#Multimodal

AIApple researchers introduced Normalizing Trajectory Models (NTM), which model each reverse diffusion step as a conditional normalizing flow trained with exact likelihood. The model matches or outperforms strong image generation baselines on text-to-image benchmarks in just four sampling steps while retaining exact likelihood over the generative trajectory.

AIBen Affleck described how visual effects work has long used machine learning, including convolutional neural networks that analyze image tensors to detect edges and features. He said these patterns help separate subjects from green screens and insert new backgrounds, and he called transformers the more advanced successors to those earlier methods.

AIOpenAI announced on X that GPT-6 and Intelligent UI are now rolling out to all ChatGPT users, after GPT-6 Astra, Sol and Luna were previously limited to ChatGPT Work and Codex. Intelligent UI lets GPT-6 combine text, images and interactive elements such as charts, clickable buttons and forms, with a mahjong learning example shown.

AIOpenAI says ChatGPT now offers Intelligent UI, which returns answers with fully interactive user interfaces. GPT-6 is rolling out in ChatGPT, powered by GPT-6 Sol for Plus, Pro, Business, and Enterprise tiers and GPT-6 Luna for Free and Go tiers. The rollout begins globally today in the Chat tab for paid tiers, with Free and Go tiers following tomorrow.

AIPerplexity's open-weights multimodal decision model, Decider v1.1, is now available on OpenRouter. It accepts text, JSON, or images and returns typed answers with probabilities, priced at $0.02 per million input tokens with free output. Perplexity says it scores highest on Hugging Face's new Decision Index 0.3 benchmark and costs half as much as v1.

AIfal has launched Vidu Q4, offering image-to-video generation from a single first frame with native audio. Reference-to-video supports up to 12 reference images and 3 voice clips for consistent characters and voices. Clips run 3 to 16 seconds at resolutions from 540p up to 4K.

AIBen Affleck says he writes Python, understands convolutional neural networks, and has worked extensively with GPUs. He also says he used his celebrity status to get private looks at Google and OpenAI's video models. The post asks whether he uses Veo, Omni, or Nano Banana, but the source does not confirm any of these.

AIOpenAI is releasing a new version of GPT-6 to all ChatGPT users, extending the model beyond text. The post says model and infrastructure improvements were combined to scale it to 1.2 billion users, and it pairs the release with Intelligent UI, which delivers fast, interactive, and visual answers.

Why it matters: The post names the rollout scope and points to model and infrastructure work behind serving the update, which shows how a large consumer launch is being scaled.

AIThree Axiom engineers had OpenAI's GPT-6 Astra drive a 2024 Toyota Corolla to an In-N-Out drive-thru through a server linked to cameras and power steering, with a safety driver ready to brake. They also built a parking-lot benchmark, DrivingBench, where Astra completed the course slowly, Claude Fable 5.1 finished 45 percent, and Grok finished 11 percent.

AILiquid AI released two open-weight multimodal decision models, d1-3B and d1-omni-600M, which return probability answers in one forward pass with zero output tokens. d1-3B scores 48.57 on Decision Index v0.2.1 and answers one question in 8 ms on an RTX 4090, while the models are licensed free for commercial use below $10 million in annual revenue.

AIOpenAI says GPT-6 can now compose responses using text, visuals, and interactive elements, choosing how they fit together based on the user's question. Responses can include graphics and charts that help explain an idea, along with tappable buttons, forms, and interactive experiences usable directly in the conversation.

AIOpenAI announced that GPT-6 and Intelligent UI are now rolling out in ChatGPT for all users. The company says Intelligent UI provides fast, interactive answers, visual explanations of complex topics, and interactive tools for tasks.

AILiquid AI has released its d1 decision models, with d1-3B recommended for high-quality text and vision tasks and d1-omni-600M offered as an experimental option for smaller footprints. The weights are available for download, fine-tuning, and local deployment.

AILiquid AI has released d1-omni-600M, an experimental 600M-parameter model that handles text plus image or audio input. It combines LFM2.5-Encoder-350M with vision and audio encoders and leads the company's text benchmark comparison on toxicity detection and paraphrase identification. The post suggests uses such as voice-command routing, on-device moderation, and intent classification.

