instruct:dict/0/?, window_size:int/0/int, num_episodes:int/0/int, num_actions:int/0/int · returned function · level recorded 2026-09-25
create_train_step instructrl/instructrl_main.py ran MIT (permissive) · 06f8960d0fb5a580 · report fixture: signature model:callable/0/?, learning_rate:callable/0/?, weight_decay:float/0/float · returned function · level recorded 2026-09-25
cross_entropy in 92 papers
census: 6 implementations from 8 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
instructrl/model.py ran MIT (permissive) · ef0abd7fbdc81c5e · report fixture: signature logits:ArrayImpl/2/float, labels:ArrayImpl/1/int, num_classes:int/0/int · returned tuple · level recorded 2026-09-24
discrete_euler_to_quaternion instructrl/data.py ran MIT (permissive) · 6f7c29d589a38d3b · report fixture: signature discrete_euler:ndarray/2/int, resolution:float/0/float · returned ndarray · level recorded 2026-09-25
extend_and_repeat in 10 papers instructrl/utils.py ran MIT (permissive) here; the stored copy is pointer only · d2f199c948f2a9ed · report fixture: signature tensor:ArrayImpl/2/float, axis:int/0/int, repeat:int/0/int · returned ArrayImpl · level recorded 2026-09-24
get_metrics in 46 papers instructrl/utils.py ran MIT (permissive) · f051af6f08e6125a · report fixture: signature metrics:dict/0/?, unreplicate:bool/0/bool · returned dict · level recorded 2026-09-24
get_pos_embed in 5 papers instructrl/model.py ran MIT (permissive) · a94b14df1af9126d · report fixture: signature embed_dim:int/0/int, length:int/0/int · returned ArrayImpl · level recorded 2026-09-24
hash_file in 7 papers instructrl/models/openai/download.py ran MIT (permissive) · 15ba5cffc310ab9f · report fixture: signature path:str/0/str · returned str · level recorded 2026-09-25
mask_intersection instructrl/models/m3ae/model.py ran fingerprinted MIT (permissive) · cd63725ed150c8be · report fixture: signature mask1:ArrayImpl/2/float, mask2:ArrayImpl/2/float · returned ArrayImpl · level recorded 2026-09-24
mask_not instructrl/models/m3ae/model.py ran fingerprinted MIT (permissive) · e0f860b8706ea27b · report fixture: signature mask:Tensor/2/float · returned Tensor · level recorded 2026-09-24
mask_union instructrl/models/m3ae/model.py ran fingerprinted MIT (permissive) · d049b3e2054cb151 · report fixture: signature mask1:ArrayImpl/2/float, mask2:ArrayImpl/2/float · returned ArrayImpl · level recorded 2026-09-25
mse_loss in 73 papers
census: 8 implementations from 12 papers, 6 distinct outputs across 4 buckets, one shared input per bucket
instructrl/model.py ran fingerprinted MIT (permissive) here; the stored copy is pointer only · cc35af8b18b7dc58 · report fixture: signature val:ArrayImpl/2/float, target:ArrayImpl/2/float · returned ArrayImpl · level recorded 2026-09-24
prefix_metrics instructrl/models/m3ae/utils.py ran MIT (permissive) · d97e89c7f1953b3a · report fixture: signature metrics:dict/0/?, prefix:str/0/str · returned dict · level recorded 2026-09-25
wrap_function_with_rng instructrl/utils.py ran MIT (permissive) · 1e6123c693775a38 · report fixture: signature rng:ArrayImpl/1/int · returned function · level recorded 2026-09-24
batch_rollout instructrl/envs/rollout.py unverified MIT (permissive) · c16d1755d384c81b · report
build_env_fn instructrl/local_run.py unverified MIT (permissive) · dc4f5bae4c75e9c4 · report
download in 53 papers instructrl/models/openai/download.py unverified MIT (permissive) · a18a67bfbd7246bb · report
get_cont_action instructrl/data.py unverified MIT (permissive) · 913edd29987265fa · report
sync_state_fn instructrl/instructrl_main.py unverified MIT (permissive) · 278d0834e4c3f3b4 · report

Tasks

Instruction FollowingVisual Grounding

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