Papers › PaLI-X: On Scaling up a Multilingual Vision and Language Model

PaLI-X: On Scaling up a Multilingual Vision and Language Model

29 May 2023arXiv:2305.18565archive 2025-07-28

Xi Chen, Josip Djolonga, Piotr Padlewski, Basil Mustafa, Soravit Changpinyo, Jialin Wu, Carlos Riquelme Ruiz, Sebastian Goodman, Xiao Wang, Yi Tay, Siamak Shakeri, Mostafa Dehghani, Daniel Salz, Mario Lucic, Michael Tschannen, Arsha Nagrani, Hexiang Hu, Mandar Joshi, Bo Pang, Ceslee Montgomery, Paulina Pietrzyk, Marvin Ritter, AJ Piergiovanni, Matthias Minderer, Filip Pavetic, Austin Waters, Gang Li, Ibrahim Alabdulmohsin, Lucas Beyer, Julien Amelot, Kenton Lee, Andreas Peter Steiner, Yang Li, Daniel Keysers, Anurag Arnab, Yuanzhong Xu, Keran Rong, Alexander Kolesnikov, Mojtaba Seyedhosseini, Anelia Angelova, Xiaohua Zhai, Neil Houlsby, Radu Soricut

We present the training recipe and results of scaling up PaLI-X, a multilingual vision and language model, both in terms of size of the components and the breadth of its training task mixture. Our model achieves new levels of performance on a wide-range of varied and complex tasks, including multiple image-based captioning and question-answering tasks, image-based document understanding and few-shot (in-context) learning, as well as object detection, video question answering, and video captioning. PaLI-X advances the state-of-the-art on most vision-and-language benchmarks considered (25+ of them). Finally, we observe emerging capabilities, such as complex counting and multilingual object detection, tasks that are not explicitly in the training mix.

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="2305.18565")

Code

Syntology Ran 6 of 7 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · honoured contract; 4 ran · violated contract; 1 ran · our draft was wrong.

By repository: community (archive-listed): 7 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

doc-doc/NExT-OE mentioned on GitHubpytorch report
kyegomez/PALI pytorchMIT 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

7 samples harvested; 6 ran; 1 honoured the contract we drafted; 1 has 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
4ran · violated contract
1ran · our draft was wrong
1unverified

Licence: 0 of the 7 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 kyegomez/PALI. “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.

cast_tuple kyegomez/PALI/pali/transformer.py community (archive-listed) ran · violated contract fingerprinted MIT (permissive) · 1f7c550e65142ef8 · report
compact kyegomez/PALI/pali/attend.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · 4a06bf1ac86f840a · report
default kyegomez/PALI/pali/attend.py community (archive-listed) ran · violated contract fingerprinted MIT (permissive) · 60fff7c3c400d7ff · report
default kyegomez/PALI/pali/transformer.py community (archive-listed) ran · violated contract MIT (permissive) · 424012cb37b31172 · report
eval_decorator kyegomez/PALI/pali/autoregressive_wrapper.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 5444a7d75d38878d · report
exists kyegomez/PALI/pali/attend.py community (archive-listed) ran · violated contract MIT (permissive) · aa5486a3650902d8 · report
top_p kyegomez/PALI/pali/autoregressive_wrapper.py community (archive-listed) unverified MIT (permissive) · 864f3eecd1ea0a36 · report

Tasks

Chart Question AnsweringFine-Grained Image RecognitionIn-Context LearningLanguage ModelingLanguage ModellingObjectObject DetectionQuestion AnsweringTemporal/Casual QAVideo CaptioningVideo Question AnsweringVisual Question Answering (VQA)document understandingobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Chart Question Answering ChartQA PaLI-X (Single-task FT w/ OCR) 1:1 Accuracy 72.3 #10 of 27 Archive leaderboard report
Chart Question Answering ChartQA PaLI-X (Single-task FT) 1:1 Accuracy 70.9 #11 of 27 Archive leaderboard report
Chart Question Answering ChartQA PaLI-X (Multi-task FT) 1:1 Accuracy 70.6 #12 of 27 Archive leaderboard report
Fine-Grained Image Recognition OVEN PaLI-X Accuracy 23.1 #1 of 5 Archive leaderboard report
Temporal/Casual QA NExT-QA PaLI-X WUPS 38.3 #1 of 8 Archive leaderboard report
Visual Question Answering (VQA) DocVQA test PaLI-X (Single-task FT w/ OCR) ANLS 0.868 #14 of 33 Archive leaderboard report
Visual Question Answering (VQA) DocVQA test PaLI-X (Multi-task FT) ANLS 0.809 #21 of 33 Archive leaderboard report
Visual Question Answering (VQA) DocVQA test PaLI-X (Single-task FT) ANLS 0.80 #23 of 33 Archive leaderboard report
Visual Question Answering (VQA) InfoSeek PaLI-X Accuracy 24 #2 of 7 Archive leaderboard report
Visual Question Answering (VQA) InfographicVQA PaLI-X (Single-task FT w/ OCR) ANLS 54.8 #10 of 21 Archive leaderboard report
Visual Question Answering (VQA) InfographicVQA PaLI-X (Multi-task FT) ANLS 50.7 #12 of 21 Archive leaderboard report
Visual Question Answering (VQA) InfographicVQA PaLI-X (Single-task FT) ANLS 49.2 #13 of 21 Archive leaderboard report
Visual Question Answering (VQA) OK-VQA PaLI-X (Single-task FT) Accuracy 66.1 #3 of 37 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