SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.00896 · 2024

TrailBlazer: Trajectory Control for Diffusion-Based 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, 1 violated it and 0 have no contract verdict; 1 failure 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/2401.00896.json · badge: /api/ran/2401.00896.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
hohonu-vicml/trailblazer canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
gaussian_2d Ran
ran, violated the contract we drafted
hohonu-vicml/trailblazer/TrailBlazer/CrossAttn/BaseProc.py
code served (permissive licence) · get_code("650163523cd1441e")
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 2, dtype family float, shape (4, 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 math

torch.manual_seed(0)

# Create small 2D coordinate tensors
# Using distinct sizes: 4x3 grid
x = torch.linspace(-2, 2, 4).unsqueeze(1).expand(4, 3)
y = torch.linspace(-2, 2, 3).unsqueeze(0).expand(4, 3)

# Define parameters for the gaussian function
mx = torch.tensor(0.5)
my = torch.tensor(-0.5)
sx = torch.tensor(1.2)
sy = torch.tensor(0.8)

ARGS = {
    'x': x,
    'y': y,
    'mx': mx,
    'my': my,
    'sx': sx,
    'sy': sy
}
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 2, dtype family float, shape (4, 3) — shape (4, 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
reshape_fortran Ran
ran; our contract draft was wrong, not the code
hohonu-vicml/trailblazer/TrailBlazer/CrossAttn/BaseProc.py
code served (permissive licence) · get_code("f61edee88c785710")
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 2, dtype family int, shape (4, 6) 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)

# The function takes a tensor x and a target shape
# It performs fortran-style reshaping by:
# 1. Permuting x dimensions in reverse order
# 2. Reshaping to reversed shape
# 3. Permuting the result back

# Create a small tensor with distinct dimensions
x = torch.arange(24).reshape(2, 3, 4)  # Shape: (2, 3, 4)

# Define a target shape for fortran reshape
# Original shape (2, 3, 4) can be reshaped to (4, 6) in fortran order
shape = (4, 6)

ARGS = {
    "x": x,
    "shape": shape,
}
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 2, dtype family int, shape (4, 6) — shape (4, 6) 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 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, 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 1 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
gaussian_2d 1 other paper
1 later
2406.16863 (2024-06)
FreeTraj: Tuning-Free Trajectory Control in Video Diffusion Models

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

Within recent approaches to text-to-video (T2V) generation, achieving controllability in the synthesized video is often a challenge. Typically, this issue is addressed by providing low-level per-frame guidance in the form of edge maps, depth maps, or an existing video to be altered. However, the process of obtaining such guidance can be labor-intensive. This paper focuses on enhancing controllability in video synthesis by employing straightforward bounding boxes to guide the subject in various ways, all without the need for neural network training, finetuning, optimization at inference time, or the use of pre-existing videos. Our algorithm, TrailBlazer, is constructed upon a pre-trained (T2V) model, and easy to implement. The subject is directed by a bounding box through the proposed spatial and temporal attention map editing. Moreover, we introduce the concept of keyframing, allowing the subject trajectory and overall appearance to be guided by both a moving bounding box and corresponding prompts, without the need to provide a detailed mask. The method is efficient, with negligible additional computation relative to the underlying pre-trained model. Despite the simplicity of the bounding box guidance, the resulting motion is surprisingly natural, with emergent effects including perspective and movement toward the virtual camera as the box size increases.

For agents

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

get_harvested_code_for_paper("2401.00896")
get_code_for_paper("2401.00896")
have("2401.00896")

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

curl https://syntology.ai/api/ran/2401.00896.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.00896.svg)](https://syntology.ai/paper/2401.00896)

Connect an agent — have() is free.