SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.13561 · ACL · 2024

Cognitive Visual-Language Mapper: Advancing Multimodal Comprehension with Enhanced Visual Knowledge Alignment

Min Zhang, Xinyu Chen, Baotian Hu, Yunxin Li, Haoyuan Shi

arXiv · PDF · Open in the Atlas

Code that ran

6 of 10 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, 1 violated it and 1 has no contract verdict; 3 failures of our instrument; 4 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/2402.13561.json · badge: /api/ran/2402.13561.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
hitsz-tmg/cognitive-visual-language-mapper canonical (classifier label)
classifier basis: census
6 ran · 4 no recorded run
FunctionStatusWhere it lives
get_2d_sincos_pos_embed Ran
ran, honoured the contract we drafted
hitsz-tmg/cognitive-visual-language-mapper/Qwen/Qwen_VL/visual.py
pointer only (licence: NONE); the stored copy get_code serves, from lluosi/RDB-CL, is pointer only (licence: NONE) · get_code("77e8a3ac46f3afec")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hitsz-tmg/cognitive-visual-language-mapper 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_abs_pos Ran
ran; our contract draft was wrong, not the code
hitsz-tmg/cognitive-visual-language-mapper/Qwen/Qwen_VL/visual.py
pointer only (licence: NONE); the stored copy get_code serves, from kesenzhao/uv-cot, is pointer only (licence: NONE) · get_code("50c4398a8645438a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hitsz-tmg/cognitive-visual-language-mapper 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_eval Ran
ran; our contract draft was wrong, not the code
hitsz-tmg/cognitive-visual-language-mapper/LLaVA/llava/eval/eval_gpt_review_visual.py
pointer only (licence: NONE) · get_code("fb48214e8ea84c17")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hitsz-tmg/cognitive-visual-language-mapper 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_to_zero Ran
ran; our contract draft was wrong, not the code
hitsz-tmg/cognitive-visual-language-mapper/LLaVA/llava/model/language_model/mpt/flash_attn_triton.py
pointer only (licence: NONE); the stored copy get_code serves, from amazon-science/dualkv-flash-attn-for-rl, is pointer only (licence: NOASSERTION) · get_code("1586b639a5abd0b0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hitsz-tmg/cognitive-visual-language-mapper 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.

parse_score Ran
ran, violated the contract we drafted
hitsz-tmg/cognitive-visual-language-mapper/LLaVA/llava/eval/eval_gpt_review_visual.py
pointer only (licence: NONE) · get_code("763f6fe20bd52fbb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hitsz-tmg/cognitive-visual-language-mapper 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.

preprocess Ran
ran on a synthesized input
hitsz-tmg/cognitive-visual-language-mapper/Qwen/finetune.py
pointer only (licence: NONE) · get_code("9770697ce0d31740")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hitsz-tmg/cognitive-visual-language-mapper 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.

flash_attn_fn Not yet run
unverified (harvested, no recorded run)
hitsz-tmg/cognitive-visual-language-mapper/LLaVA/llava/model/language_model/mpt/attention.py
pointer only (licence: NONE) · get_code("69a085d27f83db2a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hitsz-tmg/cognitive-visual-language-mapper 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.

get_2d_sincos_pos_embed_from_grid Not yet run
unverified (harvested, no recorded run)
hitsz-tmg/cognitive-visual-language-mapper/Qwen/Qwen_VL/visual.py
pointer only (licence: NONE); the stored copy get_code serves, from Zhangwenyao1/DreamVLA, is pointer only (licence: NONE) · get_code("2884deadbb637c3e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hitsz-tmg/cognitive-visual-language-mapper 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.

scaled_multihead_dot_product_attention Not yet run
unverified (harvested, no recorded run)
hitsz-tmg/cognitive-visual-language-mapper/LLaVA/llava/model/language_model/mpt/attention.py
pointer only (licence: NONE); the stored copy get_code serves, from kensho-technologies/timtc_vocabs_models, is pointer only (licence: NOASSERTION) · get_code("cd623891235b1d02")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hitsz-tmg/cognitive-visual-language-mapper 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.

