Which ‘AI scientist’ suits your lab? A guide for the perplexed
Post Content
arXiv:2607.06624v1 Announce Type: new Abstract: We present AgentLens, a production-assessed benchmark for interactive code agents. Most code-agent benchmarks reduce a…
arXiv:2607.06202v2 Announce Type: replace-cross Abstract: The deployment of Mixture-of-Experts (MoE) models on production high-bandwidth superpods, such as NVIDIA’s NVL72/576 and…
arXiv:2607.07338v1 Announce Type: cross Abstract: Nonlinear dynamics is ubiquitous in nature, ranging from chemical pattern formation to ocean circulation, yet…
arXiv:2607.07330v1 Announce Type: cross Abstract: Hypergraph neural networks have shown powerful capability in modeling higher-order relations, yet their predictive uncertainty…
arXiv:2607.05835v2 Announce Type: replace-cross Abstract: For every loopless matroid $M$ and every Feichtner–Yuzvinsky building set $mathcal{G}$ containing the top flat,…
arXiv:2607.05456v1 Announce Type: new Abstract: While recent advances in large language models have enabled end-to-end automated manuscript generation, existing systems…
arXiv:2607.05352v2 Announce Type: replace-cross Abstract: We introduce the first multiplayer world model for highly dynamic environments governed by complex physical…