SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.08439 · NeurIPS · 2024

Input-to-State Stable Coupled Oscillator Networks for Closed-form Model-based Control in Latent Space

Maximilian Stölzle, Della Cosimo, Santina

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 1 failure of our instrument; 1 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/2409.08439.json · badge: /api/ran/2409.08439.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
tud-phi/uncovering-iss-coupled-oscillator-networks-from-pixels canonical (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
FunctionStatusWhere it lives
NeuralOdeBase Ran
ran on a synthesized input · constructed an object; no result was computed
tud-phi/uncovering-iss-coupled-oscillator-networks-from-pixels/src/models/neural_odes/con.py
code served (permissive licence) · get_code("950ac8cef141148d")
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 an instance of its own class, NeuralOdeBase: the run constructed the object and did not call it, so no result was computed. 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
from flax import linen as flax_nn
import jax
import jax.numpy as jnp

torch.manual_seed(0)

# Since NeuralOdeBase is a Flax nn.Module with no required parameters,
# we need to understand what arguments forward_dynamics and forward_all_layers
# might receive. These methods delegate to __call__, which in Flax modules
# typically receives inputs and potentially other arguments.

# Create a minimal concrete subclass to test
class SimpleNeuralOde(flax_nn.Module):
    def setup(self):
        pass
    
    def __call__(self, x, *args, **kwargs):
        return x

# Since NeuralOdeBase itself has no explicit __init__ parameters,
# the ARGS dict should be empty or contain only what nn.Module base class needs
ARGS = {}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
flax, jax, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type NeuralOdeBase — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a NeuralOdeBase 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
generate_positive_definite_matrix_from_params Ran
ran; our contract draft was wrong, not the code
tud-phi/uncovering-iss-coupled-oscillator-networks-from-pixels/src/models/neural_odes/con.py
code served (permissive licence) · get_code("dd69c05388677a01")
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 ArrayImpl, ndim 2, dtype family float, shape (4, 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 jax
import jax.numpy as jnp
from flax import linen as nn

# Set seed for reproducibility
key = jax.random.PRNGKey(0)

# Define parameters
n = 4  # dimension of the matrix
# For a lower triangular matrix of size (n, n), we need (n^2 + n) / 2 parameters
num_params = (n * n + n) // 2

# Generate a random vector of parameters
a = jax.random.normal(key, shape=(num_params,))

# Convert to JAX Array if needed
a = jnp.array(a)

# Define all arguments
ARGS = {
    "n": n,
    "a": a,
    "diag_shift": 1e-06,
    "diag_eps": 2e-06
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
flax, jax — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ArrayImpl, ndim 2, dtype family float, shape (4, 4) — shape (4, 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
ConOde Not yet run
unverified (harvested, no recorded run)
tud-phi/uncovering-iss-coupled-oscillator-networks-from-pixels/src/models/neural_odes/con.py
code served (permissive licence) · get_code("890e4c17c5410d01")
How it ran

no invocation recorded.

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, 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 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.

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

Even though a variety of methods have been proposed in the literature, efficient and effective latent-space control (i.e., control in a learned low-dimensional space) of physical systems remains an open challenge. We argue that a promising avenue is to leverage powerful and well-understood closed-form strategies from control theory literature in combination with learned dynamics, such as potential-energy shaping. We identify three fundamental shortcomings in existing latent-space models that have so far prevented this powerful combination: (i) they lack the mathematical structure of a physical system, (ii) they do not inherently conserve the stability properties of the real systems, (iii) these methods do not have an invertible mapping between input and latent-space forcing. This work proposes a novel Coupled Oscillator Network (CON) model that simultaneously tackles all these issues. More specifically, (i) we show analytically that CON is a Lagrangian system -i.e., it possesses well-defined potential and kinetic energy terms. Then, (ii) we provide formal proof of global Input-to-State stability using Lyapunov arguments. Moving to the experimental side, we demonstrate that CON reaches SoA performance when learning complex nonlinear dynamics of mechanical systems directly from images. An additional methodological innovation contributing to achieving this third goal is an approximated closed-form solution for efficient integration of network dynamics, which eases efficient training. We tackle (iii) by approximating the forcing-to-input mapping with a decoder that is trained to reconstruct the input based on the encoded latent space force. Finally, we leverage these three properties and show that they enable latent-space control. We use an integral-saturated PID with potential force compensation and demonstrate high-quality performance on a soft robot using raw pixels as the only feedback information. One outstanding challenge is how to perform closed-loop control in the learned latent spacei.e., how to generate control inputs based on a high dimensional sensory input such that a desired movement is generated. Prior works have explored, among other approaches, Reinforcement Learning (RL) [11,12,13,14], Model Predictive Control (MPC) [7,15,16,17], Linear-quadratic Regulators (LQRs) [18,19,20] and gradient-based optimization [21] for planning and control towards a target evolution that is given in observation space. However, all existing latent-space control strategies have shortcomings, such as a limited planning horizon and slow control rates (MPC and gradient-based 38th Conference on Neural Information Processing Systems (NeurIPS 2024).

For agents

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

get_harvested_code_for_paper("2409.08439")
get_code_for_paper("2409.08439")
have("2409.08439")

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

curl https://syntology.ai/api/ran/2409.08439.json

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

[![Syntology run record](https://syntology.ai/api/ran/2409.08439.svg)](https://syntology.ai/paper/2409.08439)

Connect an agent — have() is free.