PulseAugur
EN
LIVE 09:46:06

vLLM's Semantic Router team releases d3-ultra multimodal model

By PulseAugur Editorial · [1 sources] ·

The Semantic Router team at vLLM has introduced d3-ultra, a 27 billion parameter open multimodal decision model. This model is designed to process text, images, or video and output probabilities for various answers, enabling it to handle tasks like routing, classification, and visual grounding without generating text. D3-ultra achieved a score of 87.2 on the SR-Text test, surpassing GLiDE V1.2's score of 85.1. AI

IMPACT This multimodal model could streamline AI agent workflows by integrating routing, classification, and visual grounding into a single decision-making process.

RANK_REASON Release of a new open-source multimodal model with benchmark results. [lever_c_demoted from research: ic=1 ai=1.0]

Read on Mastodon — sigmoid.social →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

vLLM's Semantic Router team releases d3-ultra multimodal model

How we ranked this

Signal score
12 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Release of a new open-source multimodal model with benchmark results. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. Mastodon — sigmoid.social TIER_1 English(EN) · [email protected] ·

    vLLM's Semantic Router team has released d3-ultra, a 27B open multimodal decision model under Apache 2.0. It writes no text: it reads text, images or video once

    vLLM's Semantic Router team has released d3-ultra, a 27B open multimodal decision model under Apache 2.0. It writes no text: it reads text, images or video once and returns a probability for every answer, so one call covers routing, classification and visual grounding. It scored …

    LINKS marktechpost.com/…/vllm-semantic-router-d…

RELATED ENTITIES

RELATED TOPICS