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 35 of 59

Apr 12, 2026The Universal Signature of Memorization: Why Architectural Innovation Cannot Escape Privacy Leaks Introduction Membership inference attacks have long occupied an uncomfortable middle ground in machine learning privacy. For language models, we have relied on hand-crafted heuristics; thresholding perplexity, measuring Apr 12, 2026Foveated Diffusion: Aligning Generative Compute with Human PerceptionDiffusion and flow matching models have achieved remarkable capabilities in visual synthesis, yet their deployment for interactive applications remains constrained by fundamental computational limits. The attention mecha Apr 12, 2026Frequency-Aware Token Compression: Reconciling Generation and Discrimination in Diffusion ModelsDiffusion models have evolved from pure generative tools into dual-purpose computational substrates. In medical imaging workflows, the same backbone that synthesizes counterfactual lesions for data augmentation also prov Apr 12, 2026Prediction-Powered Inference and the Difference Estimator: Uncovering Survey Sampling RootsThe proliferation of large language models as measurement instruments has reignited a classical statistical problem. Researchers now routinely use models to code text, classify images, or score essays, generating predict Apr 12, 2026Structural Causal Bottleneck Models: Targeted Dimension Reduction for Causal InferenceHigh-dimensional causal inference faces a fundamental tension. On one hand, real-world phenomena from neural population dynamics to climate teleconnections naturally involve high-dimensional random vectors interacting ac Apr 12, 2026Rethinking Vector Field Learning for Generative Segmentation: An Optimization Dynamics Perspective Introduction The apparent universality of diffusion models has prompted researchers to apply them to virtually every computer vision task imaginable. Yet while these models excel at synthesizing continuous visual data, Apr 12, 2026When Federated Learning Grows a Nervous System: On the Agentic Turn in Distributed AIFor decades, Federated Learning (FL) has operated like a rigid bureaucracy. The central server issues commands; clients execute them; models aggregate through fixed protocols. This mechanical elegance, first formalized b Apr 11, 2026Episodic Memory for Perceptually Aliased Robotic Manipulation: A Deep Dive into Chameleon Introduction: The Shell Game Challenge Consider the classic shell game. Three identical cups sit on a table; a ball is placed under one; the cups are swapped repeatedly. When the robot finally reaches to grasp a cup, th Apr 11, 2026Endogenous Chain-of-Thought: Why Diffusion Models Need to Think During GenerationDiffusion models have achieved remarkable fidelity in visual synthesis, yet they remain brittle when confronted with tasks demanding structured logical reasoning. While Multimodal Large Language Models (MLLMs) have been Apr 11, 2026GSMem and the Geometry of Memory: Why 3D Gaussian Splatting Changes Embodied AI The Memory Bottleneck in Embodied Navigation Contemporary embodied AI systems have achieved remarkable proficiency in path planning, natural language instruction following, and high-level reasoning. Yet beneath these ca Apr 11, 2026The Routing Distraction Phenomenon: Why Multimodal MoEs See Without Thinking Introduction The recent paper "Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts" by Xu et al. identifies a subtle yet critical failure mode in large vision-language models that demands our a Apr 11, 2026Beyond Retrieval: Training Agents to Reason for Visual CreationModern text-to-image models produce photorealistic outputs, yet they remain fundamentally constrained by frozen parametric knowledge acquired during pretraining. When prompted to depict recent public figures, newly relea Apr 11, 2026The Silent Architect of Convergence: How Early Replay Buffer Composition Shapes Policy Quality in Continuous State RL Introduction The deployment of Deep Q Networks and their variants to continuous state spaces represents one of the foundational achievements of modern reinforcement learning. Yet beneath the apparent simplicity of apply Apr 11, 2026Bridging the Bayesian Divide: Hybrid Extended Object Tracking with LEO Introduction The autonomous driving community has long oscillated between two epistemological poles. On one side stand classical Bayesian trackers, which encode physical priors through rigid state-space models and offer Apr 11, 2026Matryoshka Gaussian Splatting: Rethinking Level of Detail Through Stochastic TrainingThe deployment of photorealistic neural rendering at scale faces a fundamental constraint. Computational budgets vary across orders of magnitude, from high end GPU workstations to mobile devices and mixed reality headset Apr 11, 2026 Apr 11, 2026Semantic Invariance in Agentic AI: When Scale Fails and Small Models Outperform Introduction As Large Language Models increasingly migrate from chat interfaces to autonomous agentic systems, the evaluation criteria governing their deployment must evolve beyond simple accuracy metrics. We are no lon Apr 11, 2026