Pai 的 AI 雷达
今天：拆解恶意技能检测的规避手法（Agent 原型），大模型设计人形机器人全身策略代码（arXiv:2609）。并行还有 Composing Task-speci、SimEX、扩展 AI 高速安全存储访问。
arXiv:2609.40361v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) are rapidly advancing clinical diagnosis, yet their adaptation pipelines remain anchored to accuracy-based objectives. Clinical data are heavily class-imbalanced: a constant-majority predic
arXiv:2608.19842v3 Announce Type: replace Abstract: Agentic reinforcement learning (RL) has emerged as an important post-training approach for enhancing the capabilities of Large Language Models (LLMs). However, existing methods face a trade-off between policy performance and res
arXiv:2609.35596v2 Announce Type: replace-cross Abstract: Self-evolving LLM agents have gained prominence for their ability to improve after deployment by modifying their harness, including their controller instructions, memory management protocols, and reusable tools and skills,
arXiv:2609.39140v1 Announce Type: new Abstract: Learning to complete tasks in unfamiliar environments with unknown rules remains a key challenge for LLM agents. Current LLM agents often record their discoveries in prose, which may not provide a compact, explicit account of how th
arXiv:2609.38600v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly used in clinical settings, it is critical to evaluate their reliability under realistic variation in clinical text. We study this question in clinical triage, comparing LLMs to practi
arXiv:2609.39049v1 Announce Type: cross Abstract: A large language model (LLM) can rate depression severity directly from a social media post or mark which clinical criteria the post shows and let code turn the count into a label. The latter is easier to audit because a clinician
arXiv:2609.38958v1 Announce Type: new Abstract: Large language models (LLMs) have been rapidly improving in long-context tasks, powered by Chain-of-Thought (CoT) reasoning. However, the internal mechanisms underlying this improvement remain unclear. We investigate these mechanism
Deepseek and Huawei have built open-source programming tools for Huawei's Ascend AI chips. At the center is TileLang, a language designed to offer a simpler programming model than Nvidia's CUDA. The partnership targets the biggest obstacle for China's AI industry, which is softwa
Algorithms & Theory