SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.11882 · CVPR · 2024

ReGenNet: Towards Human Action-Reaction Synthesis

Wenjun Zeng, Xiaokang Yang, Xin Jin, Yichao Yan, Yizhou Zhou, Liang Xu, Fengyun Rao, Wenhan Zhu

arXiv · PDF · Open in the Atlas

Code that ran

8 of 11 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; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 3 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/2403.11882.json · badge: /api/ran/2403.11882.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
liangxuy/ReGenNet canonical (classifier label)
classifier basis: census
8 ran · 3 no recorded run
FunctionStatusWhere it lives
approx_standard_normal_cdf Ran
ran; our contract draft was wrong, not the code
liangxuy/ReGenNet/diffusion/losses.py
pointer only (licence: MIT); the stored copy get_code serves, from quandao10/slct, is pointer only (licence: NONE) · get_code("cfd76fd0d89574a4")
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 quandao10/slct, 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.

collate Ran
ran; our contract draft was wrong, not the code
liangxuy/ReGenNet/data_loaders/tensors.py
code served (permissive licence) · get_code("43f8562092d7f4be")
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 tuple. 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

torch.manual_seed(0)

# Create a minimal batch with required structure
# The collate function expects a list of dicts with 'inp' and optionally other keys

batch = [
    {
        'inp': torch.randn(2, 3, 5),  # (channels, joints, frames)
        'lengths': torch.tensor(5),
        'text': 'person walking',
        'tokens': torch.tensor([1, 2, 3]),
        'action': 0,
        'action_text': 'walk'
    },
    {
        'inp': torch.randn(2, 3, 4),
        'lengths': torch.tensor(4),
        'text': 'person running',
        'tokens': torch.tensor([4, 5]),
        'action': 1,
        'action_text': 'run'
    }
]

ARGS = {
    'batch': batch
}
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 tuple — a tuple output has no array shape of its own; none is 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
collate_tensors Ran
ran, honoured the contract we drafted
liangxuy/ReGenNet/data_loaders/tensors.py
pointer only (licence: MIT); the stored copy get_code serves, from jingyugong/SSOMotion, is pointer only (licence: NONE) · get_code("0b9f005ecb737755")
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 jingyugong/SSOMotion, 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.

discretized_gaussian_log_likelihood Ran
ran; our contract draft was wrong, not the code
liangxuy/ReGenNet/diffusion/losses.py
pointer only (licence: MIT); the stored copy get_code serves, from quandao10/slct, is pointer only (licence: NONE) · get_code("cd33283d615fb3d7")
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 quandao10/slct, 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.

lengths_to_mask Ran
ran; our contract draft was wrong, not the code
liangxuy/ReGenNet/data_loaders/tensors.py
pointer only (licence: MIT); the stored copy get_code serves, from jingyugong/SSOMotion, is pointer only (licence: NONE) · get_code("80c46a6e9bfa68f7")
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 jingyugong/SSOMotion, 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.

normal_kl Ran
ran, honoured the contract we drafted
liangxuy/ReGenNet/diffusion/losses.py
pointer only (licence: MIT); the stored copy get_code serves, from facebookresearch/agrol, is pointer only (licence: NOASSERTION) · get_code("cf2798b666b231ca")
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 facebookresearch/agrol, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

positional_encoding Ran
ran, honoured the contract we drafted
liangxuy/ReGenNet/model/transformer_utils.py
code served (permissive licence) · get_code("240608f92933f8f3")
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 (4, 8) 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 math
import torch

torch.manual_seed(0)

ARGS = {
    'd_model': 8,
    'length': 4
}
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 Tensor, ndim 2, dtype family float, shape (4, 8) — shape (4, 8) 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
trunc_normal_ Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
liangxuy/ReGenNet/model/transformer_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from f3set/f3set, is pointer only (licence: NONE) · get_code("e6ea9664b9a77523")
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 f3set/f3set, 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_dataset Not yet run
unverified (harvested, no recorded run)
liangxuy/ReGenNet/data_loaders/get_data.py
code served (permissive licence) · get_code("4311f38d177d875b")
How it ran

no invocation recorded.

get_dataset_class Not yet run
unverified (harvested, no recorded run)
liangxuy/ReGenNet/data_loaders/get_data.py
code served (permissive licence) · get_code("40a9fc1874d88972")
How it ran

no invocation recorded.

get_model_args Not yet run
unverified (harvested, no recorded run)
liangxuy/ReGenNet/utils/model_util.py
code served (permissive licence) · get_code("9b274e76718a39e4")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 4 the same month, 6 later) and 5 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
normal_kl 160 other papers
91 dated earlier, 6 the same month, 61 later, 2 same year, order not determinable · 19 only as an assembly brick
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
and 157 more not named here
trunc_normal_ 160 other papers
99 dated earlier, 4 the same month, 55 later, 2 same year, order not determinable · 36 only as an assembly brick
1911.10194 (2019-11)
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation
2005.10242 (2020-05)
Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere
2007.12911 (2020-07)
Tighter risk certificates for neural networks
and 157 more not named here
approx_standard_normal_cdf 154 other papers
86 dated earlier, 6 the same month, 60 later, 2 same year, order not determinable · 17 only as an assembly brick
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
and 151 more not named here
discretized_gaussian_log_likelihood 128 other papers
82 dated earlier, 5 the same month, 40 later, 1 same year, order not determinable · 16 only as an assembly brick
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
and 125 more not named here
collate_tensors 4 other papers
3 dated earlier, 1 later
2310.12978 (2023-10)
HumanTOMATO: Text-aligned Whole-body Motion Generation
2311.15864 (2023-11)
InterControl: Zero-shot Human Interaction Generation by Controlling Every Joint
2401.01885 (2024-01)
From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations
and 1 more not named here
lengths_to_mask 4 other papers
3 dated earlier, 1 later
2311.15864 (2023-11)
InterControl: Zero-shot Human Interaction Generation by Controlling Every Joint
2312.00063 (2023-12)
MoMask: Generative Masked Modeling of 3D Human Motions
2401.01885 (2024-01)
From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations
and 1 more not named here

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

Humans constantly interact with their surrounding environments. Current human-centric generative models mainly focus on synthesizing humans plausibly interacting with static scenes and objects, while the dynamic human actionreaction synthesis for ubiquitous causal human-human interactions is less explored. Human-human interactions can be regarded as asymmetric with actors and reactors in atomic interaction periods. In this paper, we comprehensively analyze the asymmetric, dynamic, synchronous, and detailed nature of human-human interactions and propose the first multi-setting human action-reaction synthesis benchmark to generate human reactions conditioned on given human actions. To begin with, we propose to annotate the actor-reactor order of the interaction sequences for the NTU120, InterHuman, and Chi3D datasets. Based on them, a diffusion-based generative model with a Transformer decoder architecture called ReGenNet together with an explicit distance-based interaction loss is proposed to predict human reactions in an online manner, where the future states of actors are unavailable to reactors. Quantitative and qualitative results show that our method can generate instant and plausible human reactions compared to the baselines, and can generalize to unseen actor motions and viewpoint changes.

For agents

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

get_harvested_code_for_paper("2403.11882")
get_code_for_paper("2403.11882")
have("2403.11882")

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

curl https://syntology.ai/api/ran/2403.11882.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.11882.svg)](https://syntology.ai/paper/2403.11882)

Connect an agent — have() is free.