Firehose

Filtered to tagged “multimodal models” · clear filters

All PeopleCompaniesPapersPodcastsHacker News

Browse by tag

22 JUL 2026 · Paper

This paper introduces a new environment called Trace, which allows vision-language models to reason across multiple domains and tasks, using a taxonomy-guided approach. Practitioners might care because this work could lead to more generalizable and transferable AI models.

16 JUL 2026 · Swyx

Thinky's Inkling is a 975B-params, 41B-active-params multimodal Mixture-of-Experts transformer model, the first open-weights foundation model from the company, supporting text, images, and audio inputs with a context window of up to 1M tokens, pre-trained on 45 trillion tokens of text, images, audio, and video. Inkling is licensed under Apache 2.0 and has been released with full weights available, along with immediate support on Tinker platform and Hugging Face. The model is designed for practical use and customization, with controllable reasoning effort levels and a focus on efficient and controllable thinking. AI summary