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 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="2404.10501")

Code

Syntology Ran 9 of 11 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · violated contract; 4 ran · our draft was wrong; 3 ran with no contract checked.

By repository: official repository: 11 samples from 1 repository, 9 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Kevinz-code/SeVa officialmentioned in papermentioned on GitHubpytorchGPL-3.0 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; 9 ran; 1 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.

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

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. “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.

convert_dict_to_tensor Kevinz-code/SeVa/seva/pope_eval.py official repository ran GPL-3.0 (copyleft) · pointer only · 03a90df0ec7b6c4f · report
eval_all Kevinz-code/SeVa/seva/pope_calculate.py official repository ran GPL-3.0 (copyleft) · pointer only · 2edb1a40e640ff20 · report
expand2square Kevinz-code/SeVa/seva/llava/mm_utils.py official repository ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · 592b3c1a88f93d7c · report
find_all_linear_names Kevinz-code/SeVa/seva/train_dpo_ours.py official repository ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · c774723322f1f9c6 · report
get_chunk Kevinz-code/SeVa/seva/llava/eval/model_vqa.py official repository ran · our draft was wrong fingerprinted GPL-3.0 (copyleft) · pointer only · 42a46570620cd9fa · report
is_none Kevinz-code/SeVa/seva/llava/eval/model_vqa_mmbench.py official repository ran · violated contract GPL-3.0 (copyleft) · pointer only · bae18947b56f2be1 · report
load_image Kevinz-code/SeVa/seva/llava/eval/model_vqa_qbench.py official repository ran · honoured contract GPL-3.0 (copyleft) · pointer only · 9b3c1cb391672ccb · report
load_image_from_base64 Kevinz-code/SeVa/seva/llava/mm_utils.py official repository ran GPL-3.0 (copyleft) · pointer only · c3ee9d07c900dd55 · report
split_list Kevinz-code/SeVa/seva/llava/eval/model_vqa.py official repository ran · our draft was wrong fingerprinted GPL-3.0 (copyleft) · pointer only · 076c252c52cbb161 · report
maybe_zero_3 Kevinz-code/SeVa/seva/train_dpo_ours.py official repository unverified GPL-3.0 (copyleft) · pointer only · 616ffbdc154ed2d8 · report
process_images Kevinz-code/SeVa/seva/llava/mm_utils.py official repository unverified GPL-3.0 (copyleft) · pointer only · 344dff4791fd1381 · 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