SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.05075 · NeurIPS · 2024

DeepInteraction++: Multi-Modality Interaction for Autonomous Driving

Philip Torr, Wei Li, Xiatian Zhu, Li Zhang, Zeyu Yang, Nan Song

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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; 3 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/2408.05075.json · badge: /api/ran/2408.05075.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
fudan-zvg/DeepInteraction canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
FunctionStatusWhere it lives
inverse_sigmoid Ran
ran; our contract draft was wrong, not the code
fudan-zvg/DeepInteraction/projects/mmdet3d_plugin/models/backbones/swin_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from zhongjiaru/CoopTrack, is pointer only (licence: NONE) · get_code("f3855be53d36327d")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from zhongjiaru/CoopTrack, 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.

nchw_to_nlc Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
fudan-zvg/DeepInteraction/projects/mmdet3d_plugin/models/backbones/swin_utils.py
code served (permissive licence) · get_code("0e33d9e64b10aeb7")
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 Tensor, ndim 3, dtype family float, shape (2, 15, 4) 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

torch.manual_seed(0)

# Create a small NCHW tensor
# N=2 (batch), C=4 (channels), H=3 (height), W=5 (width)
x = torch.randn(2, 4, 3, 5)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (2, 15, 4) — shape (2, 15, 4) 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
nlc_to_nchw Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
fudan-zvg/DeepInteraction/projects/mmdet3d_plugin/models/backbones/swin_utils.py
code served (permissive licence) · get_code("260dc29e84292d6f")
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 Tensor, ndim 4, dtype family float, shape (2, 4, 3, 4) 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

torch.manual_seed(0)

# Create a tensor of shape [N, L, C]
# N=2 (batch size), L=12 (sequence length), C=4 (channels)
# We need L = H * W, so let's use H=3, W=4, giving L=12
B = 2
H = 3
W = 4
L = H * W
C = 4

x = torch.randn(B, L, C)
hw_shape = [H, W]

ARGS = {
    'x': x,
    'hw_shape': hw_shape
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 4, 3, 4) — shape (2, 4, 3, 4) 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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 1 later) and 0 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
inverse_sigmoid 51 other papers
45 dated earlier, 5 later, 1 same year, order not determinable · 23 only as an assembly brick
2005.12872 (2020-05)
End-to-End Object Detection with Transformers
2010.04159 (2020-10)
Deformable DETR: Deformable Transformers for End-to-End Object Detection
2103.11161 (2021-03)
MonteFloor: Extending MCTS for Reconstructing Accurate Large-Scale Floor Plans
and 48 more not named here
nchw_to_nlc 2 other papers
2 dated earlier
2206.15398 (2022-06)
PolarFormer: Multi-camera 3D Object Detection with Polar Transformer
2303.09757 (2023-03)
Video Dehazing via a Multi-Range Temporal Alignment Network with Physical Prior
nlc_to_nchw 1 other paper
1 dated earlier
2206.15398 (2022-06)
PolarFormer: Multi-camera 3D Object Detection with Polar Transformer

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

Existing top-performance autonomous driving systems typically rely on the multi-modal fusion strategy for reliable scene understanding. This design is however fundamentally restricted due to overlooking the modality-specific strengths and finally hampering the model performance. To address this limitation, in this work, we introduce a novel modality interaction strategy that allows individual per-modality representations to be learned and maintained throughout, enabling their unique characteristics to be exploited during the whole perception pipeline. To demonstrate the effectiveness of the proposed strategy, we design DeepInteraction++, a multi-modal interaction framework characterized by a multi-modal representational interaction encoder and a multi-modal predictive interaction decoder. Specifically, the encoder is implemented as a dual-stream Transformer with specialized attention operation for information exchange and integration between separate modality-specific representations. Our multi-modal representational learning incorporates both object-centric, precise sampling-based feature alignment and global dense information spreading, essential for the more challenging planning task. The decoder is designed to iteratively refine the predictions by alternately aggregating information from separate representations in a unified modalityagnostic manner, realizing multi-modal predictive interaction. Extensive experiments demonstrate the superior performance of the proposed framework on both 3D object detection and end-to-end autonomous driving tasks. Our code is available at https://github.com/fudan-zvg/DeepInteraction.

For agents

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

get_harvested_code_for_paper("2408.05075")
get_code_for_paper("2408.05075")
have("2408.05075")

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

curl https://syntology.ai/api/ran/2408.05075.json

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

[![Syntology run record](https://syntology.ai/api/ran/2408.05075.svg)](https://syntology.ai/paper/2408.05075)

Connect an agent — have() is free.