SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2606.15751 · 2026

Acoustic Prompting via Stage-wise Modulation for Few-Shot Learning in Audio Language Models

Changick Kim, Jaehyuk Jang, Son Chung, Hyebin Cho

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/2606.15751.json · badge: /api/ran/2606.15751.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
hyebin-c/aspl canonical (classifier label)
classifier basis: census
3 ran · 2 no recorded run
FunctionStatusWhere it lives
do_mixup Ran
ran, honoured the contract we drafted
hyebin-c/aspl/pengi/models/htsat.py
code served (permissive licence) · get_code("5337e68cdb46397d")
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, 3) 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)

# Construct arguments for do_mixup
# x: (batch_size * 2, ...) - we use batch_size=2, so shape is (4, 3)
# mixup_lambda: (batch_size * 2,) - shape is (4,)

x = torch.randn(4, 3)
mixup_lambda = torch.rand(4)

ARGS = {
    "x": x,
    "mixup_lambda": mixup_lambda,
}
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, 3) — shape (2, 3) 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
drop_path Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hyebin-c/aspl/pengi/models/htsat.py
pointer only (licence: MIT); the stored copy get_code serves, from fudan-zvg/SeaFormer, is pointer only (licence: NONE) · get_code("3ac6b7d76e8e3584")
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 fudan-zvg/SeaFormer, 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.

interpolate Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hyebin-c/aspl/pengi/models/htsat.py
code served (permissive licence) · get_code("bdcac6c19196f655")
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 3, dtype family float, shape (2, 8, 3) 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)

# x: (batch_size, time_steps, classes_num)
# ratio: int, ratio to interpolate

x = torch.randn(2, 4, 3)  # batch_size=2, time_steps=4, classes_num=3
ratio = 2

ARGS = {
    "x": x,
    "ratio": ratio,
}
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 3, dtype family float, shape (2, 8, 3) — shape (2, 8, 3) 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
get_audio_encoder Not yet run
unverified (harvested, no recorded run)
hyebin-c/aspl/pengi/models/audio.py
code served (permissive licence) · get_code("886518ba9cf12339")
How it ran

no invocation recorded.

get_decoder Not yet run
unverified (harvested, no recorded run)
hyebin-c/aspl/pengi/models/decoder.py
code served (permissive licence) · get_code("360a191dd28ceec7")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 1 the same month, 0 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
drop_path 224 other papers
223 dated earlier, 1 undated · 38 only as an assembly brick
2003.12039 (2020-03)
RAFT: Recurrent All-Pairs Field Transforms for Optical Flow
2007.09384 (2020-07)
Multi-Scale Positive Sample Refinement for Few-Shot Object Detection
2010.11929 (2020-10)
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
and 221 more not named here
do_mixup 8 other papers
7 dated earlier, 1 the same month
1912.10211 (2019-12)
PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition
2305.11834 (2023-05)
Pengi: An Audio Language Model for Audio Tasks
2309.05767 (2023-09)
Natural Language Supervision for General-Purpose Audio Representations
and 5 more not named here
interpolate 8 other papers
8 dated earlier
1912.04761 (2019-12)
Sound Event Detection of Weakly Labelled Data with CNN-Transformer and Automatic Threshold Optimization
2305.11834 (2023-05)
Pengi: An Audio Language Model for Audio Tasks
2309.05767 (2023-09)
Natural Language Supervision for General-Purpose Audio Representations
and 5 more not named here
get_decoder 3 other papers
3 dated earlier
2305.11834 (2023-05)
Pengi: An Audio Language Model for Audio Tasks
2502.04476 (2025-02)
ADIFF: Explaining audio difference using natural language
2503.08540 (2025-03)
Mellow: a small audio language model for reasoning

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

Audio-Language Models (ALMs) have shown remarkable success in zero-shot audio classification by aligning audio waveforms with text. Recent efforts to improve downstream performance focus on learning optimal text prompts. However, previous approaches focus on the text encoder, leaving the potential of learnable prompts within the audio encoder unexplored. In this paper, we propose a novel framework that introduces trainable prompts into the audio encoder to capture task-specific acoustic features. We demonstrate that integrating audio-side prompt learning with existing text-side approaches enhances few-shot adaptation. Through extensive experiments across 11 datasets show that integrating our method as a plug-and-play module alongside existing text prompt tuning generally leads to performance improvements. These findings suggest that explicitly modulating the audio representation space effectively complements text-only prompting approaches. The code is available at https://github.com/hyebin-c/aspl.

For agents

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

get_harvested_code_for_paper("2606.15751")
get_code_for_paper("2606.15751")
have("2606.15751")

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

curl https://syntology.ai/api/ran/2606.15751.json

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

[![Syntology run record](https://syntology.ai/api/ran/2606.15751.svg)](https://syntology.ai/paper/2606.15751)

Connect an agent — have() is free.