SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.01439 · CVPR · 2024

Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis

arXiv · PDF · Open in the Atlas

Code that ran

7 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 0 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/2403.01439.json · badge: /api/ran/2403.01439.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
LMD0311/DAPT canonical (classifier label)
classifier basis not recorded on the link
7 ran · 0 no recorded run
FunctionStatusWhere it lives
apply_tfts Ran
ran, honoured the contract we drafted
LMD0311/DAPT/models/DAPT.py
code served (permissive licence) · get_code("9b526081c1cc6aca")
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

torch.manual_seed(0)

# Test case 1: x.shape[-1] == gamma.shape[0]
# x shape: (2, 4) where last dim is 4
# gamma, beta shape: (4,)
x1 = torch.randn(2, 4)
gamma1 = torch.randn(4)
beta1 = torch.randn(4)

ARGS = {
    "x": x1,
    "gamma": gamma1,
    "beta": beta1,
}
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 (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
farthest_point_sample Ran
ran; our contract draft was wrong, not the code
LMD0311/DAPT/datasets/ModelNetDataset.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Yuzhe-Fu/FlashFPS, is pointer only (licence: NOASSERTION) · get_code("f80066a00e7156a2")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Yuzhe-Fu/FlashFPS, 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.

get_missing_parameters_message Ran
ran; our contract draft was wrong, not the code
LMD0311/DAPT/utils/checkpoint.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from wdttt/PointSD, is pointer only (licence: NONE) · get_code("79cfc5c7bcc39b7b")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from wdttt/PointSD, 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_unexpected_parameters_message Ran
ran; our contract draft was wrong, not the code
LMD0311/DAPT/utils/checkpoint.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from wdttt/PointSD, is pointer only (licence: NONE) · get_code("f45b84cf72162235")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from wdttt/PointSD, 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.

init_tfts Ran
ran; our contract draft was wrong, not the code
LMD0311/DAPT/models/DAPT.py
code served (permissive licence) · get_code("60cd7cd407741b4c")
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
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "dim": 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 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
load_modelnet_data Ran
ran; our contract draft was wrong, not the code
LMD0311/DAPT/datasets/ModelNetDataset.py
code served (permissive licence) · get_code("39b2b4edb312a41a")
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 os
import tempfile
import h5py
import numpy as np

# Create a temporary directory structure with mock HDF5 files
temp_dir = tempfile.mkdtemp()
data_dir = os.path.join(temp_dir, 'data', 'modelnet40_ply_hdf5_2048')
os.makedirs(data_dir, exist_ok=True)

# Create mock HDF5 files for 'train' partition
for i in range(2):
    h5_path = os.path.join(data_dir, f'ply_data_train{i}.h5')
    with h5py.File(h5_path, 'w') as f:
        # Create datasets with appropriate shapes and dtypes
        f.create_dataset('data', data=np.random.rand(4, 2048, 3).astype('float32'))
        f.create_dataset('label', data=np.random.randint(0, 40, (4,)).astype('int64'))

# Monkey patch os.path.join to redirect to our temp directory
original_join = os.path.join
def patched_join(base, *args):
    if base == './' and args and args[0] == 'data':
        return os.path.join(temp_dir, *args)
    return original_join(base, *args)

os.path.join = patched_join

ARGS = {
    'partition': 'train'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
h5py, numpy — 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
pc_normalize Ran
ran, honoured the contract we drafted
LMD0311/DAPT/datasets/ModelNetDataset.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from ajhamdi/MVTN, is pointer only (licence: NONE) · get_code("4783fbece52f500e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from ajhamdi/MVTN, 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.

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, 7 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 2 the same month, 7 later) and 0 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
pc_normalize 47 other papers
27 dated earlier, 2 the same month, 17 later, 1 same year, order not determinable
1811.07246 (2018-11)
PointConv: Deep Convolutional Networks on 3D Point Clouds
1912.12098 (2019-12)
Quaternion Equivariant Capsule Networks for 3D Point Clouds
2003.00492 (2020-03)
PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling
and 44 more not named here
farthest_point_sample 43 other papers
23 dated earlier, 2 the same month, 17 later, 1 same year, order not determinable
1811.07246 (2018-11)
PointConv: Deep Convolutional Networks on 3D Point Clouds
2003.00492 (2020-03)
PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling
2010.05272 (2020-10)
IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restoration
and 40 more not named here
get_missing_parameters_message 8 other papers
1 dated earlier, 6 later, 1 same year, order not determinable
2309.00615 (2023-09)
Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following
2405.15463 (2024-05)
PoinTramba: A Hybrid Transformer-Mamba Framework for Point Cloud Analysis
and 5 more not named here
get_unexpected_parameters_message 8 other papers
1 dated earlier, 5 later, 2 same year, order not determinable
2309.00615 (2023-09)
Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following
Wang_Zero-TPrune_Zero-Shot_Token_Pruning_through_Leveraging_of_the_Attention_Graph_CVPR_2024_paper (2024 (year only))
Zero-TPrune: Zero-Shot Token Pruning through Leveraging of the Attention Graph in Pre-Trained Transformers
and 5 more not named here
load_modelnet_data 4 other papers
1 dated earlier, 3 later
2402.10739 (2024-02)
PointMamba: A Simple State Space Model for Point Cloud Analysis
2405.15463 (2024-05)
PoinTramba: A Hybrid Transformer-Mamba Framework for Point Cloud Analysis
2410.08114 (2024-10)
Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning
and 1 more not named here
apply_tfts 1 other paper
1 later
2410.08114 (2024-10)
Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning
init_tfts 1 other paper
1 later
2410.08114 (2024-10)
Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning

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

Point cloud analysis has achieved outstanding performance by transferring point cloud pre-trained models. However, existing methods for model adaptation usually update all model parameters, i.e., full fine-tuning paradigm, which is inefficient as it relies on high computational costs (e.g., training GPU memory) and massive storage space. In this paper, we aim to study parameter-efficient transfer learning for point cloud analysis with an ideal tradeoff between task performance and parameter efficiency. To achieve this goal, we freeze the parameters of the default pre-trained models and then propose the Dynamic Adapter, which generates a dynamic scale for each token, considering the token significance to the downstream task. We further seamlessly integrate Dynamic Adapter with Prompt Tuning (DAPT) by constructing Internal Prompts, capturing the instance-specific features for interaction. Extensive experiments conducted on five challenging datasets demonstrate that the proposed DAPT achieves superior performance compared to the full fine-tuning counterparts while significantly reducing the trainable parameters and training GPU memory by 95% and 35%, respectively. Code is available at https://github.com/LMD0311/DAPT.

For agents

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

get_harvested_code_for_paper("2403.01439")
get_code_for_paper("2403.01439")
have("2403.01439")

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

curl https://syntology.ai/api/ran/2403.01439.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.01439.svg)](https://syntology.ai/paper/2403.01439)

Connect an agent — have() is free.