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 2 of 59

Jun 7, 2026When the Name Changes the Answer: Surface Forms and the Limits of Memorization Benchmarks Introduction If you ask a large language model what sport Pelé played, you will almost certainly get the right answer. If you ask the same model about Edson Arantes do Nascimento, the legal name of the very same person, Jun 7, 2026Beyond "Looks Nice": Structuring Video Aesthetics into Measurable RewardsVideo generation has reached a point where photorealism is no longer the bottleneck. Models like Wan2.2, Seedance, and HunyuanVideo can produce clips that pass casual inspection. The harder problem, the one that separate Jun 7, 2026Tracing Motion Instead of Painting Pixels: Sparse Trajectory Prediction for World ModelsWhen we imagine how a scene might unfold, we do not hallucinate every pixel of every intervening frame. We picture a few salient things moving: the ball rolling toward the pocket, the cup tipping, the person stepping off Jun 7, 2026Attribute Binding as a Control Problem: Reading FOCUS Through the Lens of Optimal ControlText-to-image models have become remarkably good at rendering a single subject with a specified set of attributes. Ask for "a red apple on a wooden table" and you will likely get exactly that. But ask for "a red apple an Jun 7, 2026The Caricature Gap: Why Synthetic Political Text Fails at the Population Level, Not the Sentence LevelMost of the energy in AI-generated text detection has gone into the wrong place. We have built classifiers that hunt for perplexity anomalies, burstiness signatures, and token-level irregularities, treating the problem a Jun 7, 2026Reading the Plan Before the Picture: How Video Models Reason Through MazesWhen we talk about video diffusion models, we usually describe what they produce: high fidelity, temporally coherent clips that capture motion and, increasingly, something resembling physical intuition. What we talk abou Jun 7, 2026Object Permanence Meets Scene Graphs: A Look at World Scene Graph GenerationMost of us learned about object permanence in an introductory psychology class. An infant who cannot yet grasp that a toy still exists once it disappears behind a blanket will lose interest in it entirely; a slightly old Jun 7, 2026Reading the Black Box: How Disentangled Neural Architecture Search Turns Interpretability into Efficiency Introduction Neural architecture search has produced some of the strongest vision and language models of the past several years, yet the process by which these architectures are discovered remains stubbornly opaque. A c Jun 7, 2026When Agency Beats Intelligence: What the Conjunctive Handicap Tells Us About Scientific Reasoning in Humans and LLMsCausal reasoning sits at the heart of what we usually call intelligence. We predict, explain, and intervene in the world precisely because we can build mental models of what causes what. A long line of work in cognitive Jun 7, 2026Why Vision Language Models Fail at Reading Human EmotionsVision language models have become remarkably good at a wide range of visual tasks. They can describe scenes, ground complex textual queries, read charts, and reason about spatial relationships. So it is striking that wh Jun 6, 2026Rethinking Expert Allocation in MoE: Why Every Layer Should Not Own Its Own Experts Introduction Mixture-of-Experts (MoE) architectures have become the standard tool for scaling language models beyond the point where dense computation remains tractable. The appeal is straightforward: route each token t Jun 6, 2026Scaling the Harness: Why Agent Performance Lives in the System, Not Just the ModelThe default narrative about AI progress has been simple: make the model bigger, feed it more data, refine the post-training, and watch the benchmark numbers climb. For agentic AI, that narrative has quietly stopped being Jun 6, 2026Why Video Foundation Models Might Be the Missing Piece in Robot ManipulationRobotic manipulation sits at an awkward intersection. The robot acts in three dimensions and over time, yet most of the policies we train on it perceive the world through flat, static lenses. We feed them 2D images, ofte Jun 6, 2026The Economics of Staying Awake: How Zero-Cost Monitoring Makes 24/7 Autonomous Research ViableThe conversation around LLM research agents has fixated almost entirely on intelligence. Can the model form a good hypothesis? Can it write correct code? Can it interpret an ablation? These are reasonable questions, but Jun 6, 2026When the Headline Number Lies: What Commercial Chatbots Get Wrong About the NewsAI chatbots have quietly become a primary interface between the public and current events. By late 2025, ChatGPT alone reported 800 million weekly active users, and surveys suggest roughly one in ten US adults already co Jun 6, 2026Reasoning Without Training: Why Where You Cut Matters More Than How Much You SearchThe dominant story of the last two years of language model progress has been reinforcement learning. Take a capable base model, apply RLHF or RLVR with verifiers and curated datasets, and watch its performance on mathema Jun 6, 2026Two Graphs for Mathematical Discovery: What COMPOSE Gets RightWhen we ask a language model to imagine the next theorem a research program might produce, we are really asking two different questions at once. The first is a question of direction: given where a field has been going, w Jun 6, 2026Learning Without Weights: How CORE Distills Reasoning Insights From ContrastMost of the recent progress in getting language models to reason better has come from throwing compute at the problem. Reinforcement learning from verifiable rewards (RLVR), exemplified by methods like GRPO, can produce