arXiv Artificial IntelligenceAuditing Chinese Web-scale Corpora via Sampled BPE Token Statistics
arXiv:2608.10678v2 Announce Type: replace-cross Abstract: Chinese web pollution has surfaced in LLMs…
Curated from international AI laboratories, specialist publications and technology outlets. Last update: 3 hours ago.
arXiv Artificial IntelligencearXiv:2608.10678v2 Announce Type: replace-cross Abstract: Chinese web pollution has surfaced in LLMs…
arXiv Artificial IntelligencearXiv:2603.11398v3 Announce Type: replace-cross Abstract: Recently, visual localization has become an…
arXiv Artificial IntelligencearXiv:2509.03985v3 Announce Type: replace-cross Abstract: Jailbreak attacks bypass the safety alignment of…
arXiv Artificial IntelligencearXiv:2605.27887v4 Announce Type: replace Abstract: Large language models (LLMs) have shown strong…
arXiv Artificial IntelligencearXiv:2601.09974v3 Announce Type: replace Abstract: Personalizing Large Language Models typically relies on…
arXiv Artificial IntelligencearXiv:2508.04412v4 Announce Type: replace Abstract: The advent of large language models (LLMs) has sparked an…
arXiv Artificial IntelligencearXiv:2608.09538v3 Announce Type: replace-cross Abstract: We introduce TCS-Bench, a benchmark for evaluating…
arXiv Artificial IntelligencearXiv:2608.08311v3 Announce Type: replace-cross Abstract: We present Ouroboros, a self-developing agent…
arXiv Artificial IntelligencearXiv:2608.09512v2 Announce Type: replace Abstract: Active inference offers a unified framework for…
arXiv Artificial IntelligencearXiv:2606.08531v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly evolving…
arXiv Artificial IntelligencearXiv:2603.21607v3 Announce Type: replace Abstract: While retrieval-augmented generation (RAG) enhances LLM…
arXiv Artificial IntelligencearXiv:2608.07438v2 Announce Type: replace Abstract: Human-like cognition does not select past experience by…