Dharma-AI introduces a constraint-aware GPU allocator that improves GPU utilization by up to 33 percentage points and priority-weighted output by up to 105% compared to a FIFO scheduler, by…
Hugging Face and AWS announce a streaming data loop for Strands Robots that records, trains, and deploys robot policies using Hugging Face Storage Buckets and LeRobot format, enabling continuous…
Hugging Face ran a hackathon where 1,221 community members used coding agents to reproduce 2,226 papers from ICML 2026, finding that 51% had at least one verified claim and 23% had at least one…
OlmoEarth Studio now supports custom embedding exports, allowing users to compute and download embedding vectors from OlmoEarth foundation models for downstream tasks like similarity search and…
LFM2.5-VL-3B is our most capable vision-language model you can run on your own hardware. It understands documents and screens alike, grounds objects, and can call tools.
ALTK-Evolve and ACE both let an agent learn from its own trajectories. The difference is what they do with what they learn — and that decides the token bill.
Every voice interaction has a latency budget. By the time a user hears your application respond, you've already spent precious milliseconds capturing audio, transcribing speech, running an LLM,…
! Published August 10, 2026 Update on GitHub Upvote 88 +82 Pedro Cuenca pcuenq Follow merve merve Follow ben burtenshaw burtenshaw Follow Aritra Roy Gosthipaty ariG23498 Follow Great news from the…
Hugging Face and Allen AI introduce TutorMoments, a framework to evaluate whether LLMs can balance helping students versus letting them struggle, using real tutoring transcripts and teacher…
Baseten is now a supported Inference Provider on the Hugging Face Hub, offering serverless inference for conversational and text-generation tasks with models like Kimi K3, DeepSeek V4 Flash, and…
Utilization, not intelligence, is the next real constraint in AI. Aviation learned this the hard way. For most of the industry's history, the number that best predicted whether an airline would…
🌍 Learn more about OlmoEarth Platform: https://allenai.org/olmoearth The OlmoEarth models are our family of Earth observation foundation models, pretrained on roughly 10 terabytes of multimodal…
Today, we release two new encoder models on Hugging Face: LFM2.5-Encoder-230M and LFM2.5-Encoder-350M . They match the quality of larger models but stay fast as inputs get longer.
Surgical robotics is moving quickly from teleoperation toward increasingly capable vision-language-action policies. But evaluating and training these systems remains difficult.
A companion technical writeup to our incident disclosure . This post walks through how the intrusion actually worked: the two initial-access vectors, how the agent pivoted and moved laterally,…
Large diffusion transformers can create stunning images (or even videos, audio snippets, and now text), but loading a modern text-to-image model in BF16 precision often requires 20-30 GB of VRAM,…
. And build a shared dataset, together. Published July 21, 2026 Update on GitHub Upvote 49 +43 Steve Nguyen SteveNguyen Follow pollen-robotics Claire Houziel chouziel Follow pollen-robotics Gaelle…
Despite newer architectures, DharmaOCR outperformed Mistral OCR4 and Unlimited-OCR on Brazilian Portuguese through domain specialization and targeted training.
Building a router into your agent sounds like an easy win. Send simple requests to cheaper models, reserve expensive ones for harder tasks, or route by specialty — Claude for code, Gemini for…
Existing benchmarks suggest voice AI is nearing human-level performance but real-world conversations tell a different story. Voice is rapidly becoming AI's primary interface.
Inkling now comes in smaller size 🤗 Inkling-Small is out by Thinking Machines Lab. We have updated this post with performance , and deployment configurations for the Inkling-Small and the…
This is the third post of Profiling in PyTorch, a series where we slowly build the skill of reading profiler traces and use it to drive optimization Profiling in PyTorch (Part 1): A Beginner's Guide…
At Microsoft Build 2026, we announced Foundry Managed Compute and Hugging Face models on Foundry — a curated catalog of open-weight models from the Hugging Face ecosystem, refreshed weekly,…
This new release is about closing the robot learning loop: policies that imagine the future before acting, reward models that tell you when your robot succeeds, a deployment CLI that turns failures…
For most teams, models and datasets live in a bucket in one region of one cloud. The GPUs you can get, whether for development, training, or serving, increasingly sit on a different cloud than your…
In our previous post (From Zero to GPU) , we introduced the 🤗 Kernels project, which aims at standardizing how custom kernels are packaged, distributed, and consumed.
For voice AI, latency is a critical parameter. Developers have made tremendous progress in model quality, but the user experience is still often limited by response times.
What optimization theory, evolutionary biology, competitive markets, and machine learning all predict — and why the answer is the same --- Those who follow Dharma AI already know that we view…
Every Eval Ever (EEE) and Hugging Face Community Evals are now intercompatible. We enable cross-posting and interpreting evaluation results, while linking to open models, leaderboards, and a unified…
Many problems in machine learning and the sciences come down to the same task: you have a collection of data points and want to recover the distribution they came from—which values are common, and…
You can spin up a private, OpenAI-compatible LLM endpoint on Hugging Face infrastructure with a single command — no servers to provision, no Kubernetes, pay-per-second.
HuggingFace Transformers has become the foundation of the open-source AI ecosystem, and the recent Transformers v5 release strengthened it with first-class support for Mixture-of-Experts (MoE)…
🚀 First open far-field ASR benchmark: community-driven evaluation across 14 simulated rooms, validated against real-world measurements: https://huggingface.co/spaces/treble-technologies/ffasr 📉 The…
(This is a guest post by Developer Relations Engineer Thomas Steiner from the Chrome team at Google.) Transformers.js provides Web developers with a simple way to use the power of transformers in…
huggingface_hub is the Python client at the base of the Hugging Face ecosystem. transformers , datasets , diffusers , sentence-transformers and dozens of other libraries depend on it to talk to the…
*Free as in beer, excluding the cost of electricity, and assuming you already own the hardware June 2026 will go down as the moment that people realized closed models can be taken away.
Deep research agents increasingly combine private local documents with external tools like web retrieval, creating a privacy risk: an agent's external queries may leak sensitive information.
When you plan to fine-tune a model in a parameter-efficient way, think beyond LoRA If you want to fine-tune an open model on your own data, you are probably interested in so-called…
A walkthrough of the LeRobot integration in Strands Robots - one agent loop, from a Hub dataset to a physical robot, with sim-to-real datasets in the same on-disk format and policies you swap with a…
We're introducing GLM-5.2, our latest flagship model for long-horizon tasks. It marks a substantial leap in long-horizon task capability over its predecessor GLM-5.1 and, for the first time, delivers…
for tools, skills, and other agents. Published June 17, 2026 Update on GitHub Upvote 21 +15 ben burtenshaw burtenshaw Follow shaun smith evalstate Follow If you build with agents today, you probably…
Hugging Face· 17h ago