Papers › MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning

MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning

14 Oct 2023arXiv:2310.09478archive 2025-07-28

Jun Chen, Deyao Zhu, Xiaoqian Shen, Xiang Li, Zechun Liu, Pengchuan Zhang, Raghuraman Krishnamoorthi, Vikas Chandra, Yunyang Xiong, Mohamed Elhoseiny

Large language models have shown their remarkable capabilities as a general interface for various language-related applications. Motivated by this, we target to build a unified interface for completing many vision-language tasks including image description, visual question answering, and visual grounding, among others. The challenge is to use a single model for performing diverse vision-language tasks effectively with simple multi-modal instructions. Towards this objective, we introduce MiniGPT-v2, a model that can be treated as a unified interface for better handling various vision-language tasks. We propose using unique identifiers for different tasks when training the model. These identifiers enable our model to better distinguish each task instruction effortlessly and also improve the model learning efficiency for each task. After the three-stage training, the experimental results show that MiniGPT-v2 achieves strong performance on many visual question-answering and visual grounding benchmarks compared to other vision-language generalist models. Our model and codes are available at https://minigpt-v2.github.io/

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="2310.09478")

Code

Syntology Ran 3 of 3 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 2 ran · fixture could not drive it.

By repository: community (archive-listed): 2 samples from 1 repository, 2 ran; 1 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.

vision-cair/minigpt-4 mentioned on GitHubpytorchBSD-3-Clause report
zebangcheng/emotion-llama mentioned 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

3 samples harvested; 3 ran; 0 honoured the contract we drafted; 0 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 · our draft was wrong
2ran · fixture could not drive it

Licence: 1 of the 3 samples is 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 vision-cair/minigpt-4. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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.

computeIoU vision-cair/minigpt-4/demo_v2.py community (archive-listed) ran · fixture could not drive it BSD-3-Clause (permissive) · f8e4c1c5aac977d6 · report
extract_substrings vision-cair/minigpt-4/demo_v2.py community (archive-listed) ran · our draft was wrong fingerprinted BSD-3-Clause (permissive) · 5c3e6655c3b3e958 · report
is_overlapping identical code first harvested elsewhere ran · fixture could not drive it fingerprinted licence of this copy not recorded · 37438be3369e6493 · report

Tasks

Image ClassificationLanguage ModelingLanguage ModellingLarge Language ModelMulti-Task LearningNatural Language Visual GroundingQuestion AnsweringReferring Expression ComprehensionReferring expression generationVisual GroundingVisual Question Answering

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ColonINST-v1 (Seen) MiniGPT-v2 (w/ LoRA, w/o extra data) Accuray 91.49 #12 of 17 Archive leaderboard report
Image Classification ColonINST-v1 (Seen) MiniGPT-v2 (w/ LoRA, w/ extra data) Accuray 90.00 #14 of 17 Archive leaderboard report
Image Classification ColonINST-v1 (Unseen) MiniGPT-v2 (w/ LoRA, w/o extra data) Accuray 77.93 #11 of 17 Archive leaderboard report
Image Classification ColonINST-v1 (Unseen) MiniGPT-v2 (w/ LoRA, w/ extra data) Accuray 76.82 #13 of 17 Archive leaderboard report
Natural Language Visual Grounding ScreenSpot MiniGPT-v2 Accuracy (%) 5.7 #16 of 18 Archive leaderboard report
Referring expression generation ColonINST-v1 (Seen) MiniGPT-v2 (w/ LoRA, w/o extra data) Accuray 94.69 #13 of 17 Archive leaderboard report
Referring expression generation ColonINST-v1 (Seen) MiniGPT-v2 (w/ LoRA, w/ extra data) Accuray 87.65 #15 of 17 Archive leaderboard report
Referring expression generation ColonINST-v1 (Unseen) MiniGPT-v2 (w/ LoRA, w/o extra data) Accuray 72.05 #10 of 17 Archive leaderboard report
Referring expression generation ColonINST-v1 (Unseen) MiniGPT-v2 (w/ LoRA, w/ extra data) Accuray 70.23 #12 of 17 Archive leaderboard report
Visual Question Answering BenchLMM MiniGPTv2-7B GPT-3.5 score 30.1 #10 of 10 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.

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