SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2311.12871 · ICML · 2024

An Embodied Generalist Agent in 3D World

Song-Chun Zhu, Qing Li, Siyuan Huang, Yan Wang, Xiaojian Ma, Baoxiong Jia, Silong Yong, Jiangyong Huang, Xiongkun Linghu, Puhao Li, Robotic Manipulation

arXiv · PDF · Open in the Atlas

Code that ran

11 of 13 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; 10 failures of our instrument; 2 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/2311.12871.json · badge: /api/ran/2311.12871.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
embodied-generalist/embodied-generalist canonical (classifier label)
classifier basis: census
11 ran · 2 no recorded run
FunctionStatusWhere it lives
apply_rotary_pos_emb Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
embodied-generalist/embodied-generalist/model/transformers.py
code served (permissive licence) · get_code("9a65a30d006fc96e")
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 tuple, ndim 5, 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)

# Analyze the function:
# - q: tensor, used with *, rotate_half, and arithmetic ops
# - k: tensor, used with *, rotate_half, and arithmetic ops
# - cos: tensor, squeezed twice on dims 1 and 0, indexed by position_ids, unsqueezed
# - sin: tensor, squeezed twice on dims 1 and 0, indexed by position_ids, unsqueezed
# - position_ids: tensor, used to index into cos and sin

# The function expects:
# - q and k to have shape compatible with rotate_half (last dim must be even)
# - cos and sin to have shape (seq_len, 1, hidden_dim) before squeezing
# - position_ids to be indices into the sequence dimension

batch_size = 2
seq_len = 3
hidden_dim = 4
num_positions = 5

# q and k: (batch, seq_len, hidden_dim)
q = torch.randn(batch_size, seq_len, hidden_dim)
k = torch.randn(batch_size, seq_len, hidden_dim)

# cos and sin: (num_positions, 1, hidden_dim)
# After squeeze(1).squeeze(0), they become (num_positions, hidden_dim)
cos = torch.randn(num_positions, 1, hidden_dim)
sin = torch.randn(num_positions, 1, hidden_dim)

# position_ids: indices into the position dimension, shape (batch, seq_len)
position_ids = torch.tensor([[0, 1, 2], [1, 2, 3]], dtype=torch.long)

ARGS = {
    "q": q,
    "k": k,
    "cos": cos,
    "sin": sin,
    "position_ids": position_ids,
}
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 tuple, ndim 5, dtype family float — a tuple 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
cfg2dict Ran
ran; our contract draft was wrong, not the code
embodied-generalist/embodied-generalist/common/type_utils.py
code served (permissive licence) · get_code("592aacb855a01d0f")
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 dict. 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 omegaconf import OmegaConf

# Create a simple OmegaConf config object
cfg = OmegaConf.create({
    "model": {
        "name": "test_model",
        "layers": 3,
        "hidden_dim": 128
    },
    "training": {
        "lr": 0.001,
        "epochs": 10,
        "batch_size": 32
    },
    "debug": True
})

ARGS = {
    "cfg": cfg
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
omegaconf — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
disabled_train Ran
ran; our contract draft was wrong, not the code
embodied-generalist/embodied-generalist/model/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from RuipingL/Situat3DChange, is pointer only (licence: CC-BY-4.0) · get_code("9d2100678022a09b")
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 RuipingL/Situat3DChange, and CC-BY-4.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

generate_fourier_features Ran
ran; our contract draft was wrong, not the code
embodied-generalist/embodied-generalist/model/vision3d.py
pointer only (licence: MIT); the stored copy get_code serves, from RuipingL/Situat3DChange, is pointer only (licence: CC-BY-4.0) · get_code("edefc587492eb250")
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 RuipingL/Situat3DChange, and CC-BY-4.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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_activation_fn Ran
ran; our contract draft was wrong, not the code
embodied-generalist/embodied-generalist/model/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from RuipingL/Situat3DChange, is pointer only (licence: CC-BY-4.0) · get_code("165417eb35c55e89")
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 RuipingL/Situat3DChange, and CC-BY-4.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

