SIGMA: Search-Augmented On-Demand Knowledge Integration for Agentic Mathematical Reasoning
11月 3, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2510.27568v1 Announce Type: cross Abstract: Solving mathematical reasoning problems requires not only accurate access to...
Shrink exploit windows, slash MTTP: Why ring deployment is now a must for enterprise defense
5月 17, 2025admin NUAI,Committee,ニュース,Uncategorized(0)Ring deployment slashes MTTP and legacy CVE risk. Learn how Ivanti and Southstar Bank are...
Shifting to AI model customization is an architectural imperative
3月 31, 2026admin NUAI,Committee,ニュース,Uncategorized(0)In the early days of large language models (LLMs), we grew accustomed to massive 10x...
ShareChat: A Dataset of Chatbot Conversations in the Wild
1月 7, 2026admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2512.17843v2 Announce Type: replace Abstract: While academic research typically treats Large Language Models (LLM) as...
Shape-shifting mirrors on NASA’s new space telescope could unveil Jupiters like our own
7月 22, 2026admin NUAI,Committee,ニュース,Uncategorized(0)When NASA’s Nancy Grace Roman Space Telescope launches, as early as the end of next...
SGPO: Self-Generated Preference Optimization based on Self-Improver
7月 29, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2507.20181v1 Announce Type: new Abstract: Large language models (LLMs), despite their extensive pretraining on diverse...
SFT Doesn’t Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs
1月 30, 2026admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2509.20758v3 Announce Type: replace Abstract: Supervised Fine-Tuning (SFT) on domain-specific datasets is a common approach...
SessionIntentBench: A Multi-task Inter-session Intention-shift Modeling Benchmark for E-commerce Customer Behavior Understanding
7月 29, 2025admin NUAI,Committee,ニュース,Uncategorized(0)arXiv:2507.20185v1 Announce Type: new Abstract: Session history is a common way of recording user interacting...
ServiceNow AI Releases Apriel-1.5-15B-Thinker: An Open-Weights Multimodal Reasoning Model that Hits Frontier-Level Performance on a Single-GPU Budget
10月 2, 2025admin NUAI,Committee,ニュース,Uncategorized(0)ServiceNow AI Research Lab has released Apriel-1.5-15B-Thinker, a 15-billion-parameter open-weights multimodal reasoning model trained with...
