Google DeepMind Proposes Visual Prompting as Alternative to Text Prompts
Google DeepMind researchers have introduced a new approach to prompt engineering that relies on visual cues rather than written instructions, claiming it delivers better results for guiding AI models. The method aims to bridge natural language processing with visual intelligence, pointing to a shift in how users interact with multimodal AI systems. Source: eu.36kr.com
Importance:Newsmultimodal AI breakthroughs
Multimodal AI breakthroughs and Anduril's $100B funding round make headlines
A wave of multimodal AI progress coincides with Anduril reportedly raising $100 billion in new funding. The roundup also touches on politicians delivering AI-written speeches and other fresh AI developments shaking up the industry. Source: theneurondaily.com
Importance:LaunchVideo Generation Models
Black Forest Labs unveils FLUX 3, a multimodal model for video, audio and robot actions
Black Forest Labs has launched FLUX 3, a multimodal flow model capable of generating 20-second videos complete with native audio and action sequences. The model extends beyond image generation into video, sound, and robotics-related predictions. Source: marktechpost.com
Importance:Launchmulti-modal model
FLUX 3 Arrives: Black Forest Labs Goes Multimodal With Video and Audio
Black Forest Labs released FLUX 3 on July 23, 2026, expanding beyond image generation into video, audio, and physical AI within a single model. The German company behind the FLUX image models is positioning this as a major step toward unified multimodal AI. Source: techtimes.com
Importance:Newsindustry updates
AI Week in Review: New Models From Anthropic, Google, OpenAI, and More
This week's roundup covers a wave of new AI model releases, including Claude Opus 5, Gemini 3.6 Flash, Gemini 3.5 Flash-Lite, Qwen 3.8 Max, OpenAI Presence, FLUX 3, and MAI Image 2.5 Pro. The lineup reflects continued rapid competition among major AI labs across text, image, and multimodal models. Source: patmcguinness.substack.com
Importance:NewsAPI integration
Building Multimodal Apps With a Single API: The GPTProto Approach
Many AI apps end up juggling separate vendors for text, image, and video generation, which often happens gradually as products grow. GPTProto offers a unified API platform that lets developers integrate multiple AI model types into one application without managing several providers separately. Source: concept-phones.com
Importance:Launchmultimodal AI models
Black Forest Labs debuts FLUX 3, a multimodal model for images and short AI videos with sound
Black Forest Labs has released FLUX 3, expanding its FLUX family beyond still images to also generate up to 20-second videos with audio. The model is launching in a limited rollout rather than a full public release. Source: venturebeat.com
Importance:NewsVideo generation models
Flux 3 can generate 20-second videos with native audio, a first for the company
Black Forest Labs released Flux 3, a multimodal foundation model trained on images, video, and audio, capable of producing video clips with synchronized sound built in from the start. Source: the-decoder.com
Importance:NewsVideo generation models
Black Forest Labs launches multimodal FLUX 3 with video and robotics features
The startup, valued at $3.25 billion, unveiled a new model that produces 20-second videos with matching audio and is already being tested on Audi's production lines. Source: cryptobriefing.com
Importance:OpinionAI Data Licensing
Shutterstock: Is Multimodal AI a Data Licensing Problem?
AI Magazine speaks to Dan Mandell, SVP of Data Licensing & AI Services at Shutterstock, about multimodal data, creativity and Shutterstock's efforts in AI. Source: aimagazine.com
Importance:Researchmultimodal models
Bootstrapped Multimodal LLM Learns Medical Knowledge for Automatic EGD Diagnosis and Reporting
A new study in Nature Communications reports a multimodal large language model (MLLM) designed to assist with esophagogastroduodenoscopy (EGD)—a procedure... Source: bioengineer.org
Importance:ResearchEmbodied AI
Xiaomi introduces Xiaomi-Robotics-U0 for embodied AI and robot generation
Xiaomi on Wednesday unveiled Xiaomi-Robotics-U0, a 38-billion-parameter multimodal autoregressive foundation model for embodied AI. The company said the. Source: technode.com
Importance:NewsAurora Mobile enterprise AI
Aurora Mobile's GPTBots.ai Expands Enterprise Multimodal AI Capabilities with Modellix-Powered Image and Video Generation Tools
SINGAPORE, July 15, 2026 (GLOBE NEWSWIRE) -- Aurora Mobile Limited (NASDAQ: JG) (“Aurora Mobile” or the “Company”), a leading provider of custom... Source: markets.businessinsider.com
Importance:Researchquantum-llm-multimodal
MIT and IBM Project Quantum Unity Operators into Language Model Latent Spaces for Multimodal Circuit Synthesis
Researchers from the MIT-IBM Computing Research Lab and IBM Quantum have developed a multimodal alignment framework that maps quantum unitary operators... Source: quantumcomputingreport.com
Importance:Researchprecision nutrition
Applying Artificial Intelligence and machine learning in precision nutrition
A key feature of the Precision Nutrition and Health approach is the ability to tailor interventions to individual variability using multimodal data from... Source: nature.com
Importance:Launch
Naver turns 27 years of search into AI with tailored LLM, SLMs, multimodal - CHOSUNBIZ
Naver turns 27 years of search into AI with tailored LLM, SLMs, multimodal The search infrastructure and know-how accumulated over the past 27 years, Source: biz.chosun.com
Importance:Newsmultimodal AI models
5 Open Source Omni AI Models That Handle Text, Images, Audio, and Video
Take a practical look at multimodal, any-to-any systems for vision-language reasoning, speech interaction, document intelligence, real-time assistants,... Source: KDnuggets
Importance:NewsGemini video generation benchmark
Gemini Omni Flash claims top spot in Video Arena rankings
Google's Gemini Omni Flash ranks first in Video Arena for text-to-video and image-to-video, surpassing competitors with multimodal editing capabilities. Source: cryptobriefing.com
Importance:Researchmultimodal LLM applications
Fine-tuned multimodal large language model for autonomous state cognition system of shape-recognition 6-bar tensegrity integrated with flexible sensors
Conducting dynamic exploration in complex and unpredictable environments, particularly in space exploration, reveals the great potential of systems based on... Source: nature.com
Importance:Launchmultimodal autonomous agent
Qwen3.7-Plus is Alibaba's bid to turn multimodal AI into a full-blown autonomous agent
Alibaba's Qwen team has released Qwen3.7-Plus, a multimodal agent model that combines visual perception, GUI operation, and coding in a single agent loop. Source: the-decoder.com