YANAMI: A Large-Scale Multimodal Dataset and Benchmark for Multiturn Stateful Interaction
YANAMI is a multimodal dialogue dataset and benchmark for stateful interaction, where models must track, maintain, update, and visually realize evolving dialogue states across turns.
Source-based brief · Editor review not recorded · See checks and limits ↓
One primary source; other links are context, not independent corroboration.
- Primary sourceHugging Face
- Discovery linkHugging Face
- Linked in sourceView arXiv page
- Linked in sourceView PDF
The paper page is linked. Peer review and findings have not been independently checked by AINewsIQ.
Open full article view →- Original paper+45
- Fetched source page+30
- No editor link review+0
- Original non-discussion link+5
This measures the stored source trail and editorial steps. It does not certify accuracy, peer review, or independent corroboration. Popularity adds no points.
View full scoring →Read the scoring rubric →What the source says
YANAMI is a multimodal dialogue dataset and benchmark for stateful interaction, where models must track, maintain, update, and visually realize evolving dialogue states across turns. YANAMI-400K contains 400K multi-turn dialogues with over 2M images and 2.6M turns across four scenarios: Multi-Image Fusion, Image Editing, World Modeling, and Visual Reasoning. YANAMI-Bench contains 400 dialogues that jointly evaluate Dialogue State Understanding and Visual Realization. Fine-tuning BAGEL on YANAMI-400K reportedly improved image editing by 10.3%, generation by 2.0%, and stateful interaction by 13.23%. The authors report that existing unified multimodal models still struggle on YANAMI-Bench.
Claim explorer
Attribution, source and conditionsSource-stated points from the stored brief. Claim-level assessments have not been recorded.
Source claims not independently checked; the reported gains come from the authors' own BAGEL fine-tuning experiments.
This connects a source, an attributed statement and its qualifications. It does not establish that the claim is correct.
Questions worth asking
Open questions for further reportingWhat remains unconfirmed?
Source claims not independently checked; the reported gains come from the authors' own BAGEL fine-tuning experiments.
What material was available for this brief?
The recorded brief basis is fetched source page. These points are AINewsIQ paraphrases, not quotations or independent confirmations.
YANAMI-400K contains 400K multi-turn multimodal dialogues with more than 2M images and 2.6M dialogue turns.
Source: Hugging Face ↗Stored source-based brief · key point 1 · AINewsIQ paraphraseFine-tuning BAGEL on YANAMI-400K improves image editing by 10.3%, generation by 2.0%, and stateful interaction by 13.23%.
Source: Hugging Face ↗Stored source-based brief · key point 2 · AINewsIQ paraphraseYANAMI-Bench evaluates both Dialogue State Understanding and Visual Realization using 400 multi-turn dialogues.
Source: Hugging Face ↗Stored source-based brief · key point 3 · AINewsIQ paraphraseEvaluations on YANAMI-Bench indicate existing unified multimodal models still struggle to maintain and visually realize evolving dialogue states.
Source: Hugging Face ↗Stored source-based brief · key point 4 · AINewsIQ paraphraseLimits from the stored brief
Source claims not independently checked; the reported gains come from the authors' own BAGEL fine-tuning experiments.
This is a source-based abstract, not independent validation of the source's claims.
Evidence & sources
These links show where the signal came from and what the source page linked to. A linked page is context, not independent corroboration.
Related archive coverage
These relationships record a citation or topic overlap, not confirmation of the finding.
The paper page is linked. Peer review and findings have not been independently checked by AINewsIQ.
Timeline & updates
- Signal dated by source or discovery feed
This timestamp places the signal in the radar. It may be the discovery post date rather than the primary page's first publication date.
- Shared brief stored
AINewsIQ prepared one abstract from fetched source page.
Brief history · 1 retained version
These are changes to AINewsIQ’s own publication. Earlier history is unavailable unless recorded here. Complete retained versions are available to the editor.
- Version 1 · published
Source-based brief stored or updated. This does not establish that the publisher changed its page.
Automated record
Source observations · 1 recent captures
A changed capture means the extracted text differed. It can reflect page furniture or extraction changes; it does not establish a substantive correction. Source captures remain private.
Retained capture; no earlier comparison available.
New engagement snapshots do not mean the source itself changed. Source observations and AINewsIQ brief revisions are separate records.
Why this may matter
Most multimodal datasets and benchmarks are single-turn or allow turns to be solved independently. A benchmark that requires tracking state across turns and checking visual outputs against that state targets a gap in how unified multimodal models are trained and evaluated.
Limits and open questions
Source claims not independently checked; the reported gains come from the authors' own BAGEL fine-tuning experiments.
Organization-specific financial, security, and operational effects require the organization's own context and review.
Join the discussion
Have a different perspective or a question about the evidence? Discussion is free with a verified email account. Every comment is reviewed before publication.
No published comments yet.
New commenters: 2 submissions per 24 hours, at least 5 minutes apart, until 3 are approved. Discussion guidelines and moderation →