106 stories curated by AInformed
SkyPilot now lets you run AI workloads across clouds and store outputs on Hugging Face without egress fees. This makes AI experimentation more affordable and flexible for developers.
Hugging Face introduced a new native-speed backend for vLLM that dramatically accelerates inference for large language models, not training. This could significantly reduce costs and latency for developers deploying AI models.
Hugging Face and Amazon have teamed up to let users deploy AI models to Amazon SageMaker Studio with a single click. This makes it easier for developers to use powerful AI tools without needing deep technical expertise.
LeRobot v0.6.0 is an open-source library focused on real-world robotics, providing datasets, models, and simulation tools for reproducible AI research. It is not an image generation tool.
Hugging Face has revamped Kernels, expanding support to more AI models and improving the developer experience. The update includes better resource management, smoother integration with Hugging Face Hub, and easier sharing of kernel sessions.
AI models are becoming more specialized to handle specific tasks better. This trend is making AI more useful for everyday applications.
Hugging Face and Cerebras have released a new open-source model optimized for real-time voice AI, leveraging Cerebras hardware to achieve low-latency speech processing. This could make voice assistants and AI-powered call centers faster and more responsive.
Hugging Face now shows detailed performance metrics for AI models on their model pages. This makes it easier for users to compare models and choose the best one for their needs.
ScarfBench is a new benchmark for testing AI agents on complex Java framework migrations. It helps evaluate how well AI can handle large-scale software updates.
AllenAI introduced DiScoFormer, a transformer model that can handle both density and score estimation across different distributions. This innovation simplifies complex AI tasks by using one model instead of multiple specialized ones.
A new study from AllenAI reveals that hybrid AI models predict certain types of tokens better than others, with key implications for training more accurate language models.
Hugging Face is experimenting with a proposed web API called Cross-Origin Storage, allowing web-based AI models running in Transformers.js to securely share data like model weights or inference cache across different websites. This could reduce redundant downloads and make AI tools faster and more seamless across multiple platforms.
Hugging Face introduced the FFASR Leaderboard to evaluate speech recognition models in real-world conditions. This new tool helps developers compare how well AI understands everyday speech, not just lab recordings.
Hugging Face now uses AI and open tools to automate its weekly release of the huggingface_hub Python library, combining AI efficiency with human review for faster, reliable updates.
Hugging Face now lets you run a vLLM server with a single command, using its new Jobs feature. This makes it easier for developers to deploy large language models without complex setup. Anyone with basic coding skills can now run powerful AI models effortlessly.
NVIDIA's new NeMo AutoModel makes customizing AI models faster and easier. It automates the fine-tuning process, which could help businesses and developers create specialized AI tools without needing deep technical expertise.
IBM has launched CUGA, an open-source framework for creating AI agent applications. It includes two dozen working examples to help developers get started quickly.
Hugging Face demonstrated a proof-of-concept using local AI models—including Qwen2.5 and DeepSeek—to automatically triage pull requests on the OpenClaw repository, achieving over 80% accuracy in flagging valid contributions for review.
Sturnus is an open-source tool that automatically routes AI queries to the fastest available provider. It acts as a proxy layer compatible with OpenAI's API, simplifying usage and improving response times.
PaddlePaddle released PP-OCRv6, an AI that can read text from images in 50 languages. It's up to 700% more efficient than its predecessor, working even on smartphones. This makes it easier to digitize books, signs, and documents in any language.
OpenAI's new initiative, Patch the Planet, uses AI and expert review to help open-source maintainers find and fix vulnerabilities. This could make open-source software safer for everyone.
Hugging Face introduced a new open-source standard called Agentic Resource Discovery that enables AI agents to autonomously discover and connect to external tools, APIs, and data sources on the fly. While it is related to search, its primary focus is on expanding agent capabilities through dynamic resource discovery, not just web search.
Hugging Face has integrated MCP (Model Context Protocol) tools into the Reachy Mini robot, making it easier to program and control. This could open up robotics to more developers and hobbyists.
ServiceNow researchers discovered a vulnerability in AI research agents that can leak sensitive data through a novel attack called MosaicLeaks. The flaw exploits how these agents handle and combine information, potentially exposing private details even when individual queries seem safe. The issue affects multiple AI research platforms and highlights a fundamental security challenge in agentic AI systems.
