cs.AI（2025-08-27）

📊 共 25 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (18 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗1) 支柱八：物理动画 (Physics-based Animation) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (18 篇)

#	题目	一句话要点	标签	🔗	⭐
1	SoK: Large Language Model Copyright Auditing via Fingerprinting	提出LLM指纹技术以解决版权审计问题	large language model foundation model	✅
2	The Next Layer: Augmenting Foundation Models with Structure-Preserving and Attention-Guided Learning for Local Patches to Global Context Awareness in Computational Pathology	提出EAGLE-Net以增强基础模型在计算病理学中的局部与全局上下文理解能力	foundation model
3	Ensemble Debates with Local Large Language Models for AI Alignment	提出本地开源集成辩论以提升AI对齐能力	large language model
4	Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation?	研究链式思维动态，揭示其指导性与忠实性问题	chain-of-thought
5	AI reasoning effort predicts human decision time in content moderation	通过推理努力预测人类内容审核决策时间	large language model chain-of-thought
6	The Anatomy of a Personal Health Agent	提出个人健康代理以满足多样化健康需求	large language model multimodal
7	PG-Agent: An Agent Powered by Page Graph	提出PG-Agent以解决GUI代理在新场景中的泛化问题	large language model multimodal
8	Private, Verifiable, and Auditable AI Systems	提出集成隐私、可验证性与可审计性的AI系统框架	large language model foundation model
9	The Mathematician's Assistant: Integrating AI into Research Practice	提出增强数学家的AI助手框架以优化研究实践	large language model
10	Model Science: getting serious about verification, explanation and control of AI systems	提出模型科学以解决AI系统验证与控制问题	foundation model
11	SwizzlePerf: Hardware-Aware LLMs for GPU Kernel Performance Optimization	提出SwizzlePerf以解决GPU内核性能优化问题	large language model
12	Validating Generative Agent-Based Models for Logistics and Supply Chain Management Research	验证生成代理基础模型以提升物流与供应链管理研究的有效性	large language model
13	AI-AI Esthetic Collaboration with Explicit Semiotic Awareness and Emergent Grammar Development	提出跨符号共创协议以实现AI间的美学协作	large language model
14	Safety Alignment Should Be Made More Than Just A Few Attention Heads	提出RDSHA与AHD以增强大语言模型的安全性	large language model
15	Instructional Agents: LLM Agents on Automated Course Material Generation for Teaching Faculties	提出Instructional Agents以自动生成教学材料解决教育资源不足问题	large language model
16	Democracy-in-Silico: Institutional Design as Alignment in AI-Governed Polities	提出基于代理模拟的制度设计以解决AI治理中的权力失衡问题	large language model
17	Taming the Chaos: Coordinated Autoscaling for Heterogeneous and Disaggregated LLM Inference	提出HeteroScale以解决异构和分离LLM推理的自动扩展问题	large language model
18	SLIM: Subtrajectory-Level Elimination for More Effective Reasoning	提出SLIM框架以优化大语言模型的推理过程	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
19	Tracking World States with Language Models: State-Based Evaluation Using Chess	提出一种状态基础评估框架以提升语言模型在棋类游戏中的表现	world model affordance large language model
20	SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control	提出SWIRL以解决移动GUI控制中的多智能体强化学习问题	reinforcement learning
21	IntentionReasoner: Facilitating Adaptive LLM Safeguards through Intent Reasoning and Selective Query Refinement	提出IntentionReasoner以解决大语言模型安全性问题	reinforcement learning large language model
22	Energy-Efficient Learning-Based Beamforming for ISAC-Enabled V2X Networks	提出基于学习的能效波束成形方案以优化V2X网络	reinforcement learning deep reinforcement learning DRL
23	ReST-RL: Achieving Accurate Code Reasoning of LLMs with Optimized Self-Training and Decoding	提出ReST-RL以解决LLMs推理准确性不足的问题	reinforcement learning DPO	✅

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

#	题目	一句话要点	标签	🔗	⭐
24	Personalized Sleep Prediction via Deep Adaptive Spatiotemporal Modeling and Sparse Data	提出AdaST-Sleep模型以解决个性化睡眠预测问题	spatiotemporal

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

#	题目	一句话要点	标签	🔗	⭐
25	Orchid: Orchestrating Context Across Creative Workflows with Generative AI	提出Orchid以解决创意工作流中的上下文管理问题	affordance

⬅️ 返回 cs.AI 首页 · 🏠 返回主页