arXiv Artificial IntelligenceTHESIS-MoE: Trainable Hierarchical Extraction and SteerIng of Sycophancy in Mixture-of-Experts
arXiv:2608.15687v1 Announce Type: new Abstract: Sycophancy, the tendency of a language model to change its…
Curated from international AI laboratories, specialist publications and technology outlets. Last update: 3 hours ago.
arXiv Artificial IntelligencearXiv:2608.15687v1 Announce Type: new Abstract: Sycophancy, the tendency of a language model to change its…
arXiv Artificial IntelligencearXiv:2608.15657v1 Announce Type: new Abstract: The rapid development and widespread application of…
arXiv Artificial IntelligencearXiv:2608.15634v1 Announce Type: new Abstract: How can common ground between societies in conflict be…
arXiv Artificial IntelligencearXiv:2608.15621v1 Announce Type: new Abstract: Human Activity Recognition (HAR) with self-administered…
arXiv Artificial IntelligencearXiv:2608.15619v1 Announce Type: new Abstract: Emotion recognition from text keeps improving on benchmarks…
arXiv Artificial IntelligencearXiv:2608.15600v1 Announce Type: new Abstract: The widespread circulation of abusive online content has…
arXiv Artificial IntelligencearXiv:2608.15594v1 Announce Type: new Abstract: Multi-turn jailbreak attacks have emerged as a critical…
arXiv Artificial IntelligencearXiv:2608.15591v1 Announce Type: new Abstract: Large Language Model (LLM) agents deployed in production…
arXiv Artificial IntelligencearXiv:2608.15580v1 Announce Type: new Abstract: Reliable endoscopic polyp reporting requires integrating…
arXiv Artificial IntelligencearXiv:2608.15510v1 Announce Type: new Abstract: Chart-to-code generation requires a model to read the…
arXiv Artificial IntelligencearXiv:2608.15502v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have emerged as a…
arXiv Artificial IntelligencearXiv:2608.15488v1 Announce Type: new Abstract: Effective public event forecasting is essential for…