Hugging Face introduced a new tool to test how well open-source AI models perform as agents. This helps developers compare models without needing complex setups.
Hugging Face has integrated AI models with robot hardware, allowing developers to deploy models directly to robots. This breakthrough makes advanced AI capabilities accessible to physical robots for the first time.
Researchers have developed new open-source methods that outperform LoRA, the most popular AI fine-tuning technique. These approaches could make customizing large language models more accessible and affordable for everyone.
MolmoMotion is a new AI model that can predict 3D movements based on text descriptions. It could revolutionize fields like robotics, gaming, and animation by making motion prediction more accessible.
GLM-5.2 is a new open-source AI model designed to handle long-horizon tasks better than most. It's now available for anyone to use and build upon.
PyTorch has introduced a new optimization technique called fused MLP that speeds up AI model training. This advancement makes it easier and faster for developers to build and train complex AI models.
Hugging Face now offers a new way to run continuous integration (CI) workflows directly on its platform. This can simplify the process for developers using GitHub repositories.
The open-source community is rallying behind OpenEnv, a new platform for developing AI agents using reinforcement learning. This could make advanced AI tools more accessible to developers and researchers.
Olmo-Eval is a new open-source platform designed to help developers test and improve AI models. It streamlines the evaluation process, making it easier for anyone to assess AI performance.
A developer created a 3D Paris gallery using AI agents that chain two open-source tools. This shows how combining simple AI tools can create powerful, creative applications.
Cohere has introduced North Mini Code, a compact AI model designed specifically for developers. The model is open-source, lightweight, and optimized for code generation and completion, making advanced AI capabilities more accessible to a wider audience.
AI agents are becoming more powerful, but their terminology can be confusing. Understanding key terms like 'harness' and 'scaffold' helps clarify how these tools work and what they can do. These concepts are crucial for both developers and users to grasp as AI agents evolve.
Hugging Face has released a new command-line interface (CLI) designed to streamline interactions with their AI model Hub. This tool makes it easier for developers and AI enthusiasts to manage models and datasets directly from their terminal.
PyTorch's torch.profiler helps you find performance bottlenecks in your AI code. It's a powerful tool for developers, even if you're new to optimization.
Researchers built a multi-agent economy simulation using a small AI model with just 3 billion parameters. This shows how powerful even modest-sized models can be for complex tasks.
NVIDIA released Nemotron 3.5, an open-source AI model that helps businesses customize safety filters. This tool lets companies adapt AI content moderation to local laws and cultural norms.
EVA-Bench Data 2.0 is a comprehensive dataset designed to test AI models' ability to use tools effectively. It includes 213 scenarios across 3 domains and 121 tools, making it a valuable resource for developers and researchers.
NVIDIA's Nemotron 3.5 ASR model can now be fine-tuned for specific languages, accents, or domains. This makes it more accurate for specialized applications like medical or legal transcription.
Researchers have extended Direct Preference Optimization (DPO) to improve AI models beyond just chatbots. This could make AI assistants more helpful and safer across various applications. Researchers open-sourced the code, making it accessible to developers and researchers worldwide.
Hugging Face released Holo3.1, a free open-source tool that lets you run AI agents locally. This means you can use AI assistants without sending your data to the cloud.
IBM Research explains why AI agents—software that automates complex tasks—are crucial for businesses to use AI at scale. These agents could make AI more practical for everyday work.
NVIDIA has released Cosmos 3, an open-source AI model designed for physical reasoning and action. This breakthrough could revolutionize how robots and AI systems interact with the real world.
JetBrains has released Mellum2, a 12-billion-parameter AI model designed to be more efficient and capable. This open-source tool is aimed at developers and researchers looking for advanced AI capabilities.
Hugging Face has launched Delta Weight Sync, a tool that simplifies updating large AI models by only syncing the changes, not the entire model. This saves time and storage space for developers and researchers working with massive models.
A new benchmark shows that even advanced AI models score below 50% on simple IT tasks. This highlights how far AI has to go in understanding real-world enterprise needs. The benchmark is open-source, so anyone can test their own models.
A new report from Hugging Face highlights that smaller AI models focused on specific tasks often outperform larger, general-purpose models. This challenges the common assumption that bigger is always better in AI.
