Selective Rotary Position Embedding
11 月 24, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2511.17388v1 Announce Type: new Abstract: Position information is essential for language modeling. In softmax transformers...
Seer Self-Consistency: Advance Budget Estimation for Adaptive Test-Time Scaling
1 月 22, 2026admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2511.09345v2 Announce Type: replace Abstract: Test-time scaling improves the inference performance of Large Language Models...
Seed-Prover 1.5: Mastering Undergraduate-Level Theorem Proving via Learning from Experience
12 月 22, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2512.17260v1 Announce Type: new Abstract: Large language models have recently made significant progress to generate...
See stunning first images from the Vera C. Rubin Observatory
6 月 23, 2025admin NUAI,Committee,新闻,Uncategorized(0)The first spectacular images taken by the Vera C. Rubin Observatory have been released for...
Security leaders lose visibility as consultants deploy shadow AI copilots to stay employed
5 月 28, 2025admin NUAI,Committee,新闻,Uncategorized(0)Fearing sweeping layoffs driven by AI and automation, elite consultants and high performers are turning...
Securing FastAPI Endpoints for MLOps: An Authentication Guide
7 月 5, 2025admin NUAI,Committee,新闻,Uncategorized(0)In today’s AI world, data scientists are not just focused on training and optimizing machine...
Securing digital assets against future threats
3 月 16, 2026admin NUAI,Committee,新闻,Uncategorized(0)Post Content...
SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations
10 月 7, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2510.04398v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in high-risk domains...
Search-on-Graph: Iterative Informed Navigation for Large Language Model Reasoning on Knowledge Graphs
10 月 13, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2510.08825v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated impressive reasoning abilities yet...
