Papers › MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models

MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models

23 Oct 2024arXiv:2410.17637archive 2025-07-28

Ziyu Liu, Yuhang Zang, Xiaoyi Dong, Pan Zhang, Yuhang Cao, Haodong Duan, Conghui He, Yuanjun Xiong, Dahua Lin, Jiaqi Wang

Visual preference alignment involves training Large Vision-Language Models (LVLMs) to predict human preferences between visual inputs. This is typically achieved by using labeled datasets of chosen/rejected pairs and employing optimization algorithms like direct preference optimization (DPO). Existing visual alignment methods, primarily designed for single-image scenarios, struggle to effectively handle the complexity of multi-image tasks due to the scarcity of diverse training data and the high cost of annotating chosen/rejected pairs. We present Multi-Image Augmented Direct Preference Optimization (MIA-DPO), a visual preference alignment approach that effectively handles multi-image inputs. MIA-DPO mitigates the scarcity of diverse multi-image training data by extending single-image data with unrelated images arranged in grid collages or pic-in-pic formats, significantly reducing the costs associated with multi-image data annotations. Our observation reveals that attention values of LVLMs vary considerably across different images. We use attention values to identify and filter out rejected responses the model may have mistakenly focused on. Our attention-aware selection for constructing the chosen/rejected pairs without relying on (i) human annotation, (ii) extra data, and (iii) external models or APIs. MIA-DPO is compatible with various architectures and outperforms existing methods on five multi-image benchmarks, achieving an average performance boost of 3.0% on LLaVA-v1.5 and 4.3% on the recent InternLM-XC2.5. Moreover, MIA-DPO has a minimal effect on the model's ability to understand single images.

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: 9 from 1 repository linked to this paper, 2 identical to code harvested from another paper's repository. Across all 11: 10 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 8 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 9 samples from 1 repository, 8 ran (1 with no instrument failure; 7 where Syntology's instrument failed); 2 identical to code first harvested elsewhere. 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 2026-09-25 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 4 of the 10 samples that ran have no recorded date.

liuziyu77/mia-dpo officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 9 samples, 8 ran (7 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; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 8 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.

1ran · honoured contract
1ran · violated contract
8ran · our draft was wrong
1unverified

Licence: 2 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 liuziyu77/mia-dpo. 2 samples are listed last, in a group without a repository. “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.

liuziyu77/mia-dpo official repository 9 samples, 8 ran (7 instrument-failed) · 1 unverified
convert_to_scalar in 24 papers LLaVA-Hound-DPO/llava_hound_dpo/trl/core.py ran · our draft was wrong Apache-2.0 (permissive) · c32b636f13ed9ee5 · report fixture: signature stats:dict/0/? · returned dict · level recorded 2026-09-25
get_chunk in 197 papers LLaVA-Hound-DPO/chatuniv/ChatUniVi/eval/model_coco_vqa.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 42a46570620cd9fa · report fixture: signature lst:list/1/int, n:int/0/int, k:int/0/int · returned list · level recorded, date not recorded
get_seq_frames in 6 papers LLaVA-Hound-DPO/chatuniv/chatuniv_utils.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · fccf1d01505895d0 · report fixture: signature total_num_frames:int/0/int, desired_num_frames:int/0/int · returned list · level recorded 2026-09-26
remove_special_tokens in 10 papers LLaVA-Hound-DPO/chatuniv/chatuniv_utils.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 663e3b5a6740fa0d · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-26
remove_special_tokens in 10 papers LLaVA-Hound-DPO/llama_vid/llamavid_utils.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 160197f694bfebd8 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-26
resize_image in 74 papers LLaVA-Hound-DPO/chatuniv/chatuniv_utils.py ran · our draft was wrong Apache-2.0 (permissive) · c3f1f1085b84693b · report fixture: signature input_image:Image/0/?, target_size:tuple/1/int · returned Image · level recorded 2026-09-26
split_list in 223 papers LLaVA-Hound-DPO/chatuniv/ChatUniVi/eval/model_coco_vqa.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 076c252c52cbb161 · report fixture: signature lst:list/1/int, n:int/0/int · returned list · level recorded, date not recorded
stack_dicts in 11 papers LLaVA-Hound-DPO/llava_hound_dpo/trl/core.py ran · our draft was wrong Apache-2.0 (permissive) · 085e70e0bd6e492d · report fixture: signature stats_dicts:list/1/dict · returned dict · level recorded 2026-09-26
flatten_dict in 72 papers LLaVA-Hound-DPO/llava_hound_dpo/trl/core.py unverified Apache-2.0 (permissive) · a51ae45a1f6c0b5b · report
Repository not located 2 samples, 2 ran (1 instrument-failed) · 0 unverified
2 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
get_id_from_path in 5 papers repository not located ran · our draft was wrong fingerprinted licence of this copy not recorded · f1a2ea781d07a5ee · report fixture: signature path:str/0/str · returned str · level recorded, date not recorded
remove_special_tokens in 10 papers repository not located ran · violated contract fingerprinted licence of this copy not recorded · 4354061aab23f5b9 · report fixture: signature text:str/0/str · returned str · level recorded, date not recorded

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionSoftmax

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