NVIDIA has introduced Nemotron-Labs, a new type of AI model that generates text at near light-speed. This could revolutionize how we interact with AI assistants and tools. The models are open-source, making them accessible to everyone.
Allen Institute for AI released OlmoEarth v1.1, a suite of AI models designed to analyze satellite images. These models help track environmental changes, like deforestation and urban growth, more efficiently than before.
Hugging Face has launched the Ettin Reranker Family, a new set of open-source tools to improve search result accuracy. These models help prioritize the most relevant information in search queries, making it easier to find what you need.
Hugging Face has introduced a leaderboard to evaluate and compare AI assistants. This new tool aims to make it easier for users to find the best AI assistant for their needs.
PaddleOCR 3.5 is a free, open-source tool that can extract text and data from documents with high accuracy. It's now powered by Transformers, making it more powerful and easier to use for everyday tasks.
NVIDIA has fine-tuned its Cosmos Predict 2.5 model to generate realistic robot videos. This advancement could revolutionize robot training and simulation.
Hugging Face introduced a new technique called asynchronous batching to speed up AI model processing. This innovation allows for more efficient handling of multiple tasks at once, making AI tools faster and more responsive for users.
Amazon Web Services (AWS) has open-sourced a set of tools designed to simplify the process of training and deploying large AI models. These tools aim to make advanced AI technology more accessible to developers and businesses.
IBM has open-sourced Granite Embedding Multilingual R2, a powerful AI model that improves search and translation across languages. It handles up to 32,000 words at once, making it useful for large documents and complex queries.
OpenServ AI has released a new open-source AI model designed to be accessible and customizable for everyday users. This could make advanced AI tools more widely available without requiring technical expertise.
A new open-source project uses AI to check 3D printing designs for errors before production. This could save time and materials for hobbyists and professionals alike.
Hugging Face is updating its Open ASR Leaderboard to prevent overfitting by adding a new metric. This change aims to ensure models perform well on real-world data, not just on benchmarks.
Researchers have developed an AI system called OncoAgent that helps doctors make better cancer treatment decisions without compromising patient privacy. This dual-tier framework uses multiple AI agents to analyze medical data securely.
Researchers have created EMO, an AI model that can learn different skills separately and combine them as needed. This could make AI more flexible and efficient for everyday tasks.
A new open-source AI model is designed to run locally and help detect cyber threats. It's small, specialized, and built for everyday users to protect their devices.
The new vLLM V1 model focuses on improving AI accuracy before applying fine-tuning. This approach could make AI models more reliable for everyday users.
OpenAI has released a new tool to help developers build web apps that protect user privacy. This filter ensures sensitive data isn't exposed in AI interactions.
DeepInfra is now part of Hugging Face's Inference Providers, making it easier to deploy AI models. This collaboration simplifies running models for developers and researchers.
Evaluating AI models is now more expensive than training them, creating a bottleneck in open-source development. This shift highlights the growing importance of efficient evaluation frameworks.
IBM has released Granite 4.1, a suite of open-source large language models trained using advanced techniques like mixture-of-experts and fine-tuning. The models are optimized for both efficiency and performance, setting a new standard in open-source AI.
NVIDIA's new Nemotron 3 Nano Omni model supports long-context multimodal intelligence across documents, audio, and video. It is designed for developers to build advanced AI agents.
The Hugging Face Blog highlights how open-source AI is transforming cybersecurity by fostering collaboration and innovation. Transparency in AI models is crucial for building trust and resilience against cyber threats.
Hugging Face has ported its Transformers library to MLX, enabling faster AI model inference on Apple Silicon. This move aims to leverage Apple's neural engine for enhanced performance.
Hugging Face has released a tutorial on integrating Transformers.js into Chrome extensions. This enables developers to leverage advanced AI models directly in browser-based applications.
HCompany has unveiled HoloTab, an open-source AI browser companion designed to enhance productivity and streamline web interactions. This tool integrates seamlessly with popular browsers, offering a range of AI-driven features.
NVIDIA showcases Gemma 4's Variable-Length Attention (VLA) running on the Jetson Orin Nano Super. This highlights the model's efficiency and flexibility in edge computing applications.
Hugging Face introduces QIMMA, a quality-focused leaderboard for Arabic LLMs. It aims to highlight models that excel in both performance and cultural relevance.
