Neuromorphic Cybersecurity with Semi-supervised Lifelong Learning
arXiv:2508.04610v2 Announce Type: replace-cross Abstract: Inspired by the brain’s hierarchical processing and energy efficiency, this paper presents a Spiking Neural…
Real-Time Iteration Scheme for Diffusion Policy
arXiv:2508.05396v1 Announce Type: cross Abstract: Diffusion Policies have demonstrated impressive performance in robotic manipulation tasks. However, their long inference time,…
Echo: Decoupling Inference and Training for Large-Scale RL Alignment on Heterogeneous Swarms
arXiv:2508.05387v1 Announce Type: cross Abstract: Modern RL-based post-training for large language models (LLMs) co-locate trajectory sampling and policy optimisation on…
Symmetric Behavior Regularization via Taylor Expansion of Symmetry
arXiv:2508.04225v2 Announce Type: replace-cross Abstract: This paper introduces symmetric divergences to behavior regularization policy optimization (BRPO) to establish a novel…
MI9 — Agent Intelligence Protocol: Runtime Governance for Agentic AI Systems
arXiv:2508.03858v1 Announce Type: new Abstract: Agentic AI systems capable of reasoning, planning, and executing actions present fundamentally distinct governance challenges…
Self-Questioning Language Models
arXiv:2508.03682v2 Announce Type: replace-cross Abstract: Can large language models improve without external data — by generating their own questions and…
Deep Learning-based Scalable Image-to-3D Facade Parser for Generating Thermal 3D Building Models
arXiv:2508.04406v1 Announce Type: cross Abstract: Renovating existing buildings is essential for climate impact. Early-phase renovation planning requires simulations based on…