Auto Added by WPeMatico
Large hybrid MoE models like Nemotron-3-Super are accurate but expensive to serve. Their active parameters, KV cache, and Mamba state cap how many users a node can hold at a given per-user token rate. NVIDIA AI team has released Nemotron-Labs-3-Puzzle-75B-A9B, a compressed variant of Nemotron-3-Super. The parent model has 120.7B total and 12.8B active parameters. […]
Large hybrid MoE models like Nemotron-3-Super are accurate but expensive to serve. Their active parameters, KV cache, and Mamba state cap how many users a node can hold at a given per-user token rate. NVIDIA AI team has released Nemotron-Labs-3-Puzzle-75B-A9B, a compressed variant of Nemotron-3-Super. The parent model has 120.7B total and 12.8B active parameters.
Google AI Studio is rolling out an ‘import from GitHub’ feature inside its Build mode. It takes a repo and transforms it into a runtime-compatible format. You can then keep iterating on it, deploy it, and more. The update was shared by the Google AI Studio account and by Logan Kilpatrick, who leads the product.
Google AI Studio Adds Import from GitHub to Build a Deployable App Read More »
Ant Group’s Robbyant has released LingBot-VLA 2.0, a Vision-Language-Action (VLA) foundation model for robots. The release includes a technical report, an Apache-2.0 codebase, and a 6B checkpoint. The research team targets a well-known gap: VLA models often work in labs but stumble in deployment. LingBot-VLA 2.0 advances the prior version along three practical axes. These
SpaceXAI just released Grok 4.5. The company calls it its smartest model to date. It targets coding, agentic tasks, and knowledge work. SpaceXAI says Grok 4.5 was trained alongside Cursor, an AI coding editor. TL;DR Grok 4.5 targets coding, agentic tasks, and knowledge work, trained alongside Cursor. In SpaceXAI’s own chart, Fable (max) leads all
Google AI Studio is rolling out an ‘import from GitHub’ feature inside its Build mode. It takes a repo and transforms it into a runtime-compatible format. You can then keep iterating on it, deploy it, and more. The update was shared by the Google AI Studio account and by Logan Kilpatrick, who leads the product.
Robbyant, the embodied-AI company within Ant Group, has open-sourced LingBot-Vision, a family of self-supervised Vision Transformers built for dense spatial perception. The weights ship under Apache-2.0 on Hugging Face in four sizes — ViT-giant, ViT-large, ViT-base, and ViT-small — together with a technical report and inference code. Most vision foundation models are trained for semantic
NVIDIA has released Audex (Nemotron-Labs-Audex-30B-A3B), a unified audio-text large language model. It understands and generates both audio and speech. It also keeps the text intelligence of its backbone. The checkpoints, along with a smaller Audex-2B, are released under a noncommercial license. Most multimodal models pay a text tax. When labs add audio or vision output,
Liquid AI has released Antidoom, an open-source method that targets a common failure mode in reasoning models. That failure mode is the doom loop. In a doom loop, a model emits a span. It then repeats that span again and again. The output continues until the context window is exhausted. Small reasoning models are more
Tencent’s Hy team released Hy3. Hy3 is a 295B-parameter Mixture-of-Experts (MoE) model. It activates only 21B parameters per token. The weights ship under the Apache License 2.0. Hy3 is aimed at reasoning, agentic workflows, and long-context tasks. What is Hy3? Hy3’s architecture contains a sparse MoE with 192 experts and top-8 routing. Only 8 experts
