vLLM Releases d3-ultra: 27B Open Multimodal Model
vLLM released d3-ultra, a 27B open-weight multimodal decision model. It processes text, images, and video in one pass, scoring 87.2 on internal tests.
Summarized by AI from one outlet
Source
- MarkTechPostRead original ↗
Latest
- Open source
M3E Canvas: Browser-based Material 3 UI Design Tool
GIGAZINE reports on M3E Canvas, an open-source tool allowing developers to assemble Material 3 Expressive components in a browser. It enables testing interactions via clicks and directly converts the design into prompts for AI coding without needing other environments.
- Open source
Microsoft releases TokenEconomizer plugin to cut costs
Microsoft Research and UC Berkeley released TokenEconomizer, an open-source plugin that reduces coding agent costs by 18.4% to 30.9% on SWE-Bench. It achieves this by learning from past sessions without modifying the agent architecture.
- Open source
Xiaomi open-sources 0.8B OCR model
Xiaomi open-sourced Xiaomi-OCR-0, a lightweight document understanding model with 0.8B parameters. Based on the Qwen3.5 foundation, it covers document parsing, key information extraction, and OCR visual question answering, with weights and code available on Hugging Face.
All news → · All rights belong to the original creators