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 3 of 59

Jun 6, 2026When Supervision Is Unequal: Rethinking Federated Learning for Medical SegmentationFederated learning has a quiet assumption baked into most of its benchmarks: that every participating institution annotates its data in roughly the same way. You collect a few hospitals, each contributes pixel-level segm Jun 6, 2026Showing, Not Telling: How ITI-GEN Makes Diffusion Models Inclusive Without RetrainingText-to-image models have a representation problem that is by now well documented. Ask Stable Diffusion for "a headshot of a person" and you receive a strikingly narrow slice of humanity. The model has internalized the s Jun 6, 2026Thinking in Modality: How Archon Reframes Chain-of-Thought for Digital HumansThe phrase that stuck with me after reading Archon: A Unified Multimodal Model for Holistic Digital Human Generation was not "unified" or "holistic," both of which appear in nearly every multimodal paper these days. It w Jun 6, 2026When Evidence Disagrees: How CARE Splits Clinical Reasoning to Preserve Both Privacy and Accuracy Introduction Most benchmarks for medical language models reward a quiet kind of cheating. When a patient's reported symptoms, bedside narrative, and structured vitals all point in the same direction, a model can succeed Jun 5, 2026Spending Noise Where It Matters: A Look at Colored Noise Diffusion SamplingDiffusion models have become the default tool for high-fidelity image synthesis, but a surprising amount of the action happens not in the network architecture or training objective but in the sampler. The numerical proce Jun 5, 2026When Passing Tests Is Not Enough: Lessons from a Physicist Supervising an AI Coding AgentThe question of whether AI agents are tools, collaborators, or autonomous researchers tends to be argued in the abstract. A recent case study, "Physics Is All You Need? A Case Study in Physicist-Supervised AI Development Jun 5, 2026When Your Chatbot Has a Sponsor: Conflicts of Interest in Advertising LLMsThe transition of large language models from pure assistants to revenue-generating products is happening faster than most people realize. With OpenAI reportedly introducing advertisements into ChatGPT, the relationship b Jun 5, 2026Why the Whole Pipeline Matters: Lessons from VLA FoundryRobotics foundation models have made progress at a pace that few predicted even three years ago. Yet behind the demos of robots folding laundry or sorting groceries lies a software engineering problem that rarely gets di Jun 5, 2026Compressing 3D Scenes for Vision-Language Models: A Closer Look at Proxy3DSpatial intelligence remains one of the more stubborn gaps in multimodal large language models. A model can describe a photograph with impressive fluency, yet ask it to reason about the relative positions of objects in a Jun 5, 2026When the Right Answer Is There but Loses: Arbitration Failures in Audio-Language Models Introduction Consider a deceptively simple scenario. An audio-language model (ALM) is given a recording in which an alarm is clearly audible. Alongside that audio, the model receives a written context stating that no al Jun 5, 2026Bridging Reasoning and Masks: A Close Look at InstructSAMWhen users describe what they want segmented in an image, they rarely speak in clean noun phrases. They say "the two largest mugs except the one in front" or "the players most likely to get the ball." These instructions Jun 5, 2026When Random Weights Translate: Lessons from Echo State Neural Machine Translation Introduction There is a quiet assumption baked into most of modern deep learning: that the value of a model lives in its trained weights. We spend enormous compute budgets nudging billions of parameters toward an optimu Jun 5, 2026When the Safety Feature Becomes the Attack Surface: Watermarking Autoregressive Image Generators Introduction Watermarking has become one of the default proposals for managing the externalities of generative models. If we cannot stop synthetic images from flooding the internet, the reasoning goes, we can at least m Jun 5, 2026When Synthetic Data Becomes Indistinguishable: Lessons from GAN-Assisted Microplastic Detection Introduction Microplastic pollution is one of the more insidious environmental problems of the past decade. Particles smaller than five millimeters now appear in drinking water, marine sediments, and human tissue, yet q Jun 5, 2026When Simpler Predictors Win: A Look at Bilinear Interpretable NAS Introduction Neural Architecture Search has spent much of its history chasing accuracy through increasingly elaborate machinery. Early reinforcement learning and evolutionary methods consumed GPU-years to find competiti Jun 5, 2026Why Best-of-N Plateaus: The Entropy Shell and the Case for Bidirectional SearchWhen we sample from a language model to solve a hard problem, the intuition is straightforward: draw more samples, and eventually one of them will be correct. This belief underlies best-of-N sampling and most of the tree Jun 4, 2026Neutrality as Consistency: Rethinking Political Bias in Language ModelsWhen we talk about political bias in large language models, the mental image most people have is of a model arguing for a candidate or refusing to discuss a controversial policy from one side. That image is incomplete. T Jun 4, 2026Cross-View Consensus as a Denoising Prior: Lessons from Modulate-and-Map for 3D Anomaly DetectionWhen we inspect a manufactured part for defects, we usually have more information than we realize. We can move around the object, look at it from different angles, and combine what our eyes see with what we can infer abo