arXiv Artificial IntelligenceSteeringSafety: Benchmarking Representation Steering in LLMs Across Safety Perspectives
arXiv:2509.13450v3 Announce Type: replace Abstract: We introduce SteeringSafety, a benchmark for evaluating…
Curated from international AI laboratories, specialist publications and technology outlets. Last update: 3 hours ago.
arXiv Artificial IntelligencearXiv:2509.13450v3 Announce Type: replace Abstract: We introduce SteeringSafety, a benchmark for evaluating…
arXiv Artificial IntelligencearXiv:2507.22423v3 Announce Type: replace Abstract: To engineer AGI, we should first capture the essence of…
arXiv Artificial IntelligencearXiv:2507.14267v2 Announce Type: replace Abstract: Large language model (LLM) agents can execute…
arXiv Artificial IntelligencearXiv:2506.12283v2 Announce Type: replace Abstract: Modeling vehicle interactions at unsignalized…
arXiv Artificial IntelligencearXiv:2506.04571v3 Announce Type: replace Abstract: Agriculture is undergoing a major transformation driven…
arXiv Artificial IntelligencearXiv:2502.20502v2 Announce Type: replace Abstract: Recent advances in Artificial Intelligence (AI) have…
arXiv Artificial IntelligencearXiv:2408.06849v3 Announce Type: replace Abstract: The large language model (LLM) has achieved significant…
arXiv Artificial IntelligencearXiv:2608.12308v1 Announce Type: cross Abstract: Aerial vision-language navigation (VLN) requires an…
arXiv Artificial IntelligencearXiv:2608.12307v1 Announce Type: cross Abstract: Recent work on distillation transfers the capabilities of…
arXiv Artificial IntelligencearXiv:2608.12306v1 Announce Type: cross Abstract: Safe offline RL typically assumes access to dense per-step…
arXiv Artificial IntelligencearXiv:2608.12290v1 Announce Type: cross Abstract: Modern black-box Image-to-Video (I2V) models offer powerful…
arXiv Artificial IntelligencearXiv:2608.12278v1 Announce Type: cross Abstract: Artificial intelligence tools for education and language…