cs.AI（2025-12-14）

📊 共 14 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (11 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#题目一句话要点标签🔗⭐
1 A Disproof of Large Language Model Consciousness: The Necessity of Continual Learning for Consciousness 论证大型语言模型不具备意识：持续学习是意识的必要条件 large language model
2 Adaptive Edge-Cloud Inference for Speech-to-Action Systems Using ASR and Large Language Models 提出ASTA：一种自适应边缘-云语音指令系统，平衡性能与资源利用。 large language model
3 Pre-review to Peer review: Pitfalls of Automating Reviews using Large Language Models 评估大语言模型在学术评审中的应用，揭示其作为预审工具的潜力和局限性 large language model
4 KidsArtBench: Multi-Dimensional Children's Art Evaluation with Attribute-Aware MLLMs KidsArtBench：提出属性感知多模态大语言模型，用于儿童艺术作品的多维度评估。 large language model multimodal
5 Explainable AI as a Double-Edged Sword in Dermatology: The Impact on Clinicians versus The Public 可解释AI在皮肤科应用中是一把双刃剑：对临床医生与公众的影响 large language model multimodal
6 Fault-Tolerant Sandboxing for AI Coding Agents: A Transactional Approach to Safe Autonomous Execution 提出基于事务的容错沙箱，保障AI编码Agent自主执行的安全性 large language model
7 Beyond Task Completion: An Assessment Framework for Evaluating Agentic AI Systems 提出Agent Assessment Framework，用于评估Agentic AI系统在复杂任务中的行为不确定性 large language model
8 Memoria: A Scalable Agentic Memory Framework for Personalized Conversational AI Memoria：一种可扩展的Agentic记忆框架，用于个性化对话式AI large language model
9 One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMs 揭示预训练模型漏洞：微调LLM中的越狱风险放大效应 large language model
10 Large Language Newsvendor: Decision Biases and Cognitive Mechanisms 研究表明大型语言模型在新报童问题中存在决策偏差，且可能放大人类认知偏误 large language model
11 Diverse LLMs vs. Vulnerabilities: Who Detects and Fixes Them Better? DVDR-LLM：集成多种LLM提升软件漏洞检测与修复能力 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
12 World Models Unlock Optimal Foraging Strategies in Reinforcement Learning Agents 基于世界模型的强化学习智能体解锁最优觅食策略 reinforcement learning world model
13 Synergizing Code Coverage and Gameplay Intent: Coverage-Aware Game Playtesting with LLM-Guided Reinforcement Learning 提出SMART框架，结合代码覆盖率与游戏意图，提升游戏自动化测试效率。 reinforcement learning large language model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
14 Quantum Implicit Neural Representations for 3D Scene Reconstruction and Novel View Synthesis 提出Q-NeRF，一种混合量子-经典神经辐射场框架，用于三维场景重建和新视角合成。 NeRF neural radiance field implicit representation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页