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 12 of 59

May 17, 2026Augmenting Scientific Creativity: When Large Language Models Bridge Disciplinary SilosThe history of reinforcement learning offers a humbling lesson in scientific humility. What we now regard as a foundational paradigm within machine learning did not emerge from a single disciplinary breakthrough. Instead May 17, 2026 May 17, 2026The Tsallis Loss Continuum: Rethinking Commitment in Reasoning Model Training Introduction The post-training adaptation of large language models to reasoning tasks remains fraught with mechanical instability. When we attempt to teach models to generate latent computational trajectories, such as c May 17, 2026Disentangling Light from Matter: Appearance Decomposition in Multi-Traversal Neural ReconstructionThe construction of photorealistic digital twins for autonomous driving simulation presents a fundamental tension in computer vision. We desire geometric consistency across multiple captures of the same location, yet we May 16, 2026The Illusion of Objectivity in Chain-of-Thought Faithfulness MetricsIs DeepSeek-R1 39% faithful, 75% faithful, or 95% faithful? According to recent work by Richard J. Young in "Measuring Faithfulness Depends on How You Measure: Classifier Sensitivity in LLM Chain-of-Thought Evaluation," May 16, 2026Streaming Intelligence: How AURA Enables Continuous Visual UnderstandingVideo Large Language Models have traditionally functioned as retrospective analysts, examining complete video clips after capture to generate captions or answer questions. This offline paradigm, while effective for archi May 16, 2026PhyCo: Embedding Controllable Physical Laws into Video Diffusion ModelsModern video diffusion models have achieved remarkable fidelity in visual appearance, synthesizing photorealistic textures, coherent lighting, and fluid camera motions. Yet these models remain fundamentally detached from May 16, 2026The Hidden Architecture of Clear Speech: Why Targeted Timing Trumps Global SlowingWhen humans attempt to make themselves understood to non-native listeners or in noisy environments, the instinctive strategy is almost universal: slow down. Parents speak to children with elongated vowels, teachers addre May 16, 2026When Perfect Recall Becomes a Liability: The Memory Curse in Multi-Agent LLM Systems Introduction The prevailing wisdom in artificial intelligence suggests that expanding an agent’s context window represents unambiguous progress. More memory, after all, should enable richer context, stronger relationshi May 16, 2026 May 16, 2026Beyond Conditional Optimization: The Case for Pre-train Space Reinforcement Learning Introduction The recent success of DeepSeek-R1 and similar systems has cemented reinforcement learning with verifiable rewards (RLVR) as the dominant paradigm for enhancing reasoning capabilities in large language model May 16, 2026Depth in Recurrent Networks: Beyond the Composition of NonlinearitiesThe conventional wisdom regarding depth in neural networks is firmly rooted in the feedforward setting. In multilayer perceptrons, depth enables complexity through the composition of nonlinear transformations; each layer May 16, 2026Anticipatory Planning in Multimodal Agents: Bridging High-Level Reasoning and Executable ActionCurrent multimodal agents excel at perceiving visual interfaces and executing individual commands, yet they struggle with multi-step tasks requiring sustained coherence. The paper "Anticipatory Planning for Multimodal AI May 16, 2026Conditioning Protein Generation via Hopfield Pattern Multiplicity: Mechanistic Control in Low-Data Protein Design Introduction The generation of novel protein sequences with specific functional properties remains a formidable challenge in computational biology, particularly when working with families containing only tens to hundred May 16, 2026Reconstructing the Unseen: How Opportunistic Motion Enables Detailed 3D Perception from Sparse Cameras Introduction The reconstruction of high fidelity 3D geometry and appearance remains one of the central challenges in computer vision. While neural rendering techniques such as Neural Radiance Fields (NeRF) and 3D Gaussi May 16, 2026Meta Learning Control with Finite Time Guarantees: Navigating the Complexity of Iterative Adaptation Introduction The deployment of autonomous systems across diverse operational environments presents a fundamental challenge to classical control theory. While traditional adaptive control methods excel at tracking slowly May 15, 2026Beyond Verbalization: Reassessing Chain-of-Thought Faithfulness Through the Lens of Compression and Causal MediationThe prevailing narrative in large language model interpretability has taken a skeptical turn regarding Chain-of-Thought (CoT) reasoning. Recent studies using hint injection methods have painted a troubling picture: model May 15, 2026Latent Grammar Flow: Bridging Discrete Structure and Continuous Dynamics in ODE DiscoveryThe quest to infer governing equations from observational data sits at the intersection of machine learning and scientific discovery. While deep neural networks excel at prediction, they often function as black boxes, of