is_port_available Ran
ran, violated the contract we drafted
embodied-generalist/embodied-generalist/common/launch_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from RuipingL/Situat3DChange, is pointer only (licence: CC-BY-4.0) · get_code("2fb14462bf1a1166")
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 RuipingL/Situat3DChange, and CC-BY-4.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

load_imgs Ran
ran; our contract draft was wrong, not the code
embodied-generalist/embodied-generalist/common/io_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from RuipingL/Situat3DChange, is pointer only (licence: CC-BY-4.0) · get_code("1eee3af921bc5d88")
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 RuipingL/Situat3DChange, and CC-BY-4.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

load_json Ran
ran; our contract draft was wrong, not the code
embodied-generalist/embodied-generalist/common/io_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from RuipingL/Situat3DChange, is pointer only (licence: CC-BY-4.0) · get_code("bace1acf5a748097")
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 RuipingL/Situat3DChange, and CC-BY-4.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

load_pickle Ran
ran; our contract draft was wrong, not the code
embodied-generalist/embodied-generalist/common/io_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from RuipingL/Situat3DChange, is pointer only (licence: CC-BY-4.0) · get_code("7de9d66696a307eb")
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 RuipingL/Situat3DChange, and CC-BY-4.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

maybe_autocast Ran
ran; our contract draft was wrong, not the code
embodied-generalist/embodied-generalist/model/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from RuipingL/Situat3DChange, is pointer only (licence: CC-BY-4.0) · get_code("76f3fbdda12ce4eb")
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 RuipingL/Situat3DChange, and CC-BY-4.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

rotate_half Ran
ran; our contract draft was wrong, not the code
embodied-generalist/embodied-generalist/model/transformers.py
code served (permissive licence) · get_code("e03d53ba9d4f9ae5")
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 function takes a single parameter 'x' which is a tensor
# It accesses x[..., :x.shape[-1] // 2] and x[..., x.shape[-1] // 2:]
# So x needs to be a tensor with a last dimension that can be split in half
# Let's create a small tensor with batch size 2 and feature dimension 4

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
rgetattr Not yet run
unverified (harvested, no recorded run)
embodied-generalist/embodied-generalist/common/misc.py
code served (permissive licence) · get_code("44925cf3831bfe79")
How it ran

no invocation recorded.

