Physical AI, robots, and autonomous systems
Inspired by Andrej Karpathy's AutoResearch, I built a system where Claude Code acts as an autonomous ML researcher on tabular binary clas...
The idea is called HALO - Hierarchical Autonomous Learning Organism. The core premise is simple: what if instead of just making LLMs bigg...
The idea is called HALO - Hierarchical Autonomous Learning Organism. The core premise is simple: what if instead of just making LLMs bigg...
![[2603.03589] stratum: A System Infrastructure for Massive Agent-Centric ML Workloads](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
Abstract page for arXiv paper 2603.03589: stratum: A System Infrastructure for Massive Agent-Centric ML Workloads
Abstract page for arXiv paper 2603.03977: Right in Time: Reactive Reasoning in Regulated Traffic Spaces
Abstract page for arXiv paper 2603.03546: Real-time loosely coupled GNSS and IMU integration via Factor Graph Optimization
Abstract page for arXiv paper 2603.03953: RVN-Bench: A Benchmark for Reactive Visual Navigation
Abstract page for arXiv paper 2603.03897: IROSA: Interactive Robot Skill Adaptation using Natural Language
Abstract page for arXiv paper 2603.03881: On the Suitability of LLM-Driven Agents for Dark Pattern Audits
Abstract page for arXiv paper 2603.04378: Robustness of Agentic AI Systems via Adversarially-Aligned Jacobian Regularization
Abstract page for arXiv paper 2603.03768: Cognition to Control - Multi-Agent Learning for Human-Humanoid Collaborative Transport
Abstract page for arXiv paper 2603.03753: Agentic Peer-to-Peer Networks: From Content Distribution to Capability and Action Sharing
Abstract page for arXiv paper 2603.03751: Interaction-Aware Whole-Body Control for Compliant Object Transport
Abstract page for arXiv paper 2603.03741: HALyPO: Heterogeneous-Agent Lyapunov Policy Optimization for Human-Robot Collaboration
Abstract page for arXiv paper 2603.03704: Large-Language-Model-Guided State Estimation for Partially Observable Task and Motion Planning
Abstract page for arXiv paper 2603.03701: UrbanHuRo: A Two-Layer Human-Robot Collaboration Framework for the Joint Optimization of Hetero...
Abstract page for arXiv paper 2603.03590: Social Norm Reasoning in Multimodal Language Models: An Evaluation
Abstract page for arXiv paper 2603.03555: Molt Dynamics: Emergent Social Phenomena in Autonomous AI Agent Populations
Abstract page for arXiv paper 2603.03515: The Controllability Trap: A Governance Framework for Military AI Agents
Abstract page for arXiv paper 2603.03818: Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual ...
Abstract page for arXiv paper 2603.03380: LiteVLA-Edge: Quantized On-Device Multimodal Control for Embedded Robotics
Abstract page for arXiv paper 2603.03595: Hybrid Belief Reinforcement Learning for Efficient Coordinated Spatial Exploration
Abstract page for arXiv paper 2603.03378: AOI: Turning Failed Trajectories into Training Signals for Autonomous Cloud Diagnosis
Get the latest news, tools, and insights delivered to your inbox.
Daily or weekly digest • Unsubscribe anytime