Introducing Inversion, our family of structured LLMs. Our first... generation models excel in structured tasks, offering unmatched speed, latency, reliability, and efficiency, with the most comprehensive typed JSON output support available anywhere.show more

Introducing 𝗦𝘂𝗽𝗲𝗿 𝗝𝗦𝗢𝗡 𝗠𝗼𝗱𝗲, a framework for low latency... structured output generation from LLMs. Generate JSON up to 𝟮𝟬𝘅 𝗳𝗮𝘀𝘁𝗲𝗿 from OpenAI and open source models. ❌ No need to threaten the model, tip the AI, etc ❌ Built with Alex Derhacobian 🔧 🧵👇show more

Introducing DeepThought-8B: Transparent reasoning model built on LLaMA-3.1 with... test-time compute scaling. - JSON-structured thought chains & controllable inference paths. - ~16GB VRAM, competitive w/ 70B models. - Open model weights, and inference scripts.show more

Introducing Batch URL Enrichment on our playground 🔥 Now... you can process multiple URLs at a time in our playground with batch scrape & JSON mode. Upload a CSV, paste in a list, or enter URLs one by one to turn any collection of sites into structured LLM ready data in seconds.show more

Meta announces SceneScript Reconstructing Scenes With An Autoregressive Structured... Language Model We introduce SceneScript, a method that directly produces full scene models as a sequence of structured language commands using an autoregressive, token-based approach. Ourshow more

🇸🇦 Check out this stunning time-lapse of the Hajj... crowds at Mecca. The speed and efficiency with which they move hundreds of thousands of people is unmatched anywhere else in the world.show more

New Generation Model! 🚨 We're introducing the Mistral model... to our expanding lineup of generation models. Mistral brings efficient performance and strong language understanding capabilities to our platform. Initial testing shows promising results in code comprehension and generation tasks, making it a valuable addition to development workflows. While we continue to optimize its implementation, early benchmarks demonstrate consistent and reliable outputs across various programming tasks.show more

LongWriter Unleashing 10,000+ Word Generation from Long Context LLMs... discuss: Current long context large language models (LLMs) can process inputs up to 100,000 tokens, yet struggle to generate outputs exceeding even a modest length of 2,000 words. Through controlled experiments, we find that the model's effective generation length is inherently bounded by the sample it has seen during supervised fine-tuning (SFT). In other words, their output limitation is due to the scarcity of long-output examples in existing SFT datasets. To address this, we introduce AgentWrite, an agent-based pipeline that decomposes ultra-long generation tasks into subtasks, enabling off-the-shelf LLMs to generate coherent outputs exceeding 20,000 words. Leveraging AgentWrite, we construct LongWriter-6k, a dataset containing 6,000 SFT data with output lengths ranging from 2k to 32k words. By incorporating this dataset into model training, we successfully scale the output length of existing models to over 10,000 words while maintaining output quality. We also develop LongBench-Write, a comprehensive benchmark for evaluating ultra-long generation capabilities. Our 9B parameter model, further improved through DPO, achieves state-of-the-art performance on this benchmark, surpassing even much larger proprietary models. In general, our work demonstrates that existing long context LLM already possesses the potential for a larger output window--all you need is data with extended output during model alignment to unlock this capability.show more

LM Studio 0.3.4 ships with Apple MLX 🚢🍎 Run... on-device LLMs super fast, 100% locally and offline on your Apple Silicon Mac! Includes: > run Llama 3.2 1B at ~250 tok/sec (!) on M3 > enforce structured JSON responses > use via chat UI, or from your own code > run multiple models simultaneously > download any model from Hugging Face Video at 1x speed.show more

Good discussion and a clear common ambition at MED9... to improve our collective management of migration in the Mediterranean. In particular by supporting Member States with crisis response, and structured approaches through reinforced partnerships with our southern neighbourhood.show more

We're open sourcing a 9B model that extracts structured... data from documents at near-frontier performance. - 90.2% on our bench, vs Gemini 3.5 Flash at 91.3% - Leads extraction models like NuExtract3 (81.5%) - 9.5s p50 timings - Pass JSON schemashow more

We are introducing v0-1.5-md and v0-1.5-lg, our newest models... for UI generation and web development. Available today on Coming to the API next week.show more

Introducing Asta DataVoyager—our new AI capability in Asta that... turns structured data into transparent, reproducible insights. Built for scientists, grounded in open, inspectable workflows. 🧵show more

I've nearly ditched closed source models for image generation... (in creative workflows). For most tasks, the cost/speed ratio doesn't justify closed models anymore. Open models have caught up on quality and I can try 15 new images in 1-2 sec. Iteration speed matters. Sharing the few models I currently use ⬇️show more

🔥Spatial intelligence requires world generation, and now we have... the first comprehensive evaluation benchmark📏 for it! Introducing WorldScore: Unifying evaluation for 3D, 4D, and video models on world generation! 🧵1/7 Web: arxiv:show more

Introducing the first wave of our official Slay the... Princess collection! Available now:show more

Import transactions from CSV with the power of AI... field mappings: ◇ Extract 5 rows ◇ Structured output with AI SDK ◇ Stream response to client ◇ Run import background jobshow more

Introducing Lyria 3 Pro and Lyria 3 Clip, our... full song and 30 second music models, available starting today in the Gemini API and our all new music experience in Google AI Studio!!show more

Historically, RWAs are illiquid. Not with Nest. Our integration... with Nest powers unified asset issuance, lending strategies, and structured products built on top of liquid yield bearing RWAs.show more

Introducing DI-PCG: A diffusion-based Image2PCG framework that automates Procedural... Content Generation, and our first step towards neural symbolic 3D generation. The demo showcases six object categories and can be extended to support customized PCGs. Links in comments. CC: Wang Zhaoshow more

New Generation Model! 🚨 We're introducing the o3m model... to our expanding lineup of generation models. While still in its beta phase, we're actively refining its output to push its capabilities even further. So far, we've observed a significant leap in physics calculations, AI-driven mechanics, and the overall fluidity of app and game interactions. As we continue to tweak and optimize, expect even greater advancements in precision, automation, and creative execution.show more