SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.03181 · 2024

Behavior Generation with Latent Actions

arXiv · PDF · Open in the Atlas

Code that ran

8 of 14 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; 2 honoured the contract we drafted, 3 violated it and 1 has no contract verdict; 2 failures of our instrument; 6 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/2403.03181.json · badge: /api/ran/2403.03181.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
jayLEE0301/vq_bet_official canonical (classifier label)
classifier basis: census
7 ran · 3 no recorded run
ziyadsheeba/qfat community (classifier label)
classifier basis not recorded on the link
1 ran · 3 no recorded run
FunctionStatusWhere it lives
collate_policy Ran
ran on a synthesized input
ziyadsheeba/qfat/src/qfat/datasets/dataset.py
code served (permissive licence) · get_code("290e63bdbac69bc8")
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 Batch. 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 numpy as np
from dataclasses import dataclass
from typing import Optional

torch.manual_seed(0)

@dataclass
class Trajectory:
    states: np.ndarray
    actions: np.ndarray
    prev_actions: Optional[np.ndarray] = None
    goals: Optional[np.ndarray] = None
    raw_goals: Optional[np.ndarray] = None
    labels: Optional[np.ndarray] = None

# Create sample trajectories with distinct dimension sizes
traj1 = Trajectory(
    states=np.random.randn(5, 4).astype(np.float32),  # sequence_len=5, state_dim=4
    actions=np.random.randn(5, 3).astype(np.float32),  # sequence_len=5, action_dim=3
    prev_actions=np.random.randn(5, 3).astype(np.float32),  # sequence_len=5, action_dim=3
    goals=np.random.randn(5, 6).astype(np.float32),  # sequence_len=5, goal_dim=6
)

traj2 = Trajectory(
    states=np.random.randn(3, 4).astype(np.float32),  # sequence_len=3, state_dim=4
    actions=np.random.randn(3, 3).astype(np.float32),  # sequence_len=3, action_dim=3
    prev_actions=np.random.randn(3, 3).astype(np.float32),  # sequence_len=3, action_dim=3
    goals=np.random.randn(3, 6).astype(np.float32),  # sequence_len=3, goal_dim=6
)

batch = [traj1, traj2]

ARGS = {
    "batch": batch,
}
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 Batch — a Batch output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Batch 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
default Ran
ran, violated the contract we drafted
jayLEE0301/vq_bet_official/vector_quantize_pytorch/residual_vq.py
pointer only (licence: MIT); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("60fff7c3c400d7ff")
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 ThomasMrY/VCT, 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.

exists Ran
ran, violated the contract we drafted
jayLEE0301/vq_bet_official/vector_quantize_pytorch/residual_vq.py
pointer only (licence: MIT); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("aa5486a3650902d8")
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 ThomasMrY/VCT, 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.

get_tensor Ran
ran; our contract draft was wrong, not the code
jayLEE0301/vq_bet_official/vqvae/vqvae_utils.py
code served (permissive licence) · get_code("5f5f6bab7bdf48cb")
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 (2, 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)

# Case 1: z is None
z_none = None
device_cpu = 'cpu'

# Case 2: z is a numpy array with dtype object (should return None)
z_object_dtype = np.array([object(), object()], dtype=object)

# Case 3: z is a 1D numpy array (should unsqueeze to add batch dimension)
z_1d = np.array([1.0, 2.0, 3.0, 4.0], dtype=np.float32)

# Case 4: z is a 2D numpy array (should convert directly)
z_2d = np.array([[1.0, 2.0, 3.0, 4.0],
                  [5.0, 6.0, 7.0, 8.0]], dtype=np.float32)

# Choose one case to test
ARGS = {
    'z': z_2d,
    'device': device_cpu
}
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 2, dtype family float, shape (2, 4) — shape (2, 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
identity Ran
ran, honoured the contract we drafted
jayLEE0301/vq_bet_official/vector_quantize_pytorch/vector_quantize_pytorch.py
code served (permissive licence) · get_code("f3232418205f7cbd")
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) and returned Tensor, ndim 2, dtype family float, shape (2, 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)

# The identity function takes a single parameter 't' and returns it unchanged
# We'll provide a simple tensor as the argument
t = torch.randn(2, 4)

ARGS = {
    "t": t
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 (2, 4) — shape (2, 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
new_gelu Ran
ran; our contract draft was wrong, not the code
jayLEE0301/vq_bet_official/vq_behavior_transformer/gpt.py
code served (permissive licence) · get_code("92101b06ecbf1f1e")
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) and returned Tensor, ndim 2, dtype family float, shape (2, 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 math

torch.manual_seed(0)

# The function new_gelu takes a single parameter 'x' which should be a tensor
# It performs mathematical operations on x: addition, multiplication, power, tanh
# So x needs to be a torch.Tensor that supports these operations

x = torch.randn(2, 4)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 (2, 4) — shape (2, 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
q_inv Ran
ran, violated the contract we drafted
jayLEE0301/vq_bet_official/envs/antenv/ant.py
code served (permissive licence) · get_code("b518b50864d18ead")
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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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)

# q_inv takes a quaternion representation as input
# A quaternion is typically [w, x, y, z] or [x, y, z, w]
# The function returns the inverse by negating the imaginary parts (indices 1, 2, 3)
# So we need a list or sequence of 4 elements

a = [1.0, 0.5, -0.3, 0.2]

