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 26 of 59

Apr 26, 2026Aligning Generative Models with Reality: Adversarial Distribution Alignment for Scientific DiscoveryThe persistent chasm between computational simulation and experimental observation defines one of the central methodological challenges in modern computational science. While molecular dynamics simulations provide comple Apr 26, 2026Context Unrolling and the Geometry of Multimodal ThoughtMost contemporary multimodal systems operate as sophisticated translators. They ingest inputs from one modality, compress them through a shared bottleneck, and emit outputs in another, often treating the intermediate rep Apr 25, 2026Algorithmic Advice in the Courtroom: Reassessing the Integration of AI in Judicial Decision Making Introduction The deployment of artificial intelligence in criminal justice systems has moved from speculative fiction to institutional reality. Across jurisdictions in the United States and beyond, judges now encounter Apr 25, 2026Multi Granularity Knowledge Transfer in Continual Reinforcement Learning: A Hierarchical Approach to LLM Guided ControlContinual Reinforcement Learning (CRL) represents one of the most challenging frontiers in artificial intelligence research. Unlike the standard reinforcement learning paradigm, where agents optimize for a single station Apr 25, 2026Selective Conciseness: Multi-Agent Approaches to Efficient Chain-of-Thought ReasoningThe emergence of Large Reasoning Models (LRMs) has fundamentally altered our approach to complex problem solving in artificial intelligence. Models such as OpenAI's o1 series and DeepSeek-R1 demonstrate that enabling lan Apr 25, 2026Order Matters: How Flexible Sequencing Unlocks Autoregressive Models for Visual Classification Introduction The resurgence of generative modeling has produced remarkable systems capable of synthesizing photorealistic imagery, yet the discriminative potential of these models remains comparatively underexplored. Wh Apr 25, 2026Selective Memory in Spatial AI: How LingBot-Map Reshapes Streaming 3D ReconstructionThe human brain does not store every photon that hits the retina. Instead, it maintains a sparse, structured representation of space: a sense of where we are relative to a fixed landmark, a vivid memory of the immediate Apr 25, 2026The Localization of Personality in Neural Space: Why Controlling Representations Does Not Fully Control Behavior Introduction Large language models now routinely exhibit behaviors that appear to reflect stable individual differences. When prompted appropriately, they can simulate distinct conversational styles, value orientations, Apr 25, 2026Cross-Lingual Language Model Pretraining: Unifying Multilingual Representation Through Shared Vocabulary and Joint TrainingThe dominance of English in natural language processing research has long created a distorted view of model capabilities. While monolingual pretraining approaches such as GPT and BERT demonstrated remarkable transfer lea Apr 25, 2026SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement LearningThe reinforcement learning paradigm in robotics has long been constrained by the reward engineering bottleneck. While foundation models promise to abstract away task specific programming, their deployment as reward signa Apr 25, 2026The Medical Moravec's Paradox: Why Vision-Language Models Fail at Clinical Triage Introduction Modern Vision-Language Models (VLMs) can generate radiology reports that appear clinically coherent, answer complex diagnostic questions, and engage in multi-step reasoning over medical images. Yet these sa Apr 25, 2026Semantic Drift in Medical Imaging: When Model Explanations Diverge Without Accuracy Loss Introduction Transfer learning has become the de facto standard for medical image classification, offering reliable performance gains across radiological tasks. Yet a troubling question remains largely unexamined in cli Apr 25, 2026Decomposing the Black Box: A Theoretical Analysis of How LLMs Understand and ReasonThe apparent cognitive sophistication of Large Language Models presents a striking paradox. These systems are trained exclusively on next-token prediction, yet they exhibit capabilities suggesting genuine comprehension, Apr 25, 2026Agentic Aggregation: Treating Consensus as an Investigation Rather Than a VoteThe pursuit of scaling test-time compute has fundamentally altered how we conceptualize intelligence in large language models. Where once we focused exclusively on training larger models, recent work by Wei et al., Snell Apr 24, 2026 Apr 24, 2026DriveTok: Reconciling Geometry and Semantics in Autonomous Driving Through Unified 3D Tokenization Introduction The autonomous driving community is witnessing a fundamental architectural shift. As the field moves from modular perception pipelines toward end-to-end reasoning systems, the representation of visual input Apr 24, 2026Absolute Relevance in Attention: How Screening Challenges the Softmax Paradigm Introduction Standard softmax attention has dominated deep learning for nearly a decade, yet a fundamental limitation has persisted largely unchallenged until now. The mechanism relies exclusively on relative relevance; Apr 24, 2026Neural Garbage Collection: When AI Learns to Manage Its Own MemoryThe current generation of reasoning models has demonstrated that extended chains of thought enable remarkable problem solving capabilities, yet this capability comes with a steep computational price. As models think long