The Archive

As more teams move from humanoid robot bring-up to task-specific skill development, the need for repeatable development workflows is growing. Building humanoids... As more teams move from humanoid robot bring-up to task-specific skill development, the need for repeatable development workflows is growing. Building humanoids remains complex, and today’s development pipelines are still highly fragmented. As a result, developers spend significant time configuring robotics infrastructure before they can focus on building robot capabilities. Source

RMISC corpus evaluates time series foundation models pretrained on real-world multivariate data versus synthetic alternatives.

Method detects and aborts failing LLM agent episodes early via hidden activation probes, reducing inference compute waste.

Industrial machinery generates more alarms than technicians can triage. For each important alarm requiring follow-up, the technician pulls historical context,... Industrial machinery generates more alarms than technicians can triage. For each important alarm requiring follow-up, the technician pulls historical context, determines the correct procedure, checks whether a specialist signal confirms the failure mode, and writes up a recommendation. This process remains consistent, and is well-suited for an AI agent. This post discusses a per-alarm… Source

Spectrum is one of the most valuable assets in wireless communications. Over the last 30 years, telecom operators in the US have spent more than $240B to... Spectrum is one of the most valuable assets in wireless communications. Over the last 30 years, telecom operators in the US have spent more than $240B to acquire wireless spectrum. A goal of a radio access network (RAN) system is to extract the maximum spectral efficiency (bits/second/Hertz) possible, which translates into more capacity, stronger network resilience with fewer dropped packets… Source

EntroPath recovers manifold geometry via maximum-entropy random walk ensembles, improving on locally-normalized and shortest-path baselines.

Pitwall generates faithful Formula 1 race strategy briefings in real-time by verifying claims against probabilistic race simulation.

Multi-agent DRL battery management system optimizes renewable energy integration in Irish dairy farms via dynamic pricing.

AirflowAttack: first adversarial attack on infrared remote-sensing VLMs using thermal-airflow perturbations, achieving high zero-shot transferability.

Empirical study of poisoning attack resilience in 3D point cloud datasets augmented for autonomous vehicles, examining backdoor injection and misclassification risk.

DataGovBench: benchmark for LLM data analysis on real-world multi-tabular government datasets with Table QA and Table Insight tasks.

PACR-Video: parameter-efficient framework for long video generation using low-rank temporal adapters and prompt routing, without fine-tuning diffusion models.

Physics-informed neural network framework for elastodynamic wave propagation in bimaterial systems using Split Hopkinson Pressure Bar configuration.

sqlite-migrate 0.2 retires the library in favor of sqlite-utils 4.0 compatibility shim.

Theoretical PAC-learning analysis of quantum machine learning separations for predicting quantum many-body system dynamics.

Anthropic’s Claude Cowork is now available on web and mobile for Max subscribers. Until now, Cowork largely lived on a user’s laptop. With the update, users can start a task from their desk, get status updates on their phone, and pick up the finished output later — even if their laptop is closed.

WordVoice: LLM-based TTS system with explicit word-level acoustic control for audiobook and video dubbing applications.

github-code Web Component uses GPT-5.5 to embed GitHub code snippets with line ranges.

It's early, but the plan is to reduce dependency on Nvidia and Huawei.

Question-type-specific LLM framework for BioASQ 14b improves biomedical QA robustness via answer-type-aware inference pipelines.

Danus orchestration system coordinates parallel mathematical reasoning agents using shared fact-graph memory for research-level proof search.

Study identifies localization gaps in VLMs used as condition encoders for diffusion image editing in multi-entity scenes.

Multi-agent system automates H. pylori case finding from gastric biopsy reports with evidence linking and contextual assertion/negation handling.

TILDE method enables concept unlearning in text-to-image diffusion models while preserving benign generation quality and diversity.

Experimental design framework quantifies variability and factors in LLM coding agents' autonomous model discovery via stochastic evaluation.

sqlite-utils 4.0 ships with database schema migration support.

RuBench 1.0 repository-level coding benchmark with 25 natively-authored Russian task specifications across Python, PHP, TypeScript, JavaScript projects.

ExplAIner declarative query language enables uniform specification and analysis of explainability notions for Boolean classification model interpretability.

SCENT multimodal framework bridges vision and olfaction via language guidance from VLMs for scene-smell alignment beyond visible cues.

Perspective article defines world models as environment simulators, discusses key technical aspects, and charts staged research roadmap across AI subfields.