SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.06845 · 2024

DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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; 0 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/2403.06845.json · badge: /api/ran/2403.06845.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
f1yfisher/drivedreamer2 canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
load_config Ran
ran; our contract draft was wrong, not the code
f1yfisher/drivedreamer2/dreamer-train/dreamer_train/configs/config.py
code served (permissive licence) · get_code("5c18c9c202b2d699")
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) and returned Config. The image it ran in was not recorded. If your copy returns the same type 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 tempfile
import os
import json
import yaml
import pickle
from pathlib import Path

# Create temporary directory for test files
temp_dir = tempfile.mkdtemp()

# Test case 1: Create a config.json file
config_dict = {
    "model": "test_model",
    "learning_rate": 0.001,
    "batch_size": 32,
    "nested": {
        "param1": "value1",
        "param2": 42
    }
}

config_json_path = os.path.join(temp_dir, "config.json")
with open(config_json_path, 'w') as f:
    json.dump(config_dict, f)

# Test case 2: Create a directory with config.json
config_dir = os.path.join(temp_dir, "model_config")
os.makedirs(config_dir, exist_ok=True)
config_in_dir_path = os.path.join(config_dir, "config.json")
with open(config_in_dir_path, 'w') as f:
    json.dump(config_dict, f)

# Test case 3: Create a YAML config file
config_yaml_path = os.path.join(temp_dir, "config.yaml")
with open(config_yaml_path, 'w') as f:
    yaml.dump(config_dict, f)

# Test case 4: Create a pickle config file
config_pkl_path = os.path.join(temp_dir, "config.pkl")
with open(config_pkl_path, 'wb') as f:
    pickle.dump(config_dict, f)

# Test case 5: Pass a Config object directly
from yaml import Loader, Dumper

# Import the Config class (simulating it's available)
class Config(dict):
    def __init__(self, d=None, **kwargs):
        if d is None:
            d = {}
        if kwargs:
            d.update(**kwargs)
        for k, v in d.items():
            setattr(self, k, v)
        super().__init__(d)

config_obj = Config(config_dict)

# Test case 6: Pass a dict directly
config_dict_input = {
    "param1": "value1",
    "param2": 123,
    "nested": {"key": "value"}
}

ARGS = {
    "config_or_path": config_json_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
yaml — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Config — a Config output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Config output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
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
load_file Ran
ran; our contract draft was wrong, not the code
f1yfisher/drivedreamer2/dreamer-train/dreamer_train/configs/config.py
code served (permissive licence) · get_code("2be7756925318d0b")
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) and returned dict. The image it ran in was not recorded. If your copy returns the same type 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 json
import pickle
import yaml
import tempfile
import os

# Create temporary files for testing
temp_dir = tempfile.mkdtemp()

# Create a pickle file
pickle_file = os.path.join(temp_dir, "test.pkl")
with open(pickle_file, 'wb') as f:
    pickle.dump({"key": "value"}, f)

# Create a JSON file
json_file = os.path.join(temp_dir, "test.json")
with open(json_file, 'w') as f:
    json.dump({"key": "value"}, f)

# Create a YAML file
yaml_file = os.path.join(temp_dir, "test.yaml")
with open(yaml_file, 'w') as f:
    yaml.dump({"key": "value"}, f)

# Define ARGS - test with pickle file as the primary case
ARGS = {
    "file_path": pickle_file,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
yaml — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 2 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.

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

World models have demonstrated superiority in autonomous driving, particularly in the generation of multi-view driving videos. However, significant challenges still exist in generating customized driving videos. In this paper, we propose DriveDreamer-2, which builds upon the framework of DriveDreamer and incorporates a Large Language Model (LLM) to generate user-defined driving videos. Specifically, an LLM interface is initially incorporated to convert a user's query into agent trajectories. Subsequently, a HDMap, adhering to traffic regulations, is generated based on the trajectories. Ultimately, we propose the Unified Multi-View Model to enhance temporal and spatial coherence in the generated driving videos. DriveDreamer-2 is the first world model to generate customized driving videos, it can generate uncommon driving videos (e.g., vehicles abruptly cut in) in a user-friendly manner. Besides, experimental results demonstrate that the generated videos enhance the training of driving perception methods (e.g., 3D detection and tracking). Furthermore, video generation quality of DriveDreamer-2 surpasses other state-of-the-art methods, showcasing FID and FVD scores of 11.2 and 55.7, representing relative improvements of 30% and 50%.

For agents

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

get_harvested_code_for_paper("2403.06845")
get_code_for_paper("2403.06845")
have("2403.06845")

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

curl https://syntology.ai/api/ran/2403.06845.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.06845.svg)](https://syntology.ai/paper/2403.06845)

Connect an agent — have() is free.