新闻
Semi-Supervised Learning for Large Language Models Safety and Content Moderation
arXiv:2512.21107v1 Announce Type: new Abstract: Safety for Large Language Models (LLMs) has been an ongoing...
Semantic Reconstruction of Adversarial Plagiarism: A Context-Aware Framework for Detecting and Restoring “Tortured Phrases” in Scientific Literature
arXiv:2512.10435v1 Announce Type: new Abstract: The integrity and reliability of scientific literature is facing a...
Semantic Mastery: Enhancing LLMs with Advanced Natural Language Understanding
arXiv:2504.00409v2 Announce Type: replace Abstract: Large language models (LLMs) have greatly improved their capability in...
Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models
arXiv:2502.06130v2 Announce Type: replace-cross Abstract: While recent Large Vision-Language Models (LVLMs) have shown remarkable performance...
Self-Consistency Preference Optimization
arXiv:2411.04109v3 Announce Type: replace Abstract: Self-alignment, whereby models learn to improve themselves without human annotation...
Selective Rotary Position Embedding
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
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
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
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
Fearing sweeping layoffs driven by AI and automation, elite consultants and high performers are turning...
Securing FastAPI Endpoints for MLOps: An Authentication Guide
In today’s AI world, data scientists are not just focused on training and optimizing machine...
SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations
arXiv:2510.04398v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in high-risk domains...
