AI Briefing#multimodal
The latest AI and developer news about #multimodal, with the original source and a short summary.
The latest AI and developer news about #multimodal, with the original source and a short summary.
An experimental vision-capable version of DeepSeek V4 Flash has been released on Vercel AI Gateway.
Tencent has released an ultra-lightweight, high-performance multilingual Visual Document Retrieval (VDR) model based on Qwen3.5-4B.
A provenance error was observed in ChatGPT's audio preprocessing pipeline, where generated text is treated as direct user input.
dots-studio has released a 280B MoE multimodal model supporting a 512K context window.
CohereLabs released a 2.4B vision-language model under the Apache 2.0 license.
Liquid AI released a 3.1B vision-language model with enhanced screen understanding and tool use.
Meta has open-sourced Muse Glimmer, a 30-billion-parameter model for local agents.
JoyAI has released a 16B model that causally edits live video streams in real time based on natural language instructions.
Muse Glimmer has been released as a 30B open-weight agent model capable of running on 24GB-class memory.
Meta has released Muse Glimmer, a 30B multimodal model for local agents, under the Apache 2.0 license.
ByteDance Seed has deployed SeedRealtime, a full-duplex model that processes audio and video in real time, on Doubao.
SpaceXAI has released Image 2.0, enhancing precision generation and editing capabilities.
NVIDIA has released Nemotron Parse 2.0, enhancing multilingual and chart document analysis.
Qwen-Image-3.0-Pro supports sophisticated text and image generation as well as multilingual rendering.
Thinking Machines Lab released an open-weight model one-quarter the size of Inkling.
MiniMax has released the weights for its 33B H3 model, which jointly generates video and stereo audio, but Korea is excluded from the license.
SenseNova has released a preview of U1.5 Lite, which strengthens 4K generation and precise image editing.
xAI unveiled Imagine Video 1.5, which supports voice and image references along with native 1080p.
MiniMax H3 has been added to AI Gateway, supporting 2K resolution video generation through text and multimodal inputs.
Thinking Machines' lightweight model Inkling Small has been added to AI Gateway, enabling efficient inference and coding tasks.
Amazon plans to consolidate its various Nova AI models into a single frontier model.
Moonshot AI has released Kimi K3, an open-weight multimodal model with 2.8T parameters.
GOT-OCR2.0, an end-to-end OCR model that processes complex visual information such as formulas, tables, and sheet music with a single model, has been released.
On the new ActiveVision benchmark, GPT-5.5 scored 10.6% and Claude Fable 5 scored 3.5%, while human participants achieved 96.1%.