triton_flash_attn_fn Not yet run
unverified (harvested, no recorded run)
hitsz-tmg/cognitive-visual-language-mapper/LLaVA/llava/model/language_model/mpt/attention.py
pointer only (licence: NONE) · get_code("a27f1a3818430d86")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hitsz-tmg/cognitive-visual-language-mapper 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 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 9 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 7 the same month, 8 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
get_2d_sincos_pos_embed_from_grid 190 other papers
65 dated earlier, 8 the same month, 116 later, 1 same year, order not determinable · 65 only as an assembly brick
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
2105.12723 (2021-05)
Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding
2111.06377 (2021-11)
Masked Autoencoders Are Scalable Vision Learners
and 187 more not named here
get_2d_sincos_pos_embed 95 other papers
46 dated earlier, 3 the same month, 45 later, 1 same year, order not determinable · 33 only as an assembly brick
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
2105.12723 (2021-05)
Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding
2111.06377 (2021-11)
Masked Autoencoders Are Scalable Vision Learners
and 92 more not named here
parse_score 27 other papers
6 dated earlier, 1 the same month, 20 later
2309.09958 (2023-09)
An Empirical Study of Scaling Instruct-Tuned Large Multimodal Models
2310.03744 (2023-10)
Improved Baselines with Visual Instruction Tuning
2312.03818 (2023-12)
Alpha-CLIP: A CLIP Model Focusing on Wherever You Want
and 24 more not named here
init_to_zero 12 other papers
4 dated earlier, 2 the same month, 6 later
2304.11277 (2023-04)
PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel
2309.06180 (2023-09)
Efficient Memory Management for Large Language Model Serving with PagedAttention
2310.05869 (2023-10)
HyperAttention: Long-context Attention in Near-Linear Time
and 9 more not named here
get_abs_pos 8 other papers
1 dated earlier, 7 later
2311.16922 (2023-11)
Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding
2405.17220 (2024-05)
RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness
2405.19298 (2024-05)
Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare
and 5 more not named here
get_eval 3 other papers
3 later
2403.16999 (2024-03)
Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning
2403.18252 (2024-03)
Beyond Embeddings: The Promise of Visual Table in Visual Reasoning
2503.15621 (2025-03)
LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuning
flash_attn_fn 2 other papers
1 the same month, 1 later
2402.18376 (2024-02)
Tokenization Is More Than Compression
2403.09054 (2024-03)
Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference
triton_flash_attn_fn 2 other papers
1 the same month, 1 later
2402.18376 (2024-02)
Tokenization Is More Than Compression
2403.09054 (2024-03)
Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference
scaled_multihead_dot_product_attention 1 other paper
1 the same month
2402.18376 (2024-02)
Tokenization Is More Than Compression

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

Evaluating and Rethinking the current landscape of Large Multimodal Models (LMMs), we observe that widely-used visual-language projection approaches (e.g., Q-former or MLP) focus on the alignment of image-text descriptions yet ignore the visual knowledgedimension alignment, i.e., connecting visuals to their relevant knowledge. Visual knowledge plays a significant role in analyzing, inferring, and interpreting information from visuals, helping improve the accuracy of answers to knowledge-based visual questions. In this paper, we mainly explore improving LMMs with visual-language knowledge alignment, especially aimed at challenging knowledge-based visual question answering (VQA). To this end, we present a Cognitive Visual-Language Mapper (CVLM), which contains a pretrained Visual Knowledge Aligner (VKA) and a Finegrained Knowledge Adapter (FKA) used in the multimodal instruction tuning stage. Specifically, we design the VKA based on the interaction between a small language model and a visual encoder, training it on collected imageknowledge pairs to achieve visual knowledge acquisition and projection. FKA is employed to distill the fine-grained visual knowledge of an image and inject it into Large Language Models (LLMs). We conduct extensive experiments on knowledge-based VQA benchmarks and experimental results show that CVLM significantly improves the performance of LMMs on knowledge-based VQA (average gain by 5.0%). Ablation studies also verify the effectiveness of VKA and FKA, respectively. 1

For agents

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

get_harvested_code_for_paper("2402.13561")
get_code_for_paper("2402.13561")
have("2402.13561")

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

curl https://syntology.ai/api/ran/2402.13561.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.13561.svg)](https://syntology.ai/paper/2402.13561)

Connect an agent — have() is free.