rsetattr Not yet run
unverified (harvested, no recorded run)
embodied-generalist/embodied-generalist/common/misc.py
pointer only (licence: MIT); the stored copy get_code serves, from DBO-DKFZ/uncertainty-benchmark, is pointer only (licence: NONE) · get_code("f9de4cdd8a624801")
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 DBO-DKFZ/uncertainty-benchmark, 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. No invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 12 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 5 the same month, 12 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
rotate_half 360 other papers
39 dated earlier, 7 the same month, 311 later, 3 undated · 30 only as an assembly brick
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
2203.08913 (2022-03)
Memorizing Transformers
2302.13971 (2023-02)
LLaMA: Open and Efficient Foundation Language Models
and 357 more not named here
disabled_train 173 other papers
57 dated earlier, 6 the same month, 110 later · 5 only as an assembly brick
2012.09841 (2020-12)
Taming Transformers for High-Resolution Image Synthesis
2102.05379 (2021-02)
Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
2104.07652 (2021-04)
Geometry-Free View Synthesis: Transformers and no 3D Priors
and 170 more not named here
apply_rotary_pos_emb 83 other papers
9 dated earlier, 3 the same month, 71 later · 6 only as an assembly brick
2306.15595 (2023-06)
Extending Context Window of Large Language Models via Positional Interpolation
2307.05695 (2023-07)
ReLoRA: High-Rank Training Through Low-Rank Updates
2307.06945 (2023-07)
In-context Autoencoder for Context Compression in a Large Language Model
and 80 more not named here
rgetattr 13 other papers
6 dated earlier, 1 the same month, 5 later, 1 same year, order not determinable · 1 only as an assembly brick
2203.04036 (2022-03)
StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN
2209.02952 (2022-09)
BiFuse++: Self-supervised and Efficient Bi-projection Fusion for 360 Depth Estimation
2211.05778 (2022-11)
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
and 10 more not named here
rsetattr 8 other papers
3 dated earlier, 1 the same month, 4 later
2203.04036 (2022-03)
StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN
2212.04501 (2022-12)
Learning Video Representations from Large Language Models
2305.13417 (2023-05)
VISIT: Visualizing and Interpreting the Semantic Information Flow of Transformers
and 5 more not named here
load_imgs 2 other papers
2 later
2401.01529 (2024-01)
Glance and Focus: Memory Prompting for Multi-Event Video Question Answering
2510.11509 (2025-10)
Situat3DChange: Situated 3D Change Understanding Dataset for Multimodal Large Language Model
load_json 2 other papers
2 later
2401.01529 (2024-01)
Glance and Focus: Memory Prompting for Multi-Event Video Question Answering
2510.11509 (2025-10)
Situat3DChange: Situated 3D Change Understanding Dataset for Multimodal Large Language Model
load_pickle 2 other papers
2 later
2401.01529 (2024-01)
Glance and Focus: Memory Prompting for Multi-Event Video Question Answering
2510.11509 (2025-10)
Situat3DChange: Situated 3D Change Understanding Dataset for Multimodal Large Language Model
generate_fourier_features 1 other paper
1 later
2510.11509 (2025-10)
Situat3DChange: Situated 3D Change Understanding Dataset for Multimodal Large Language Model
get_activation_fn 1 other paper
1 later
2510.11509 (2025-10)
Situat3DChange: Situated 3D Change Understanding Dataset for Multimodal Large Language Model
is_port_available 1 other paper
1 later
2510.11509 (2025-10)
Situat3DChange: Situated 3D Change Understanding Dataset for Multimodal Large Language Model
maybe_autocast 1 other paper
1 later
2510.11509 (2025-10)
Situat3DChange: Situated 3D Change Understanding Dataset for Multimodal Large Language Model

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

Leveraging massive knowledge from large language models (LLMs), recent machine learning models show notable successes in generalpurpose task solving in diverse domains such as computer vision and robotics. However, several significant challenges remain: (i) most of these models rely on 2D images yet exhibit a limited capacity for 3D input; (ii) these models rarely explore the tasks inherently defined in 3D world, e.g., 3D grounding, embodied reasoning and acting. We argue these limitations significantly hinder current models from performing real-world tasks and approaching general intelligence. To this end, we introduce LEO, an embodied multimodal generalist agent that excels in perceiving, grounding, reasoning, planning, and acting in the 3D world. LEO is trained with a unified task interface, model architecture, and objective in two stages: (i) 3D vision-language (VL) alignment and (ii) 3D vision-language-action (VLA) instruction tuning. We collect large-scale datasets comprising diverse object-level and scene-level tasks, which require considerable understanding of and interaction with the 3D world. Moreover, we meticulously design an LLM-assisted pipeline to produce high-quality 3D VL data. Through extensive experiments, we demonstrate LEO's remarkable proficiency across a wide spectrum of tasks, including 3D captioning, question answering, embodied reasoning, navigation and manipulation. Our ablative studies and scaling analyses further provide valuable insights for developing future embodied generalist agents. Code and data are available on project page.

For agents

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

get_harvested_code_for_paper("2311.12871")
get_code_for_paper("2311.12871")
have("2311.12871")

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

curl https://syntology.ai/api/ran/2311.12871.json

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

[![Syntology run record](https://syntology.ai/api/ran/2311.12871.svg)](https://syntology.ai/paper/2311.12871)

Connect an agent — have() is free.