Papers › PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts

PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts

24 May 2023arXiv:2305.14839archive 2025-07-28

Yunshui Li, Binyuan Hui, Zhichao Yin, Min Yang, Fei Huang, Yongbin Li

Perceiving multi-modal information and fulfilling dialogues with humans is a long-term goal of artificial intelligence. Pre-training is commonly regarded as an effective approach for multi-modal dialogue. However, due to the limited availability of multi-modal dialogue data, there is still scarce research on multi-modal dialogue pre-training. Yet another intriguing challenge emerges from the encompassing nature of multi-modal dialogue, which involves various modalities and tasks. Moreover, new forms of tasks may arise at unpredictable points in the future. Hence, it is essential for designed multi-modal dialogue models to possess sufficient flexibility to adapt to such scenarios. This paper proposes PaCE, a unified, structured, compositional multi-modal dialogue pre-training framework. It utilizes a combination of several fundamental experts to accommodate multiple dialogue-related tasks and can be pre-trained using limited dialogue and extensive non-dialogue multi-modal data. Furthermore, we propose a progressive training method where old experts from the past can assist new experts, facilitating the expansion of their capabilities. Experimental results demonstrate that PaCE achieves state-of-the-art results on eight multi-modal dialog benchmarks.

PaperPDFCodeCode Syntology ranMethod as code

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 1 code sample harvested from 1 repository linked to this paper: 0 ran · 1 unverified.

By repository: official repository: 1 sample from 1 repository, 0 ran (0 with no instrument failure; 0 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.

AlibabaResearch/DAMO-ConvAI officialpytorchSyntology: 1 sample, 0 ran · 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

1 sample harvested: 0 ran · 1 unverified. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1unverified

Licence: 0 of the 1 sample 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 AlibabaResearch/DAMO-ConvAI. “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 “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.

AlibabaResearch/DAMO-ConvAI official repository 1 sample, 0 ran · 1 unverified
TransformerSS pace/pace/modules/pace_module.py unverified MIT (permissive) · 94634ba582cc19b4 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for PaCE (graph method: PaCE). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

  1. TransformerSS entry · level 0 · unverified · 94634ba582cc19b4

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2305.14839") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Dialogue State TrackingImage RetrievalMultimodal Intent RecognitionResponse GenerationText RetrievalVisual Dialog

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Dialogue State Tracking MMConv PaCE Categorical Accuracy 92.2 #1 of 2 Archive leaderboard report
Dialogue State Tracking MMConv PaCE Non-Categorical Accuracy 43.4 #1 of 2 Archive leaderboard report
Dialogue State Tracking MMConv PaCE Overall 39.2 #1 of 2 Archive leaderboard report
Dialogue State Tracking SIMMC2.0 PaCE Act F1 97.1 #1 of 5 Archive leaderboard report
Dialogue State Tracking SIMMC2.0 PaCE Slot F1 87.0 #1 of 5 Archive leaderboard report
Image Retrieval PhotoChat PaCE R1 15.2 #1 of 5 Archive leaderboard report
Image Retrieval PhotoChat PaCE R@10 49.6 #1 of 5 Archive leaderboard report
Image Retrieval PhotoChat PaCE R@5 36.7 #1 of 5 Archive leaderboard report
Image Retrieval PhotoChat PaCE Sum(R@1,5,10) 101.5 #1 of 5 Archive leaderboard report
Multimodal Intent Recognition MMDialog PaCE F1 77.6 #1 of 4 Archive leaderboard report
Multimodal Intent Recognition PhotoChat PaCE F1 63.8 #1 of 6 Archive leaderboard report
Multimodal Intent Recognition PhotoChat PaCE Precision 63.3 #1 of 6 Archive leaderboard report
Multimodal Intent Recognition PhotoChat PaCE Recall 68 #1 of 6 Archive leaderboard report
Response Generation MMConv PaCE BLEU 22 #1 of 2 Archive leaderboard report
Response Generation MMConv PaCE Comb. 44.7 #1 of 2 Archive leaderboard report
Response Generation MMConv PaCE Inform 34.5 #1 of 2 Archive leaderboard report
Response Generation MMConv PaCE Success 13.9 #1 of 2 Archive leaderboard report
Response Generation SIMMC2.0 PaCE BLEU 34.1 #1 of 5 Archive leaderboard report
Text Retrieval Image-Chat PaCE R@1 51.9 #1 of 3 Archive leaderboard report
Text Retrieval Image-Chat PaCE R@5 76.8 #1 of 3 Archive leaderboard report
Text Retrieval Image-Chat PaCE Sum(R@1,5) 128.7 #1 of 3 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