SAVER: Selective As-Needed Vision Evidence for Multimodal Information Extraction
The article discusses a new framework called SAVER designed for multimodal information extraction in social media. It addresses the challenges of weakly related or misleading images in posts by selectively consulting visual evidence. SAVER improves performance metrics while reducing computational costs compared to traditional methods.
- ▪SAVER is a selective vision-as-needed framework for multimodal named entity recognition and relation extraction.
- ▪The framework uses a Conformal Groundability Gate to estimate visual groundability and calibrate activation thresholds.
- ▪Experiments show that SAVER consistently improves F1 scores and reduces computational costs compared to text-only and always-on multimodal baselines.
arXiv cs.AI files mainly under ai research. We currently carry 1,128 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv cs.AI |
| Canonical URL | https://arxiv.org/abs/2605.20713 |
| Publication time | Fri, 22 May 2026 00:00:00 -0400 |
| Retrieval time | 2026-05-22T04:02:00.009Z |
| Last seen | 2026-05-22T04:02:00.009Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | HtlI429MIwpq |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Computer Vision and Pattern Recognition arXiv:2605.20713 (cs) [Submitted on 20 May 2026] Title:SAVER: Selective As-Needed Vision Evidence for Multimodal Information Extraction Authors:Miaobo Hu, Shuhao Hu, Bokun Wang, Rui Chen, Xin Wang, Xiaobo Guo, Daren Zha, Jun Xiao View a PDF of the paper titled SAVER: Selective As-Needed Vision Evidence for Multimodal Information Extraction, by Miaobo Hu and 6 other authors View PDF Abstract:Multimodal IE in social media is difficult because a post may attach multiple images that are weakly related, redundant, or even misleading with respect to the text. In this setting, always-on multimodal fusion wastes computation and can amplify spurious visual cues.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
