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 11 of 59

May 18, 2026Rethinking Spatial Interpolation: When Deep Reinforcement Learning Meets Inverse Distance Weighting Introduction Spatial prediction remains a fundamental challenge in industrial process modeling. From monitoring chemical concentration gradients across manufacturing floors to predicting equipment wear patterns in distr May 18, 2026Decoupling Skill Acquisition from Consolidation: A New Architecture for Continual Reinforcement Learning Introduction The pursuit of artificial general intelligence in embodied agents hinges on solving a fundamental tension in continual learning. Agents must remain plastic enough to acquire new skills while maintaining sta May 18, 2026From Shannon's Taxonomy to Self-Programming AI: Analyzing the Nemobot Framework for Strategic Game AgentsClaude Shannon, in his seminal 1950 work on machine chess, posed a question that continues to haunt artificial intelligence research: can we program a computer so that eventually 99 percent of its instructions are writte May 18, 2026Intermediate Representations in Multimodal Translation: Analyzing the SignThought FrameworkSign language translation has long suffered from a categorical error in its foundational assumptions. The field historically approached the task as a sequence alignment problem, treating brief video segments as directly May 18, 2026Beyond Tokens: How Positional Encoding Creates a Hidden Attack Surface in Large Language ModelsThe prevailing mental model of backdoor attacks against large language models has remained remarkably consistent since the early days of text classification systems. Security researchers and practitioners have long assum May 18, 2026Exact Gaussian Processes in High Dimensions: Escaping the Curse of Dimensionality Through Structured SparsityGaussian process regression stands as one of the most theoretically principled approaches in machine learning, offering not merely predictions but full probabilistic distributions over functions. Yet this elegance comes May 18, 2026Executable Communication: Weight-Space Collaboration in Multi-Agent LLM SystemsMulti-agent systems built upon large language models have traditionally operated like diplomatic committees. Each agent drafts memos in natural language, appends them to shared transcripts, and awaits responses. This arc May 18, 2026Repository Level Safety Auditing: Detecting Distributed Violations with MeerkatCurrent AI safety monitoring operates like a security checkpoint inspecting individual passengers. Each trace, a complete interaction between user and model, receives independent scrutiny. This approach suffices when har May 18, 2026Detecting the Invisible: Task Boundary Awareness in Online Meta-LearningMeta-learning has traditionally operated within the comfortable confines of curated datasets and clearly delineated tasks. Yet the promise of artificial intelligence that truly adapts like biological intelligence require May 18, 2026Rethinking Hierarchical Inference: The Case for Three Tier ML Pipeline Distribution in Edge AI Introduction The proliferation of Internet of Things devices has fundamentally altered the data processing landscape, generating zettabytes of sensor data that strain traditional cloud centric architectures. Conventiona May 17, 2026From Concept to Layout in 80 Hours: Analyzing Design Conductor 2.0 and the VerTQ AcceleratorThe economics of modern semiconductor design have long followed a brutal calculus. A typical chip tapeout requires 18 to 36 months, costs exceeding $400 million, and teams of hundreds of engineers working from existing d May 17, 2026Token-Level Structure as a First-Class Citizen: Rethinking Clustering for Multivector Retrieval Introduction The transition from lexical to neural information retrieval has introduced a fundamental tension between effectiveness and efficiency. While dense retrievers compress documents into single vectors for fast May 17, 2026Causal Forcing++: Reconciling Efficiency and Alignment in Real-Time Video GenerationThe transition from passive video synthesis to interactive world models represents one of the most consequential shifts in generative AI. As models evolve from batch processors into streaming, controllable environments c May 17, 2026Beyond the Roll Call Vote: Computational Analysis Reveals the Multidimensional Nature of Legislative DiscourseTraditional computational political science has long relied on the tyranny of the roll call vote. From the foundational NOMINATE scores developed by Poole and Rosenthal to contemporary ideal point estimation techniques, May 17, 2026The Mirror Test for Machine Self-Preservation: Analyzing the TBSP BenchmarkInstrumental convergence theory has long predicted that sufficiently capable artificial agents will resist shutdown regardless of their terminal goals. As Omohundro argued in 2008, self-preservation emerges as an instrum May 17, 2026Deep Reinforcement Learning for Lesion Detection: Reimagining Sample Efficiency in Radiological AI Introduction The deployment of artificial intelligence in radiology has encountered a persistent triad of obstacles: the insatiable demand for large annotated datasets, the fragility of models when confronted with domai May 17, 2026Learning the Grammar of Human Movement: A Technical Analysis of Action MotifsHuman behavior modeling has long grappled with a fundamental tension. We need representations that capture the fluid continuity of motion, yet human actions are inherently compositional. The act of "reaching" appears in May 17, 2026CodePivot: Rethinking Multilingual Transpilation Through Python-Centric Bootstrapping Introduction Transpilation, the automated translation of source code between programming languages, represents one of the most practically challenging applications of large language models. While recent advances have en