Tag
Google 的 Gemini 4 Argon 展示了多模态能力，能够从单张图片一次性生成数学可视化内容。
A tweet praising Meta's Muse Wonder model for outperforming other models at pointing to objects in images, marking a notable comeback for Meta in visual grounding.
Miles Brundage notes that since models like o3, AI systems can easily infer where photos were taken via reasoning, image understanding, and web search, yet people remain unaware and keep posting location-identifiable images.
A user tested a 6B-parameter small model on a full poster and praised its ability to break down every layer — title, background, and main elements — while the quoted post shares a cloud deployment tutorial for running open-source image/video models at roughly 1/8 of the official API price.
New model Wity-1, a reasoning decision model positioned between non-reasoning decision models like Jev and fully reasoning LLMs, reportedly beats Jev on all 4 baselines and ranks #1 on the Image Jev Bench, and is multi-modal. It reasons just enough until internal LLM probabilities indicate the answer is reached.
A tweet suggests using Gemini 3.8 Flash for multimodal understanding and references a visual test comparing AI models' ability to name people from a drawing.
One year after launch, Switzerland's open AI model Apertus has achieved over 4 million downloads and updated to version 1.5 with enhanced features, but still faces competition and usability issues.
The paper introduces Libra, a decoupled vision-language architecture for multimodal large language models that enables both image-to-text understanding and text-to-image generation, demonstrating strong performance on benchmarks.
This paper presents MoE-ViE, a mixture-of-experts vision encoder that efficiently scales for image and video understanding, outperforming larger dense models with lower inference latency.
ClinFusion is a new open medical multimodal LLM from Alibaba DAMO Academy, available in 8B and 32B sizes (Apache 2.0), with unified 2D + 3D image understanding and state-of-the-art results on medical benchmarks.
A tweet claims Qwen3.8-Max is the best object detection VLM, excelling across satellite, infrared, document, and hand-drawn images, with examples shared.
Inkling is a large open-weights multimodal model (975B total, 41B active parameters) using a sparse MoE architecture, accepting text, image, and audio inputs and generating text outputs, intended for agentic systems, coding assistants, and chatbots.
Snippai is a fully open source and free screenshot recognition AI tool that supports formula conversion to LaTeX, text extraction, table conversion to Markdown, image understanding, screenshot problem solving, code explanation, color analysis, and screenshot translation.
The user shows two outfits in real-time via GPT-Live, and the AI gives specific clothing suggestions for the scenario of meeting parents, demonstrating multi-round image understanding and contextual recommendation capabilities.