Papers › Self-Supervised Visual Preference Alignment

Self-Supervised Visual Preference Alignment

16 Apr 2024arXiv:2404.10501archive 2025-07-28

Ke Zhu, Zheng Ge, Liang Zhao, Xiangyu Zhang

This paper makes the first attempt towards unsupervised preference alignment in Vision-Language Models (VLMs). We generate chosen and rejected responses with regard to the original and augmented image pairs, and conduct preference alignment with direct preference optimization. It is based on a core idea: properly designed augmentation to the image input will induce VLM to generate false but hard negative responses, which helps the model to learn from and produce more robust and powerful answers. The whole pipeline no longer hinges on supervision from GPT-4 or human involvement during alignment, and is highly efficient with few lines of code. With only 8k randomly sampled unsupervised data, it achieves 90% relative score to GPT-4 on complex reasoning in LLaVA-Bench, and improves LLaVA-7B/13B by 6.7%/5.6% score on complex multi-modal benchmark MM-Vet. Visualizations shows its improved ability to align with user-intentions. A series of ablations are firmly conducted to reveal the latent mechanism of the approach, which also indicates its potential towards further scaling. Code are available in https://github.com/Kevinz-code/SeVa.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 11 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 10 ran (6 with no instrument failure; 4 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 10 samples that ran have no recorded date.

Kevinz-code/SeVa officialmentioned in papermentioned on GitHubpytorchGPL-3.0Syntology: 11 samples, 10 ran (4 instrument-failed) · 1 unverified 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

11 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
1ran · violated contract
4ran · our draft was wrong
2ran
1unverified

Licence: 11 of the 11 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 Kevinz-code/SeVa. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

Kevinz-code/SeVa official repository 11 samples, 10 ran (4 instrument-failed) · 1 unverified
convert_dict_to_tensor seva/pope_eval.py ran GPL-3.0 (copyleft) · pointer only · 03a90df0ec7b6c4f · report fixture: signature results:dict/0/?, device:str/0/str · returned Tensor · level recorded 2026-09-24
eval_all seva/pope_calculate.py ran GPL-3.0 (copyleft) · pointer only · 2edb1a40e640ff20 · report fixture: signature ans_file:str/0/str, label_file:str/0/str · returned tuple · level recorded 2026-09-24
expand2square in 78 papers seva/llava/mm_utils.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · 592b3c1a88f93d7c · report fixture: signature pil_img:Image/0/?, background_color:tuple/1/int · returned Image · level recorded 2026-09-22
find_all_linear_names in 50 papers seva/train_dpo_ours.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · c774723322f1f9c6 · report fixture: signature model:callable/0/? · returned list · level recorded 2026-09-22
get_chunk in 197 papers seva/llava/eval/model_vqa.py ran · our draft was wrong fingerprinted GPL-3.0 (copyleft) · pointer only · 42a46570620cd9fa · report fixture: signature lst:list/1/int, n:int/0/int, k:int/0/int · returned list · level recorded, date not recorded
is_none in 88 papers seva/llava/eval/model_vqa_mmbench.py ran · violated contract GPL-3.0 (copyleft) · pointer only · bae18947b56f2be1 · report fixture: signature value:NoneType/0/? · returned bool · level recorded 2026-09-22
load_image in 273 papers seva/llava/eval/model_vqa_qbench.py ran · honoured contract GPL-3.0 (copyleft) · pointer only · 9b3c1cb391672ccb · report fixture: signature image_file:str/0/str · returned Image · level recorded 2026-09-22
load_image_from_base64 in 87 papers seva/llava/mm_utils.py ran · honoured contract GPL-3.0 (copyleft) · pointer only · c3ee9d07c900dd55 · report fixture: signature image:str/0/str · returned PngImageFile · level recorded 2026-09-24
process_images in 79 papers seva/llava/mm_utils.py ran · honoured contract GPL-3.0 (copyleft) · pointer only · 344dff4791fd1381 · report fixture: signature images:list/1/Image, image_processor:callable/0/?, model_cfg:MockModelConfig/0/? · returned Tensor · level recorded 2026-09-26
split_list in 223 papers seva/llava/eval/model_vqa.py ran · our draft was wrong fingerprinted GPL-3.0 (copyleft) · pointer only · 076c252c52cbb161 · report fixture: signature lst:list/1/int, n:int/0/int · returned list · level recorded, date not recorded
maybe_zero_3 in 74 papers seva/train_dpo_ours.py unverified GPL-3.0 (copyleft) · pointer only · 616ffbdc154ed2d8 · report

Tasks

Visual Question Answering

2 archive task tags without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Question Answering MM-Vet SeVa-13B GPT-4 score 41.0 #105 of 231 Archive leaderboard report
Visual Question Answering MM-Vet SeVa-7B GPT-4 score 37.2 #136 of 231 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

ALIGNAbsolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutGPT-4Label SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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