Blog

Notes on teaching robots new tricks

How the studio works, why tiny robots come first, what the checks catch, and how a policy gets from simulation to a servo.

workflowopen-duck-miniSep 29, 2026 · 6 min readFrom a sentence to a walking duck: how kualia turns a plain-language brief into a training taskA walk through the whole kualia workflow, from a one-sentence brief to an ONNX policy, using the Open Duck Mini and a small ramp.Read the post

Sep 27, 2026 · 5 minWhy we start with tiny robotsDesk-sized robots train on CPU in minutes to hours, cost little to own and cross the sim-to-real gap without heroics. That is why kualia's shelf starts with them.

Sep 25, 2026 · 6 min13 checks before a single training stepalia writes the training task, but it does not get to grade its own work. Every task passes 13 sandbox checks before training can start. Here is what each one catches.

Sep 23, 2026 · 5 minFrom simulation to servo: running your ONNX policy on a real SO-101What is inside a kualia ONNX export, how to read its metadata, a minimal onnxruntime loop for the SO-101, and the sim-to-real checklist before you power the servos.

Sep 21, 2026 · 5 minLet your coding agent train the robotkualia is a remote MCP server. Point Claude Code, Cursor or Codex at it and your agent can pick a robot, build the task, train it and fetch the ONNX policy from your editor.

Research digest

Short reads on new robotics and AI papers, written by our research assistant and reviewed before publishing. 1,060 so far.

Page 54 of 59

Mar 22, 2026Spectrally-Guided Diffusion: Why Your Noise Schedule Should Listen to the Fourier TransformDiffusion models have become the dominant paradigm in generative modeling, yet a surprising amount of their behavior remains governed by folklore and hand tuned heuristics. While Latent Diffusion Models (LDMs) currently Mar 22, 2026 · TR Mar 22, 2026The Geometry of Moral Indifference: Why Language Models Fail to Understand EthicsThe prevailing metaphor for modern AI alignment, popularized within mechanistic interpretability circles, depicts Large Language Models as Shoggoths wearing smiley faces. These gelatinous, many-eyed creatures from Lovecr Mar 22, 2026 · TR Mar 22, 2026In-Context Reinforcement Learning: How AdA Achieves Human-Timescale AdaptationWhile foundation models have fundamentally reshaped natural language processing and computer vision through their ability to perform in-context learning, reinforcement learning has remained stubbornly fragmented into nar Mar 22, 2026 · TREm-Garde ve Akış Video Anlama Paradigmasının Yeniden TanımlanmasıEm-Garde ve Akış Video Anlama Paradigmasının Yeniden Tanımlanması Mar 22, 2026 Mar 22, 2026 · TREEG Tabanlı Rehabilitasyon Eksoskeletonlerinde Niyet Kontrolü: Geometrik Yöntemlerle Kalibrasyon Hatalarını Düzeltmek Giriş İnme sonrası üst ekstremite fonksiyonlarının kazanılmasında robotik rehabilitasyon sistemleri yüksek dozlu, göreve özgü antrenman sunar. Ancak bu sistemlerin çoğu distal mekanik seviyede çalışır, hasarlı sinir dev Mar 22, 2026The Geometry of Intention: Why We Must Stop Recalibrating Against Ourselves in Brain-Computer Interfaces The Contingency Gap in Rehabilitation Robotics Robot assisted therapy promises high dose, task specific training for neurologic injury, yet clinical outcomes remain modest despite decades of engineering refinement. The Mar 22, 2026 · TRForwardFlow: Derin Öğrenme ile Simülasyon Temelli Frekansist Çıkarım Giriş: Simülasyon Temelli Çıkarımın Yeni Aşaması İstatistiksel çıkarım problemlerinde likelihood fonksiyonunun hesaplanabilir olmadığı durumlar uzun zamandır araştırmacıları zorlayan temel sorulardan biri olmuştur. Appr Mar 22, 2026ForwardFlow: Reimagining Simulation Based Inference Through the Lens of Frequentist Neural EstimationThe landscape of statistical inference is undergoing a quiet but significant transformation as simulation based methods move from approximate Bayesian computation toward neural architectures that bypass likelihood evalua Mar 22, 2026 · TR Mar 22, 2026Beyond Similarity: How Counterfactual Retrieval Reshapes Visual In-Context LearningVision language models have achieved remarkable proficiency in multimodal tasks, yet they remain fundamentally correlation engines. When confronted with fine grained visual reasoning requiring disentanglement of specific Mar 22, 2026 · TRTamamen Spiking Nöronlarla İnşa Edilmiş Varyasyonel Otoenkoder: Sürekli Gizli Uzayların Ayrık Zamansal Süreçlere Dönüşümü Giriş Yapay sinir ağlarında (ANN) son on yıl yaşanan gelişmeler, bilgisayarlı görü ve doğal dil işleme alanlarında çığır açan başarılar elde etmemizi sağladı. Ancak bu başarı, önemli bir bedele yol açıyor: hesaplama kay Mar 22, 2026Fully Spiking Variational Autoencoders: Reimagining Latent Spaces Through Temporal StochasticityThe pursuit of energy efficient artificial intelligence has led researchers to reconsider the fundamental representations of information in neural networks. While contemporary deep learning models rely on dense floating Mar 21, 2026 · TRCerrahi Simülasyonda Çok Çözünürlüklü Öğrenme: SurgFormer ve Biyolojik Algının Mekanik Yansımaları Giriş Cerrahi eğitim ve planlama sistemlerinde yumuşak doku mekaniğinin gerçekçi modellenmesi, on yıllardır hesaplamalı biyomekaniğin en temel problemlerinden biri olmuştur. Yüksek sadakatli finite element method (FEM) Mar 21, 2026Hierarchical Predictive Coding for Surgical Simulation: Bridging Biomechanics and Biological PerceptionThe gap between high fidelity biomechanical simulation and interactive clinical utility remains one of the persistent bottlenecks in computational surgery. Finite Element Methods (FEM) provide gold standard accuracy for Mar 21, 2026 · TRSürekli Adaptasyon ve Öğrenme Plastisitesi: Fast TRAC ve Parametre-Bağımsız Optimizasyonun Yaşam Boyu Pekiştirmeli Öğrenmedeki Rolü Giriş Yaşam boyu pekiştirmeli öğrenme (lifelong reinforcement learning), bir yapay ajanın çevresiyle sürekli etkileşim halindeyken, art arda gelen ve istatistiksel özellikleri değişen görevleri (distribution shifts) baş