ARGS = {
    "a": a
}
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 list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
round_up_multiple Ran
ran, honoured the contract we drafted
jayLEE0301/vq_bet_official/vector_quantize_pytorch/residual_vq.py
code served (permissive licence) · get_code("bf63ff5f88b9f6b3")
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 int, ndim 0, dtype family int, shape () 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
from math import ceil

def round_up_multiple(num, mult):
    return ceil(num / mult) * mult

ARGS = {
    "num": 7,
    "mult": 3
}
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 int, ndim 0, dtype family int, shape () — shape () 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
covariance_ellipse Not yet run
unverified (harvested, no recorded run)
ziyadsheeba/qfat/src/qfat/utils.py
code served (permissive licence) · get_code("1a66725274da6033")
How it ran

no invocation recorded.

create_gather_env Not yet run
unverified (harvested, no recorded run)
jayLEE0301/vq_bet_official/envs/antenv/create_gather_env.py
code served (permissive licence) · get_code("cde2ae8e18dc91d3")
How it ran

no invocation recorded.

create_maze_env Not yet run
unverified (harvested, no recorded run)
jayLEE0301/vq_bet_official/envs/antenv/create_maze_env.py
code served (permissive licence) · get_code("45edef65d8e9ec47")
How it ran

no invocation recorded.

get_image_from_fig Not yet run
unverified (harvested, no recorded run)
ziyadsheeba/qfat/src/qfat/utils.py
code served (permissive licence) · get_code("c32a6f9abdf33258")
How it ran

no invocation recorded.

load_metric_from_wandb Not yet run
unverified (harvested, no recorded run)
ziyadsheeba/qfat/src/qfat/utils.py
code served (permissive licence) · get_code("512357de55b799f0")
How it ran

no invocation recorded.

q_mult Not yet run
unverified (harvested, no recorded run)
jayLEE0301/vq_bet_official/envs/antenv/ant.py
code served (permissive licence) · get_code("b5987afb2eb91889")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 8 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 3 the same month, 5 later) and 6 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
exists 486 other papers
309 dated earlier, 19 the same month, 147 later, 9 same year, order not determinable, 2 undated · 78 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1804.04637 (2018-04)
EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models
and 483 more not named here
default 163 other papers
120 dated earlier, 3 the same month, 37 later, 2 same year, order not determinable, 1 undated · 27 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1810.00825 (2018-10)
Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks
1907.01470 (2019-07)
Augmenting Self-attention with Persistent Memory
and 160 more not named here
identity 21 other papers
6 dated earlier, 14 later, 1 undated · 2 only as an assembly brick
2011.10043 (2020-11)
Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning
2203.08913 (2022-03)
Memorizing Transformers
2302.04761 (2023-02)
Toolformer: Language Models Can Teach Themselves to Use Tools
and 18 more not named here
new_gelu 9 other papers
3 dated earlier, 1 the same month, 5 later
2210.13319 (2022-10)
MARS: Meta-Learning as Score Matching in the Function Space
2307.03381 (2023-07)
Teaching Arithmetic to Small Transformers
2309.07207 (2023-09)
EarthPT: a time series foundation model for Earth Observation
and 6 more not named here
q_inv 3 other papers
3 dated earlier
2004.12974 (2020-04)
Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning
2210.10195 (2022-10)
Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation
2401.09870 (2024-01)
Reconciling Spatial and Temporal Abstractions for Goal Representation
q_mult 2 other papers
2 dated earlier
2004.12974 (2020-04)
Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning
2401.09870 (2024-01)
Reconciling Spatial and Temporal Abstractions for Goal Representation
round_up_multiple 2 other papers
2 later
2411.02038 (2024-11)
Addressing Representation Collapse in Vector Quantized Models with One Linear Layer
2601.22244 (2026-01)
Is Hierarchical Quantization Essential for Optimal Reconstruction?
create_gather_env 1 other paper
1 dated earlier
2401.09870 (2024-01)
Reconciling Spatial and Temporal Abstractions for Goal Representation

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

Generative modeling of complex behaviors from labeled datasets has been a longstanding problem in decision making. Unlike language or image generation, decision making requires modeling actions - continuous-valued vectors that are multimodal in their distribution, potentially drawn from uncurated sources, where generation errors can compound in sequential prediction. A recent class of models called Behavior Transformers (BeT) addresses this by discretizing actions using k-means clustering to capture different modes. However, k-means struggles to scale for high-dimensional action spaces or long sequences, and lacks gradient information, and thus BeT suffers in modeling long-range actions. In this work, we present Vector-Quantized Behavior Transformer (VQ-BeT), a versatile model for behavior generation that handles multimodal action prediction, conditional generation, and partial observations. VQ-BeT augments BeT by tokenizing continuous actions with a hierarchical vector quantization module. Across seven environments including simulated manipulation, autonomous driving, and robotics, VQ-BeT improves on state-of-the-art models such as BeT and Diffusion Policies. Importantly, we demonstrate VQ-BeT's improved ability to capture behavior modes while accelerating inference speed 5x over Diffusion Policies. Videos and code can be found https://sjlee.cc/vq-bet

For agents

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

get_harvested_code_for_paper("2403.03181")
get_code_for_paper("2403.03181")
have("2403.03181")

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

curl https://syntology.ai/api/ran/2403.03181.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.03181.svg)](https://syntology.ai/paper/2403.03181)

Connect an agent — have() is free.