SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2405.20985 · 2024

DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 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, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 1 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/2405.20985.json · badge: /api/ran/2405.20985.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
yaolinli/deco canonical (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
FunctionStatusWhere it lives
box_xywh2xyxy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yaolinli/deco/llava/explainability/get_R-GAE_example.py
code served (permissive licence) · get_code("2921ee8cd4935633")
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.

from typing import List, Tuple

# Set up arguments for box_xywh2xyxy function
# Parameters: bbox_xywh (List[float]), img_wh (Tuple[int, int]), do_normalize (bool)

# bbox_xywh: [x, y, width, height] format
bbox_xywh = [10.0, 20.0, 50.0, 30.0]

# img_wh: (image_width, image_height)
img_wh = (640, 480)

# do_normalize: whether to normalize coordinates
do_normalize = True

ARGS = {
    "bbox_xywh": bbox_xywh,
    "img_wh": img_wh,
    "do_normalize": do_normalize,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — 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
load_function_inputs Ran
ran; our contract draft was wrong, not the code
yaolinli/deco/llava/explainability/get_R-GAE_example.py
code served (permissive licence) · get_code("2cf49df7083dc04e")
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 pickle
import tempfile
import os

torch_seed = __import__('torch').manual_seed(0) if True else None

# Create a temporary pickle file with sample args and kwargs
temp_file = tempfile.NamedTemporaryFile(mode='wb', delete=False, suffix='.pkl')
sample_args = (42, "test_string", [1, 2, 3])
sample_kwargs = {"key1": "value1", "key2": 3.14}
pickle.dump((sample_args, sample_kwargs), temp_file)
temp_file.close()

ARGS = {
    "file_path": temp_file.name
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — 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
get_sgae_v Not yet run
unverified (harvested, no recorded run)
yaolinli/deco/llava/explainability/get_R-GAE_example.py
code served (permissive licence) · get_code("33a69559d8c59f44")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 3 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.

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

The visual projector, which bridges the vision and language modalities and facilitates cross-modal alignment, serves as a crucial component in MLLMs. However, measuring the effectiveness of projectors in vision-language alignment remains under-explored, which currently can only be inferred from the performance of MLLMs on downstream tasks. Motivated by the problem, this study examines the projector module by interpreting the vision-language semantic flow within MLLMs. Specifically, we trace back the semantic relevance flow from generated language tokens to raw visual encoder patches and the intermediate outputs produced by projectors. Our findings reveal that compressive projectors (e.g., QFormer), abstract visual patches into a limited set of semantic concepts, such as objects or attributes, resulting in a 'double abstraction' phenomenon. This involves a first visual semantic abstraction by the projector referring to pre-defined query tokens, and a second extraction by the LLM based on text instructions. The double abstraction is inefficient in training and will result in cumulative vision semantics deficiency. To mitigate this issue, we propose the key insight of 'Decouple Compression from Abstraction (DeCo), that is compressing the visual token number at the patch level by projectors and allowing the LLM to handle visual semantic abstraction entirely. Consequently, we adopt a simple compressor, i.e., 2D Adaptive Pooling, to downsample visual patches in a parameter-free manner. Empirical evaluation demonstrates that DeCo surpasses traditional compressive projectors regarding both performance and efficiency. It achieves performance gains of 0.9%, 7.1%, and 2.9% across the MLLM Benchmarks, Visual Localization, and Open-ended VQA tasks with fewer trainable parameters and faster convergence speed.

For agents

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

get_harvested_code_for_paper("2405.20985")
get_code_for_paper("2405.20985")
have("2405.20985")

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

curl https://syntology.ai/api/ran/2405.20985.json

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

[![Syntology run record](https://syntology.ai/api/ran/2405.20985.svg)](https://syntology.ai/paper/2405.20985)

Connect an agent — have() is free.