SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.08481 · ICLR · 2025

Enhancing End-to-End Autonomous Driving with Latent World Model

Tieniu Tan, Lue Fan, Zhaoxiang Zhang, Yuqi Wang, Yuntao Chen, Jiawei He, Yingyan Li

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2406.08481.json · badge: /api/ran/2406.08481.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
BraveGroup/LAW canonical (classifier label)
classifier basis: census
2 ran · 2 no recorded run
FunctionStatusWhere it lives
draw_lidar_pts Ran
ran; our contract draft was wrong, not the code
BraveGroup/LAW/projects/mmdet3d_plugin/LAW/utils/visualization.py
code served (permissive licence) · get_code("b9fb8403671571ec")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 3, dtype family int, shape (480, 640, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np
import cv2

torch.manual_seed(0)

# Create a dummy image (3-channel BGR image)
img = np.zeros((480, 640, 3), dtype=np.uint8)

# Create ref_pts_cam: tensor of camera points
# Shape: (num_cam, num_points, 2) where each point has (x, y) coordinates
# Using batch size 2 (num_cam=2), num_points=4
ref_pts_cam = torch.tensor([
    [[100, 150], [200, 250], [300, 350], [400, 450]],
    [[120, 160], [220, 260], [320, 360], [420, 460]]
], dtype=torch.float32)

# Create pts_mask: boolean mask indicating which points to draw
# Shape: (num_cam, num_points)
# For first camera: draw points 0 and 2
# For second camera: draw points 1 and 3
pts_mask = torch.tensor([
    [True, False, True, False],
    [False, True, False, True]
], dtype=torch.bool)

ARGS = {
    "ref_pts_cam": ref_pts_cam,
    "pts_mask": pts_mask,
    "img": img,
    "length": 6,
    "color": (255, 255, 0)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (480, 640, 3) — shape (480, 640, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_locations Ran
ran; our contract draft was wrong, not the code
BraveGroup/LAW/projects/mmdet3d_plugin/LAW/dense_heads/utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from SEU-zxj/CoIRL-AD, is pointer only (licence: NONE) · get_code("49a5dc5b545790ba")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from SEU-zxj/CoIRL-AD, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

prj_ego_traj_to_2d Not yet run
unverified (harvested, no recorded run)
BraveGroup/LAW/projects/mmdet3d_plugin/LAW/utils/visualization.py
code served (permissive licence) · get_code("fee9f1584419c696")
How it ran

no invocation recorded.

prj_pts_to_img Not yet run
unverified (harvested, no recorded run)
BraveGroup/LAW/projects/mmdet3d_plugin/LAW/utils/visualization.py
code served (permissive licence) · get_code("814f003ae4ffef5e")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
get_locations 1 other paper
1 later
2510.12560 (2025-10)
CoIRL-AD: Collaborative-Competitive Imitation-Reinforcement Learning in Latent World Models for Autonomous Driving

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In autonomous driving, end-to-end planners directly utilize raw sensor data, enabling them to extract richer scene features and reduce information loss compared to traditional planners. This raises a crucial research question: how can we develop better scene feature representations to fully leverage sensor data in end-to-end driving? Self-supervised learning methods show great success in learning rich feature representations in NLP and computer vision. Inspired by this, we propose a novel self-supervised learning approach using the LAtent World model (LAW) for end-to-end driving. LAW predicts future scene features based on current features and ego trajectories. This self-supervised task can be seamlessly integrated into perception-free and perception-based frameworks, improving scene feature learning and optimizing trajectory prediction. LAW achieves state-of-the-art performance across multiple benchmarks, including real-world open-loop benchmark nuScenes, NAVSIM, and simulator-based closed-loop benchmark CARLA. The code is released at https://github.com/BraveGroup/LAW.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2406.08481")
get_code_for_paper("2406.08481")
have("2406.08481")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2406.08481.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2406.08481.svg)](https://syntology.ai/paper/2406.08481)

Connect an agent — have() is free.