Papers › Bootstrapping Vision-Language Learning with Decoupled Language Pre-training

Bootstrapping Vision-Language Learning with Decoupled Language Pre-training

13 Jul 2023NeurIPS 2023 11arXiv:2307.07063archive 2025-07-28

Yiren Jian, Chongyang Gao, Soroush Vosoughi

We present a novel methodology aimed at optimizing the application of frozen large language models (LLMs) for resource-intensive vision-language (VL) pre-training. The current paradigm uses visual features as prompts to guide language models, with a focus on determining the most relevant visual features for corresponding text. Our approach diverges by concentrating on the language component, specifically identifying the optimal prompts to align with visual features. We introduce the Prompt-Transformer (P-Former), a model that predicts these ideal prompts, which is trained exclusively on linguistic data, bypassing the need for image-text pairings. This strategy subtly bifurcates the end-to-end VL training process into an additional, separate stage. Our experiments reveal that our framework significantly enhances the performance of a robust image-to-text baseline (BLIP-2), and effectively narrows the performance gap between models trained with either 4M or 129M image-text pairs. Importantly, our framework is modality-agnostic and flexible in terms of architectural design, as validated by its successful application in a video learning task using varied base modules. The code will be made available at https://github.com/yiren-jian/BLIText.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2307.07063")

Code

Syntology Ran 7 of 9 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 7 ran with no contract checked.

By repository: official repository: 9 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

yiren-jian/blitext officialmentioned in papermentioned on GitHubpytorchBSD-3-Clause report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

9 samples harvested; 7 ran; 0 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

7ran
2unverified

Licence: 0 of the 9 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from yiren-jian/BLIText. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

generate_caption yiren-jian/BLIText/app/caption.py official repository ran BSD-3-Clause (permissive) · 56f02812d66a0d11 · report
get_concat_v yiren-jian/BLIText/app/dataset_browser.py official repository ran BSD-3-Clause (permissive) · 92f2e16ee0d3a24d · report
read_img yiren-jian/BLIText/app/calculate_coco_features.py official repository ran BSD-3-Clause (permissive) · 13a43a7d815937e6 · report
resize_img yiren-jian/BLIText/app/utils.py official repository ran BSD-3-Clause (permissive) · 926bb38f979a61ef · report
resize_img_w yiren-jian/BLIText/app/dataset_browser.py official repository ran BSD-3-Clause (permissive) · f809f2ecf34c1c99 · report
sample_dataset yiren-jian/BLIText/app/dataset_browser.py official repository ran BSD-3-Clause (permissive) · 3d4bbb5ca53fd24a · report
tile yiren-jian/BLIText/lavis/models/base_model.py official repository ran fingerprinted BSD-3-Clause (permissive) · cb33571427334815 · report
all_gather_with_grad yiren-jian/BLIText/lavis/models/base_model.py official repository unverified BSD-3-Clause (permissive) · 0ec9fc2025c16f65 · report
compute_gradcam_batch yiren-jian/BLIText/app/multimodal_search.py official repository unverified BSD-3-Clause (permissive) · 3e12ea8c09674aa8 · report

Tasks

Image to text

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ALIGNBASEFocus

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections