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 5 of 59

Jun 3, 2026Occupancy Prediction Without Training: A Closer Look at FreeOcc Introduction For an embodied agent to navigate and interact with its surroundings, it needs more than a sparse point cloud. It needs a dense, semantically labeled understanding of where space is occupied, where it is fr Jun 3, 2026When Driving Models Memorize Instead of Generalize: A Look at Fail2Drive Introduction One of the more uncomfortable truths in autonomous driving research is that we rarely know whether a model has learned to drive or merely learned to pass a test. The distinction matters enormously. A system Jun 3, 2026Why Tokenization, Not the Objective, May Be the Real Bottleneck in Wearable SSLFor the past several years, the wearable sensing community has treated self-supervised learning as a contest of objectives. Should we use contrastive learning, masked reconstruction, or augmentation prediction? Each year Jun 3, 2026Translation Without a Rosetta Stone: How Unsupervised NMT Learns From Monolingual Text AloneWhen I first read "Unsupervised Neural Machine Translation" by Artetxe, Labaka, Agirre, and Cho (ICLR 2018), I had to reread the experimental section twice. The claim seemed to violate a foundational assumption of the fi Jun 2, 2026Who Asks the Questions: SymptomAI and the Case for Active Clinical Interviewing in Medical LLMs Introduction When we evaluate medical language models, we tend to ask a narrow question: can the model reason correctly given a complete clinical picture? Benchmarks like MedQA, archival case challenges, and curated vig Jun 2, 2026Reauthoring the Camera: How Vista4D Turns Monocular Video Into a 4D SceneMost of us think of a video clip as a finished object. The camera moved the way it moved, the lens did what it did, and whatever was outside the frame is simply gone. The premise behind Vista4D: Video Reshooting with 4D Jun 2, 2026When Agents Optimize Attacks: What Claudini Tells Us About Automated Adversarial Research Introduction There is a particular kind of research result that forces you to update your priors not because the method is novel, but because it works far better than the framing suggested it should. The paper Claudini: Jun 2, 2026Breaking the Speed-Accuracy Tradeoff in Shapley Interaction Estimation Introduction Cooperative game theory has quietly become the standard mathematical language for explaining machine learning models. When we want to know how much a single feature contributes to a prediction, or how much Jun 2, 2026Lifelong Reinforcement Learning: Why the Reset Button Breaks the Theory Introduction Most of the reinforcement learning we discuss in research papers and deployment write-ups shares a hidden assumption so deeply embedded that we rarely question it: the episode. We define a task, the agent i Jun 2, 2026Why Curiosity Forgets: Persistent Worlds and Episodic Memory for 3D ExplorationCuriosity-driven reinforcement learning carries an appealing premise. Instead of waiting for sparse external rewards in long-horizon tasks, an agent generates its own intrinsic motivation from surprise, the gap between w Jun 2, 2026Sampling Without the Network: A Look at Conditional Diffusion Sampling Introduction Drawing independent samples from an unnormalized, multimodal probability distribution is one of those problems that looks deceptively simple on paper and turns out to be a persistent bottleneck across machi Jun 2, 2026Opening the Black Box of Protein Folding: Sparse Autoencoders Meet ESMFoldProtein language models have become the workhorses of computational structural biology. Models like ESM2 and the structure prediction systems built on top of them, such as ESMFold, can map an amino acid sequence to a thr Jun 2, 2026When Explanations Become Sensors: Reasoning Consistency as a Safety Monitor in Driving VLAsVision-Language-Action models occupy an unusual position in the autonomous driving stack. Unlike purely reactive planners that map sensor inputs to control commands through opaque feature hierarchies, VLAs are designed t Jun 2, 2026Generating Audio Without a Tokenizer: What WavFlow Tells Us About CompressionFor the last several years, the recipe for generating audio with neural networks has been remarkably consistent. Take a raw waveform, compress it into a latent representation using a pretrained variational autoencoder or Jun 2, 2026Why Brightness Tweaks Lie to You: Counterfactual Stress Testing for Medical Image ClassifiersWhen a medical imaging model passes its validation set with flying colors, the temptation is to declare victory and move toward deployment. Anyone who has watched a model crumble on data from a new hospital knows how pre Jun 2, 2026Version Control for Agents: What Shepherd Gets Right About Meta-AgentsWhen I first read the abstract for Shepherd: A Runtime Substrate Empowering Meta-Agents with a Formalized Execution Trace, the phrase that stuck with me was not any of the benchmark numbers. It was the quiet structural c Jun 1, 2026Thinking Without Words: When Models Invent Their Own Compressed LanguageReasoning models have settled into a comfortable but expensive habit. To solve a hard math problem or trace a multi-hop question, a large language model produces a long natural language chain-of-thought, often hundreds o Jun 1, 2026Composition as Continual Learning: A Look at Self-Composing Policies Introduction Continual reinforcement learning sits at an uncomfortable intersection of two desirable but often conflicting properties: the ability to retain what was learned on previous tasks, and the ability to keep le