Papers › Multi-Modal Fusion Transformer for End-to-End Autonomous Driving
Multi-Modal Fusion Transformer for End-to-End Autonomous Driving
Aditya Prakash, Kashyap Chitta, Andreas Geiger
How should representations from complementary sensors be integrated for autonomous driving? Geometry-based sensor fusion has shown great promise for perception tasks such as object detection and motion forecasting. However, for the actual driving task, the global context of the 3D scene is key, e.g. a change in traffic light state can affect the behavior of a vehicle geometrically distant from that traffic light. Geometry alone may therefore be insufficient for effectively fusing representations in end-to-end driving models. In this work, we demonstrate that imitation learning policies based on existing sensor fusion methods under-perform in the presence of a high density of dynamic agents and complex scenarios, which require global contextual reasoning, such as handling traffic oncoming from multiple directions at uncontrolled intersections. Therefore, we propose TransFuser, a novel Multi-Modal Fusion Transformer, to integrate image and LiDAR representations using attention. We experimentally validate the efficacy of our approach in urban settings involving complex scenarios using the CARLA urban driving simulator. Our approach achieves state-of-the-art driving performance while reducing collisions by 76% compared to geometry-based fusion.
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):
get_harvested_code_for_paper(arxiv_id="2104.09224")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2104.09224", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2104.09224")
Code
Syntology 15 code samples harvested from 2 repositories linked to this paper: 9 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.
By repository: official repository: 6 samples from 1 repository, 3 ran (2 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 9 samples from 1 repository, 6 ran (6 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
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: 9 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 1 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 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.
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 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”. For 3 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket team_code_transfuser/transfuser.py ran · metamorphic tier: deterministic MIT (permissive) ·
d93ea624e09cfe3d · report
fixture: returned Block · level recorded 2026-09-22 7a6582011815aa73 · report
fixture: returned GPT · level recorded 2026-09-22 1529467107cafc96 · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22 d2d93b6e784851f4 · report
8d4dbe093612822d · report
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket team_code/benchmarks/transfuser/model.py ran · metamorphic tier: deterministic MIT (permissive) ·
5075118d0c207c37 · report
fixture: returned Block · level recorded 2026-09-22 594894f4b9eb35a1 · report
fixture: returned GPT · level recorded 2026-09-22 152cd035838391cd · report
fixture: returned LidarEncoder · level recorded 2026-09-22 bd73b9145f2b9944 · report
fixture: returned PIDController · level recorded 2026-09-22 6141dbd1107c57fd · report
fixture: returned SelfAttention · level recorded 2026-09-22 af36a314f4f4a4be · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22 277c052f581f3276 · report
1a4dc7d1e43090ab · report
3d3c28ac7ec98753 · 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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.
2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).
2 sibling assemblies for TransFuser (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.
harvested Assembly for TransFuser (graph method: TransFuser). 9 bricks; individually on a fixture: 6 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.
one of 2 siblings
- TransFuser entry · level 0 · unverified ·
3d3c28ac7ec98753 - Encoder model · level 0 · unverified ·
277c052f581f3276 - PIDController helper · level 1 · ran ·
bd73b9145f2b9944 - GPT model · level 1 · ran ·
594894f4b9eb35a1 - ImageCNN model · level 0 · unverified ·
1a4dc7d1e43090ab - LidarEncoder model · level 1 · ran ·
152cd035838391cd - normalize_imagenet helper · level 1 · ran · violated contract ·
af36a314f4f4a4be - Block model · level 1 · ran ·
5075118d0c207c37 - SelfAttention model · level 1 · ran ·
6141dbd1107c57fd
harvested Assembly for TransFuser (graph method: TransFuser). 7 bricks; individually on a fixture: 4 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; 1 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.
one of 2 siblings
- TransfuserBackbone entry · level 0 · unverified ·
8d4dbe093612822d - GPT model · level 1 · ran ·
7a6582011815aa73 - ImageCNN model · level 0 · unverified ·
e1a45fd31eaf668d - LidarEncoder model · level 0 · unverified ·
d2d93b6e784851f4 - normalize_imagenet helper · level 1 · ran · our draft was wrong ·
1529467107cafc96 - Block model · level 1 · ran ·
d93ea624e09cfe3d - SelfAttention model · level 1 · ran ·
6141dbd1107c57fd
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="2104.09224") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Autonomous Driving | CARLA Leaderboard | Transfuser | Driving Score | 16.93 | #16 of 18 | Archive leaderboard | report |
| Autonomous Driving | CARLA Leaderboard | Transfuser | Infraction penalty | 0.42 | #16 of 18 | Archive leaderboard | report |
| Autonomous Driving | CARLA Leaderboard | Transfuser | Route Completion | 51.82 | #16 of 18 | Archive leaderboard | report |
| Autonomous Driving | Town05 Long | Geometric Fusion | RC | 69.17 | #1 of 2 | Archive leaderboard | report |
| Autonomous Driving | Town05 Long | TransFuser | DS | 33.15 | #2 of 2 | Archive leaderboard | report |
| Autonomous Driving | Town05 Long | TransFuser | RC | 56.36 | #2 of 2 | Archive leaderboard | report |
| Autonomous Driving | Town05 Short | Geometric Fusion | RC | 86.91 | #1 of 2 | Archive leaderboard | report |
| Autonomous Driving | Town05 Short | TransFuser | DS | 54.52 | #2 of 2 | Archive leaderboard | report |
| Autonomous Driving | Town05 Short | TransFuser | RC | 78.41 | #2 of 2 | Archive leaderboard | report |
| Semantic Segmentation | KITTI-360 | TransFuser (RGB-LiDAR) | mIoU | 56.57 | #10 of 17 | 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.
Methods
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