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 43 of 59

Mar 31, 2026Beyond Sequential Distance: Rethinking Position Encoding in Multimodal Language ModelsAs Multimodal Large Language Models (MLLMs) evolve from single turn question answering systems into sophisticated agents capable of processing lengthy documents, extended video sequences, and complex interleaved conversa Mar 30, 2026 · TRYaşam Boyu Pekiştirmeli Öğrenmede İstatistiksel BağlamYaşam Boyu Pekiştirmeli Öğrenmede İstatistiksel Bağlam Mar 30, 2026When the World Changes Without Warning: Statistical Context Detection in Lifelong Reinforcement LearningThe promise of lifelong reinforcement learning rests on an assumption so fundamental it often goes unquestioned. We assume that when an agent encounters a new task, it knows that the task has changed. This assumption man Mar 30, 2026 · TRVideo Difüzyon Modellerinin Gizli 3D Bilgisi: VEGA-3D ile Mekansal Öncülleri Açığa Çıkarmak Giriş: Mekansal Körlük ve Yeni Bir Paradigma Multimodal Large Language Models (MLLM'ler) son yıllarda görsel anlama yeteneklerinde kayda değer ilerlemeler kaydetti. Ancak bu modeller halen spatial blindness (mekansal kö Mar 30, 2026The Geometry of Imagination: How Video Generation Models Learn Spatial Structure Without Ever Seeing a Point Cloud Introduction Multimodal Large Language Models have achieved remarkable proficiency in semantic understanding, yet they remain fundamentally spatially blind. When asked to reason about fine-grained geometric relationship Mar 30, 2026 · TR Mar 30, 2026Thermodynamic Response Theory as an Operational Framework for Singular Bayesian ModelsSingular statistical models have long presented a conceptual tension in Bayesian statistics. While mixtures, neural networks, and low-rank factorizations dominate modern machine learning practice, their theoretical analy Mar 30, 2026 · TR Mar 30, 2026Beyond Execution: The Architecture of Scientific Memory in AI AgentsThe current generation of AI agents has largely solved the execution problem in computational materials science. Given a specific simulation task, modern large language models can autonomously plan workflows, configure q Mar 30, 2026 · TR Mar 30, 2026CoCoEvo and the Evolutionary Turn in Automated Code Generation: Beyond the Test Case BottleneckLarge Language Models have transformed software engineering research, yet a persistent structural limitation constrains their practical deployment. Current automated code generation systems typically assume access to pre Mar 30, 2026 · TRCustomTex: Çok Referanslı Özelleştirme ile Yüksek Sadakatli İç Mekan Sahne Tekstürizasyonu Giriş 3D sahne oluşturma ve tekstürizasyon, mimari görselleştirme, sanal gerçeklik ve film prodüksiyonu gibi alanlarda kritik bir rol oynar. Ancak mevcut yöntemlerde karşılaşılan temel sorunlardan biri, dokuların aydınl Mar 30, 2026CustomTex and the Disentanglement of Scene Appearance: Toward Factorized 3D Assets Introduction The generation of photorealistic 3D indoor scenes remains a bottleneck in computer graphics and vision, particularly when user customization enters the equation. While neural reconstruction methods such as Mar 30, 2026 · TR Mar 30, 2026The Amortization of Thought: How Lifelong Learning Agents Learn to Stop Planning Introduction There is a peculiar quality to expertise. Watch a master craftsperson at work, or an athlete in flow, and you will notice a conspicuous absence of hesitation. The chess grandmaster does not calculate every Mar 30, 2026 · TRVahşi Doğada Metrik Ölçek: Görüntüdeki Geometriyi Sayılara Dönüştürmek Giriş Biyoçeşitlilik kaybı ve habitat tahribatı karşısında vahşi yaşam popülasyonlarını izlemek, modern ekoloji ve koruma biyolojisinin en temel görevlerinden biri haline geldi. Bilgisayarlı görü ve uzaktan algılama ala Mar 30, 2026WildDepth: Why Metric Scale, Not Visual Complexity, Limits Wildlife Depth EstimationThe recent WildDepth dataset from researchers at Oxford, University of Cape Town, and UCL challenges a fundamental assumption in computer vision: that depth estimation for wildlife fails primarily because animals are def Mar 30, 2026 · TRKenar Cihazlarda Sürekli Uyum Sağlayan Radyoloji Yapay Zekası: Coreset Geometrisi ve Adaptif Derin Pekiştirmeli Öğrenme Giriş Tıbbi görüntüleme sistemlerinin kenarında, yani MRI veya CT cihazlarının kendisinde çalışan yapay zeka modelleri, modern radyoloji pratiğinin en kritik ihtiyaçlarından biri haline geldi. Bulut tabanlı çözümlerin k