arXiv Artificial IntelligenceWhat Fixed-Rollout pass@k Evaluations Can Identify
arXiv:2609.09245v1 Announce Type: cross Abstract: Repeated-sampling evaluations increasingly extrapolate…
Curated from international AI laboratories, specialist publications and technology outlets. Last update: 3 hours ago.
arXiv Artificial IntelligencearXiv:2609.09245v1 Announce Type: cross Abstract: Repeated-sampling evaluations increasingly extrapolate…
arXiv Artificial IntelligencearXiv:2609.09244v1 Announce Type: cross Abstract: The edge-of-chaos condition preserves first-order input…
arXiv Artificial IntelligencearXiv:2609.09243v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) grounds a language…
arXiv Artificial IntelligencearXiv:2609.09242v1 Announce Type: cross Abstract: Large Language Models (LLMs) often generate…
arXiv Artificial IntelligencearXiv:2609.09241v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures have emerged as a…
arXiv Artificial IntelligencearXiv:2609.09240v1 Announce Type: cross Abstract: Ultra-low-bit language models promise reductions in storage…
arXiv Artificial IntelligencearXiv:2609.09229v1 Announce Type: cross Abstract: Additional inference compute can increase the number of…
arXiv Artificial IntelligencearXiv:2609.09219v1 Announce Type: cross Abstract: AI research agents combine prior knowledge, public sources…
arXiv Artificial IntelligencearXiv:2609.09213v1 Announce Type: cross Abstract: We study how physical-state inputs affect a 0.8B hybrid…
arXiv Artificial IntelligencearXiv:2609.09212v1 Announce Type: cross Abstract: This paper presents an end-to-end evaluation framework for…
arXiv Artificial IntelligencearXiv:2609.09189v1 Announce Type: cross Abstract: High classification accuracy alone is insufficient for…
arXiv Artificial IntelligencearXiv:2609.09187v1 Announce Type: cross Abstract: Advertising video generation is not only a video synthesis…