arXiv:2606.15903v2 Announce Type: replace-cross Abstract: Where an LLM sits in an agent memory pipeline — between the recall plane that…
arXiv:2606.17867v1 Announce Type: cross Abstract: Despite increasing adoption of multimodal approaches in Alzheimer’s Disease (AD) research — aimed at integrating…
arXiv:2606.17872v1 Announce Type: cross Abstract: Large language models (LLMs) outperform earlier architectures on generative inference and long-context tasks, but their…
arXiv:2606.16590v2 Announce Type: replace-cross Abstract: Exploration in deep reinforcement learning (RL) is commonly implemented as temporally uncorrelated white noise. However,…
arXiv:2606.17209v1 Announce Type: new Abstract: Test-time scaling for agentic search typically increases depth (i.e., more turns and tokens per trajectory)…
arXiv:2606.16112v1 Announce Type: cross Abstract: Residual architectures are ubiquitous in deep learning, but they suffer from a subtle structural limitation:…
arXiv:2606.16127v1 Announce Type: cross Abstract: The worldwide surge of authoritarianism, combined with the increasing central role in users’ everyday lives,…
arXiv:2606.14238v2 Announce Type: replace-cross Abstract: Safety certification of Vision-Language-Action (VLA) driving planners under ISO 21448 (SOTIF) rests on an Operational…
arXiv:2606.14838v1 Announce Type: new Abstract: How to define a good explanation is a long-standing philosophical debate which has found recent…
arXiv:2512.07212v3 Announce Type: replace Abstract: Imitation learning with diffusion models has advanced robotic control by capturing the multi-modal action distributions.…
