SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.09471 · 2024

MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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; 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/2403.09471.json · badge: /api/ran/2403.09471.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
kkakkkka/MambaTalk canonical (classifier label)
classifier basis: census
1 ran · 0 no recorded run
FunctionStatusWhere it lives
get_loss_func Ran
ran; our contract draft was wrong, not the code
kkakkkka/MambaTalk/optimizers/loss_factory.py
code served (permissive licence) · get_code("4f043bf1bec12652")
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 HuberLoss. 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 torch
import torch.nn as nn
import numpy as np

torch.manual_seed(0)

# Test different loss functions with appropriate arguments

# For GeodesicLoss - needs rotation matrices (batch x 3 x 3)
geodesic_args = {
    'loss_name': 'GeodesicLoss',
}

# For BCE_Loss - needs logits and targets
bce_args = {
    'loss_name': 'bce_loss',
}

# For L2Loss - needs outputs and targets
l2_args = {
    'loss_name': 'l2_loss',
}

# For HuberLoss - needs beta and reduction
huber_args = {
    'loss_name': 'huber_loss',
    'beta': 0.1,
    'reduction': 'mean',
}

# For KLDLoss - needs beta
kl_args = {
    'loss_name': 'kl_loss',
    'beta': 0.1,
}

# For REGLoss - needs beta
reg_args = {
    'loss_name': 'id_loss',
    'beta': 0.1,
}

# For weight_Loss - no additional args needed
weight_args = {
    'loss_name': 'weight_Loss',
}

# Choose one representative test case
ARGS = {
    'loss_name': 'huber_loss',
    'beta': 0.1,
    'reduction': 'mean',
}
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 HuberLoss — a HuberLoss output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a HuberLoss 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 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 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 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
get_loss_func 1 other paper
1 later
2505.13447 (2025-05)
Mean Flows for One-step Generative Modeling

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

Gesture synthesis is a vital realm of human-computer interaction, with wide-ranging applications across various fields like film, robotics, and virtual reality. Recent advancements have utilized the diffusion model and attention mechanisms to improve gesture synthesis. However, due to the high computational complexity of these techniques, generating long and diverse sequences with low latency remains a challenge. We explore the potential of state space models (SSMs) to address the challenge, implementing a two-stage modeling strategy with discrete motion priors to enhance the quality of gestures. Leveraging the foundational Mamba block, we introduce MambaTalk, enhancing gesture diversity and rhythm through multimodal integration. Extensive experiments demonstrate that our method matches or exceeds the performance of state-of-the-art models. Our project is publicly available at https://kkakkkka.github.io/MambaTalk

For agents

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

get_harvested_code_for_paper("2403.09471")
get_code_for_paper("2403.09471")
have("2403.09471")

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

curl https://syntology.ai/api/ran/2403.09471.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.09471.svg)](https://syntology.ai/paper/2403.09471)

Connect an agent — have() is free.