SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.12766 · 2023

Language-Driven Representation Learning for Robotics

arXiv · PDF · Open in the Atlas

Code that ran

2 of 7 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 2 have no contract verdict; 0 failures of our instrument; 5 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/2302.12766.json · badge: /api/ran/2302.12766.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
siddk/voltron-evaluation canonical (classifier label)
classifier basis not recorded on the link
1 ran · 4 no recorded run
siddk/voltron-robotics canonical (classifier label)
classifier basis not recorded on the link
1 ran · 1 no recorded run
FunctionStatusWhere it lives
get_path Ran
ran on a synthesized input
siddk/voltron-robotics/voltron/preprocessing/core.py
code served (permissive licence) · get_code("2789bdfe6df3cb6a")
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 str. 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.

from pathlib import Path

ARGS = {
    "save_dir": Path("/tmp/test_save"),
    "v": "model_v1",
    "i": 42,
    "relpath": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
set_global_seed Ran
ran on a synthesized input
siddk/voltron-evaluation/voltron_evaluation/util/random.py
code served (permissive licence) · get_code("c8c4e5a3dc4f02b7")
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 function. 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 os
import random
from typing import Callable
import numpy as np
import torch

def worker_init_function(worker_id: int) -> None:
    """
    Borrowed directly from PyTorch-Lightning; inspired by this issue comment in the PyTorch repo:
        > Ref: https://github.com/pytorch/pytorch/issues/5059#issuecomment-817392562

    Intuition: You can think of the seed sequence spawn function as a "janky" torch.Generator() or jax.PRNGKey that
    you can run iterative splitting on to get new (predictable) randomness.

    :param worker_id: Identifier for the given worker [0, num_workers) for the Dataloader in question.
    """
    global_rank, process_seed = (0, torch.initial_seed())
    base_seed = process_seed - worker_id
    seed_seq = np.random.SeedSequence([base_seed, worker_id, global_rank])
    np.random.seed(seed_seq.generate_state(4))
    torch_seed_seq, random_seed_seq = seed_seq.spawn(2)
    torch.manual_seed(torch_seed_seq.generate_state(1, dtype=np.uint64)[0])
    random_seed = (random_seed_seq.generate_state(2, dtype=np.uint64).astype(list) * [1 << 64, 1]).sum()
    random.seed(random_seed)

def set_global_seed(seed: int) -> Callable[[int], None]:
    """Sets seed for all randomness libraries (mostly random, numpy, torch) and produces a `worker_init_fn`"""
    assert np.iinfo(np.uint32).min < seed < np.iinfo(np.uint32).max, 'Seed outside the np.uint32 bounds!'
    os.environ['EXPERIMENT_GLOBAL_SEED'] = str(seed)
    random.seed(seed)
    np.random.seed(seed)
    torch.manual_seed(seed)
    return worker_init_function

torch.manual_seed(0)

ARGS = {
    'seed': 42
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
build_datamodule Not yet run
unverified (harvested, no recorded run)
siddk/voltron-evaluation/voltron_evaluation/grasping/preprocessing.py
code served (permissive licence) · get_code("40e9f2fb3e486b05")
How it ran

no invocation recorded.

build_datamodule Not yet run
unverified (harvested, no recorded run)
siddk/voltron-evaluation/voltron_evaluation/langref/preprocessing.py
code served (permissive licence) · get_code("f7040983eb9ab964")
How it ran

no invocation recorded.

instantiate_detector Not yet run
unverified (harvested, no recorded run)
siddk/voltron-evaluation/voltron_evaluation/langref/adapter.py
code served (permissive licence) · get_code("d356844b20b60e44")
How it ran

no invocation recorded.

instantiate_segmenter Not yet run
unverified (harvested, no recorded run)
siddk/voltron-evaluation/voltron_evaluation/grasping/adapter.py
code served (permissive licence) · get_code("c60a652253161341")
How it ran

no invocation recorded.

serialize_epoch Not yet run
unverified (harvested, no recorded run)
siddk/voltron-robotics/voltron/preprocessing/core.py
code served (permissive licence) · get_code("29134be0dcfd36fc")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 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 7 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

Recent work in visual representation learning for robotics demonstrates the viability of learning from large video datasets of humans performing everyday tasks. Leveraging methods such as masked autoencoding and contrastive learning, these representations exhibit strong transfer to policy learning for visuomotor control. But, robot learning encompasses a diverse set of problems beyond control including grasp affordance prediction, language-conditioned imitation learning, and intent scoring for human-robot collaboration, amongst others. First, we demonstrate that existing representations yield inconsistent results across these tasks: masked autoencoding approaches pick up on low-level spatial features at the cost of high-level semantics, while contrastive learning approaches capture the opposite. We then introduce Voltron, a framework for language-driven representation learning from human videos and associated captions. Voltron trades off language-conditioned visual reconstruction to learn low-level visual patterns, and visually-grounded language generation to encode high-level semantics. We also construct a new evaluation suite spanning five distinct robot learning problems $\unicode{x2013}$ a unified platform for holistically evaluating visual representations for robotics. Through comprehensive, controlled experiments across all five problems, we find that Voltron's language-driven representations outperform the prior state-of-the-art, especially on targeted problems requiring higher-level features.

For agents

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

get_harvested_code_for_paper("2302.12766")
get_code_for_paper("2302.12766")
have("2302.12766")

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

curl https://syntology.ai/api/ran/2302.12766.json

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

[![Syntology run record](https://syntology.ai/api/ran/2302.12766.svg)](https://syntology.ai/paper/2302.12766)

Connect an agent — have() is free.