DeepSeek-V4 introduces a one-million-token context window, making it the largest available. This breakthrough enables agents to process extensive documents and conversations with unprecedented context retention.
NVIDIA has open-sourced a new OCR model that supports multiple languages and leverages synthetic data for training. The model is designed for speed and accuracy in text recognition tasks.
Hugging Face has published a comprehensive guide on training and fine-tuning multimodal embedding and reranker models using Sentence Transformers. This resource is aimed at developers looking to enhance their multimodal applications with state-of-the-art techniques.
Ecom-RLVE is a new open-source framework designed to create verifiable and adaptive environments for e-commerce conversational agents. It aims to enhance the reliability and performance of AI-driven customer interactions.
NVIDIA has released Isaac GR00T N1.7, an open-source reasoning model designed for humanoid robots. This model enables advanced decision-making and interaction capabilities for robotic systems.
IBM Research has introduced VAKRA, a new benchmark for assessing agents' reasoning, tool use, and failure modes. The benchmark aims to provide a standardized way to evaluate agent capabilities across various tasks.
Hugging Face has released Waypoint-1.5, an open-source model designed to generate high-fidelity interactive worlds that run efficiently on consumer-grade GPUs. This release lowers the barrier to entry for developers building immersive, real-time 3D environments without requiring massive enterprise infrastructure.
TII has released Falcon Perception, a multimodal model combining text and vision capabilities. This open-source model sets a new standard for accessibility in AI.
Safetensors, a popular open-source library for secure model serialization, has joined the PyTorch Foundation. This move aims to improve AI safety standards and interoperability within the PyTorch ecosystem.
NVIDIA has released a tool to fine-tune domain-specific embedding models quickly. This democratizes access to specialized AI applications.
IBM has released Granite 4.0 3B Vision, a compact open-source model designed to analyze enterprise documents with high efficiency. This release bridges the gap between heavy multimodal models and the need for fast, local document processing.
Hugging Face has released OpenClaw, an open-source framework designed to streamline AI model training and deployment. The tool aims to democratize access to advanced AI capabilities.
Hugging Face's Spring 2026 report highlights a 40% increase in open-source AI models. The platform now hosts over 500,000 models, with significant contributions from both academia and industry.
Hugging Face has released TRL v1.0, a comprehensive library designed to streamline post-training workflows for large language models. This update unifies Reinforcement Learning from Human Feedback (RLHF) and other alignment techniques under a single, modular framework.
Hugging Face has released new multimodal embedding and reranker models via Sentence Transformers. These models enable advanced cross-modal retrieval and ranking capabilities.
Hugging Face has launched EVA, an open-source framework designed to rigorously evaluate the performance of voice AI agents. This tool addresses the critical need for standardized metrics in assessing voice interaction quality, reliability, and safety.
Gradio now allows developers to integrate custom frontends with its backend, expanding flexibility for AI application development. This move could democratize AI deployment further.
IBM Research has released ALTK-Evolve, an open-source framework enabling AI agents to learn and adapt in real-time during task execution. This approach eliminates the need for static pre-training by allowing agents to evolve their strategies based on immediate feedback.
Researchers trained mRNA language models across 25 species for $165. This breakthrough has significant implications for bioinformatics and natural language processing.
Holotron-12B is a new high throughput computer use agent. It is designed for efficient computing.
Gemma 4 is a new multimodal intelligence model. It runs on devices, enabling local AI processing.
Ulysses Sequence Parallelism enables training with million-token contexts. This technology improves model performance.
Researchers trained mRNA language models across 25 species for $165. This breakthrough has significant implications for open-source AI development.
Linggen is a local-first, open-source AI coding agent with P2P remote access. It proposes step-by-step plans before writing code and works with various models.
Holotron-12B is a new high throughput computer use agent. It is designed for efficient computing.
Holo3 breaks the computer use frontier with its open-source release. This innovation is set to revolutionize the way we interact with computers.
Google is investing in open source security for the AI era. The company is building new tools and developing code security to improve open source security.
Gemma 4 is a new multimodal intelligence model. It enables on-device processing for various tasks.
CongaLine is a self-hosted AI agent fleet that allows teams and individuals to run isolated AI assistants. It prioritizes security and offers flexible deployment options.