AILiquid AI's d1-3B ranks first among models under 10B parameters on the Decision Index v0.2.1, a benchmark for structured decision-making. Built from LFM2.5-VL-3B, it makes decisions from text and images in a single pass. It is suited to reranking, agent guardrails, and visual inspection.

AILiquid AI released Open d1, two open-weight multimodal models in its d1 decision model family. The d1-3B model supports text and vision, while d1-omni-600M supports text plus image or text plus audio. The source says the models are meant for real-time decision making across data centers, RTX workstations, and Jetson edge devices.

AILiquid AI released two open-weight decision models, d1-3B and d1-omni-600M (experimental), built on its Liquid Foundation Models and available on Hugging Face. d1-3B scores 48.57 on the Decision Index 0.2.1, the highest among decision models under 10B parameters, and answers a question in 16 ms on an NVIDIA Jetson AGX Thor and under 50 ms on a Jetson Orin Nano. The models support text and images (d1-3B) or text with image or audio (d1-omni-600M).

AIPerplexity is open-sourcing pplx-embed-v2-late, multi-vector embedding models for text and images in one shared space, in 9B and 0.6B sizes. The 9B model can index multimodal data, the 0.6B model can run queries on device, and PDF pages can be searched without OCR. The author reports 92.4% on MADQA and 64% on BrowseComp+, with weights available on Hugging Face.

AIAmazon Science is inviting attendees to its booth at COLM 2026 on Day 2 for talks on multi-agent orchestration, visual reasoning, and LLM agent evaluation. The post links to more details about the booth sessions.

AIPerplexity has released pplx-embed-v2-late, two late-interaction embedding models that retrieve text, images, and pages within a shared embedding space for cross-model querying. The company says both models achieve frontier performance and are publicly available on Hugging Face.

AIAi2 introduces Bolmo, a model that operates on bytes rather than tokens, which the team hopes will lead to larger models adapting how they represent information across languages and domains. Because bytes can also represent images and audio, the approach could eventually extend beyond text.

AIRowan Cheung says he built an app with GPT-6 Astra that selects his outfit each morning using live weather, with himself as the model. He describes the setup as uploading full-body and face photos, adding height, sizes, fit notes, and preferred and refused colors, then pasting a master prompt and letting it build for 1 to 2 hours.

AIKrea has released a plugin that brings its models, including Nano Banana, Krea 2, and GPT IMG 2.5, directly into Adobe Photoshop. The post invites users to try it now but gives no pricing or availability details.

AIGoogle is expanding its SynthID Detector verification portal through partnerships with OpenAI, NVIDIA, Kakao, and soon Apple to improve transparency for AI-generated content. The portal is now available globally in English and lets users check whether media was made with AI.

AIGoogle is making its SynthID Detector available globally in English, letting anyone check whether an image, video, or audio file was made with AI from Google or partners including OpenAI, NVIDIA, Kakao, and soon Apple. The tool joins built-in verification in Search, the Gemini app, and Chrome, which now handle over 1 million requests daily. Google says SynthID has watermarked over 180 billion images and videos and 240,000 years of audio.

Why it matters: The source specifies which vendors' AI media the detector checks, helping readers judge how far the verification covers content they encounter online.

AIThe Technology Innovation Institute introduces Falcon-ASR, a 1.6 billion parameter speech recognition model for Arabic with a focus on the Emirati dialect. On six Arabic test sets it reports an average word error rate of 20.92%, versus 23.17% for the best published leaderboard result it compared against. The model also transcribes English, French, Spanish and Portuguese with the same weights, and a demo Space is available while API access and native apps are planned.

AIElon Musk said the Grok bot will now use the best back-end model for each task, including Claude Opus 5.5, Midjourney, Suno, and other leading APIs. The aim is to deliver whatever is most likely to produce the best outcome, not just Grok 4.7 or 4.6.

AIGoogle DeepMind released EmbeddingGemma 2, an open 740M-parameter embedding model that maps text, code, images, video, and audio into one 768-dimensional space. Text-only use needs a 270M-parameter footprint, about 191MB active RAM when quantized on a Pixel 11 Pro, while loading all modalities takes about 567MB. The reported MTEB Code NDCG@10 score is 78.68, about 14% above the first generation, and MTEB Multilingual v2 is 61.36, roughly flat.

