arXiv Artificial IntelligenceAPEX: Adaptive Expert Prefetching for Memory-Efficient Edge MoE Inference
arXiv:2608.11688v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models are attractive for edge…
Curated from international AI laboratories, specialist publications and technology outlets. Last update: 3 hours ago.
arXiv Artificial IntelligencearXiv:2608.11688v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models are attractive for edge…
arXiv Artificial IntelligencearXiv:2608.11681v1 Announce Type: cross Abstract: This work addresses the challenge of open-vocabulary…
arXiv Artificial IntelligencearXiv:2608.11674v1 Announce Type: cross Abstract: On-policy rollout methods such as GRPO are central to…
arXiv Artificial IntelligencearXiv:2608.11669v1 Announce Type: cross Abstract: Reinforcement learning against rubrics, lists of criteria…
arXiv Artificial IntelligencearXiv:2608.11661v1 Announce Type: cross Abstract: A multiplicative dual-encoder network computes a…
arXiv Artificial IntelligencearXiv:2608.11660v1 Announce Type: cross Abstract: Large language models (LLMs) achieve remarkable performance…
arXiv Artificial IntelligencearXiv:2608.11658v1 Announce Type: cross Abstract: Many reinforcement learning systems, from fleet management…
arXiv Artificial IntelligencearXiv:2608.11655v1 Announce Type: cross Abstract: Motion-centric video reasoning is fundamental to…
arXiv Artificial IntelligencearXiv:2608.11632v1 Announce Type: cross Abstract: Persistent AI agents accumulate versioned state across long…
arXiv Artificial IntelligencearXiv:2608.11627v1 Announce Type: cross Abstract: The Relative Transfer Matrix (ReTM), recently introduced as…
arXiv Artificial IntelligencearXiv:2608.11624v1 Announce Type: cross Abstract: Persuasion is a core dynamic of natural language…
arXiv Artificial IntelligencearXiv:2608.11623v1 Announce Type: cross Abstract: Recent advances in Large Language Models (LLMs) have…