cs.AI（2025-06-07）

📊 共 18 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (13) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱一：机器人控制 (Robot Control) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (13 篇)

#	题目	一句话要点	标签	🔗	⭐
1	LLM-D12: A Dual-Dimensional Scale of Instrumental and Relational Dependencies on Large Language Models	提出LLM-D12量表，用于评估个体对大型语言模型的工具性和关系性依赖程度	large language model
2	Fuse and Federate: Enhancing EV Charging Station Security with Multimodal Fusion and Federated Learning	提出多模态融合与联邦学习以增强电动汽车充电站安全性	multimodal
3	QuantMCP: Grounding Large Language Models in Verifiable Financial Reality	QuantMCP：利用模型上下文协议，将大语言模型应用于可验证的金融数据分析	large language model
4	VisioMath: Benchmarking Figure-based Mathematical Reasoning in LMMs	VisioMath：提出用于评估LMMs在图表数学推理能力上的基准测试。	multimodal
5	Contextual Experience Replay for Self-Improvement of Language Agents	提出上下文经验回放(CER)，提升LLM Agent在复杂环境中的自适应能力	large language model
6	An Agentic Framework for Autonomous Metamaterial Modeling and Inverse Design	提出基于Agentic Framework的自主超材料建模与逆向设计方法	large language model
7	Causal Graph based Event Reasoning using Semantic Relation Experts	提出基于因果图和语义关系专家的事件推理方法，提升LLM在事件预测和时间线理解中的性能。	large language model
8	United Minds or Isolated Agents? Exploring Coordination of LLMs under Cognitive Load Theory	提出CoThinker框架，利用认知负荷理论提升LLM在复杂任务中的协同能力	large language model
9	AI-Generated Compromises for Coalition Formation	提出基于AI的妥协方案生成方法，促进联盟形成，应用于协同文档撰写。	large language model
10	Cross-Entropy Games for Language Models: From Implicit Knowledge to General Capability Measures	提出交叉熵游戏以衡量语言模型的通用能力	large language model
11	AI PsyRoom: Artificial Intelligence Platform for Segmented Yearning and Reactive Outcome Optimization Method	AI PsyRoom：用于细粒度情感分析和个性化心理治疗方案生成的AI平台	large language model
12	Modeling Earth-Scale Human-Like Societies with One Billion Agents	Light Society：利用LLM驱动的十亿智能体模拟地球规模的人类社会	large language model
13	From Threat to Tool: Leveraging Refusal-Aware Injection Attacks for Safety Alignment	提出拒绝感知自适应注入攻击以解决安全对齐问题	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
14	WorldLLM: Improving LLMs' world modeling using curiosity-driven theory-making	WorldLLM：利用好奇心驱动的理论构建，提升LLM的世界建模能力	reinforcement learning world model predictive model
15	Meta-Adaptive Prompt Distillation for Few-Shot Visual Question Answering	提出元自适应Prompt蒸馏方法，提升小模型在Few-Shot VQA任务上的性能。	distillation multimodal
16	Boosting LLM Reasoning via Spontaneous Self-Correction	提出SPOC，通过自发性自纠正提升LLM数学推理能力	reinforcement learning large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
17	The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity	通过问题复杂度分析，揭示推理模型的能力边界与局限性	manipulation

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
18	Bio-Inspired Classification: Combining Information Theory and Spiking Neural Networks -- Influence of the Learning Rules	结合信息论与脉冲神经网络的生物启发式分类器，研究学习规则的影响	spatiotemporal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页