AIJerry Liu argues that OCR, long dominated by brittle legacy systems, can be solved accurately and cheaply by applying agentic intelligence. He says a properly tuned agentic OCR dynamically allocates extra compute to complex elements, reviews and corrects failures, and builds semantic meaning across the page. He contends frontier models are overengineered for this task in cost and latency yet still struggle with complex edge cases.

AILiquid AI released two open-weight d1 decision models, d1-3B and d1-omni-600M, on Hugging Face. d1-3B scores 48.57 on the Decision Index v0.2.1 public split and answers a single question in 8 ms on an NVIDIA GeForce RTX 4090 and 50 ms on a Jetson Orin Nano. d1-omni-600M is an experimental checkpoint that handles text with images or audio and scores 15.95 on the same index.

Why it matters: The release pairs open-weight decision models with measured latency across Apple, NVIDIA, and Jetson hardware, showing how edge deployment changes what is practical.

AIGoogle's Gemini Nano Banana 2.1 image generation and editing model is now available through ComfyUI Partner Nodes, succeeding Nano Banana 2 with a balance of price and performance. It accepts up to 14 reference images, outputs images up to 4K, and offers Minimal, Medium, and High thinking levels plus search grounding and 9:21 aspect ratio support.

AIThomas Wolf's post is a short, playful reply: "how do you like them convolutions," apparently referencing Ben Affleck's comments on convolutional neural networks. The quoted context reports Affleck describing his Python scripting, understanding of CNNs and tensors, GPU work, and private looks at Google and OpenAI's video models.

AISimon Willison released llm-openai-decisions 0.1a0, a plugin that adds OpenAI's new Decisions API to the LLM command-line tool. The plugin supports yes/no, choices, and score question types, and works with the gpt-6-luna decision model, which accepts both text and image input. OpenAI charges 10 cents per million input tokens for gpt-6-luna, while Jev's rate is 4.2 cents per million, and output is not charged.

AIOllama announced that Google DeepMind's EmbeddingGemma 2 is now available on Ollama. The author describes it as made for consumer devices and multimodal, and gives the command ollama pull embeddinggemma-2 to download it. The quoted DeepMind post says the model is a natively multimodal open model for on-device embeddings that unifies code, images, audio, and video in a shared space.

AIDevelopers are using OpenAI's Decisions API to route requests to the right model, tool, or agent and to turn scaled inputs into labels, rankings, and scores. The post also lists uses including analyzing images and video frames, choosing buttons or form actions from screenshots, flagging risky tool calls, and categorizing large datasets.

AIOpenAI's GPT-6 Luna accepts text and image inputs and supports three output types: predicates that estimate the probability a statement is true, choices that select from predefined options with confidence scores, and scores that evaluate an input against a numeric range.

AIGoogle DeepMind has released EmbeddingGemma 2, an open 740 million parameter model that maps text, images, audio, and video into one embedding space. It is built on the Gemma 4 architecture under an Apache 2.0 license and supports an 8K token context window. The company reports a code benchmark gain from 68.76 to 78.68 on MTEB Code and says the model can run on-device with about 567MB of active RAM for the full multimodal version on a Google Pixel 11 Pro.

Why it matters: The release shows how a 740M-parameter embedding model can cover text, code, images, audio, and video on local hardware, with memory and storage figures to compare against other on-device options.

AIfal is now available inside ChatGPT and Codex, letting users generate images and videos without leaving the chat. Generated media can be browsed directly in the conversation, and users can access their fal Media Library from ChatGPT. The library can be pinned to the sidebar for quick access to assets in any chat.

AIOn a livestream, Arthur Soroken interviews Amir and Ali Sadeghian, co-founders of Astrocade, about how generative AI and Gemini multimodal models are reshaping game development.

AIGoogle Gemini's Guided Vision supports everyday tasks such as reading fine print, finding objects, describing items, and exploring one's immediate surroundings. The feature is also presented as practical visual assistance for older adults, people with low literacy, and anyone reading in low light.