cs.AI（2025-04-03）

📊 共 18 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) (13 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱三：空间感知与语义 (Perception & Semantics) (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 How Deep Do Large Language Models Internalize Scientific Literature and Citation Practices? 研究揭示大型语言模型在科学文献引用中强化马太效应并偏好特定引用特征 large language model
2 Digital Forensics in the Age of Large Language Models 综述性论文：探讨大型语言模型在数字取证中的应用、挑战与未来方向 large language model
3 A Memory-Augmented LLM-Driven Method for Autonomous Merging of 3D Printing Work Orders 提出一种基于记忆增强LLM的3D打印工单自主合并方法，提升生产效率。 large language model
4 Affordable AI Assistants with Knowledge Graph of Thoughts 提出知识图谱思维（KGoT）架构，降低AI助手成本并提升复杂任务成功率。 large language model
5 Design of AI-Powered Tool for Self-Regulation Support in Programming Education 提出CodeRunner Agent，集成LLM以增强编程教育中的自调节学习能力 large language model
6 Language Models Guidance with Multi-Aspect-Cueing: A Case Study for Competitor Analysis 提出多方面提示引导的语言模型，用于增强竞争对手分析能力 large language model
7 Pel, A Programming Language for Orchestrating AI Agents Pel：一种用于编排AI Agent的新型编程语言，提升LLM控制能力 large language model
8 A Framework for Situating Innovations, Opportunities, and Challenges in Advancing Vertical Systems with Large AI Models 提出垂直系统框架，旨在解决大模型在特定领域应用的挑战与机遇。 foundation model ✅
9 From Consumption to Collaboration: Measuring Interaction Patterns to Augment Human Cognition in Open-Ended Tasks 提出一种评估人机协作模式的框架，旨在提升开放任务中人类认知能力。 large language model
10 Multi-Mission Tool Bench: Assessing the Robustness of LLM based Agents through Related and Dynamic Missions 提出多任务工具平台，评估LLM智能体在相关动态任务中的鲁棒性 large language model
11 BOOST: Bootstrapping Strategy-Driven Reasoning Programs for Program-Guided Fact-Checking BOOST：提出一种自举策略驱动的推理程序，用于程序引导的事实核查。 large language model
12 FlowKV: A Disaggregated Inference Framework with Low-Latency KV Cache Transfer and Load-Aware Scheduling FlowKV：一种低延迟KV缓存传输和负载感知调度的解耦推理框架 large language model
13 LLM Social Simulations Are a Promising Research Method 利用LLM进行社会模拟是一种有前景的研究方法，但面临可控的挑战。 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 Robust Reinforcement Learning from Human Feedback for Large Language Models Fine-Tuning 提出一种鲁棒的基于人类反馈的强化学习方法，用于提升大语言模型微调效果 reinforcement learning RLHF large language model
15 SymDQN: Symbolic Knowledge and Reasoning in Neural Network-based Reinforcement Learning SymDQN：融合符号知识与推理的深度强化学习框架 reinforcement learning policy learning
16 Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving 提出Multi-SWE-bench，一个用于多语言代码问题修复的综合基准测试。 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🔗⭐
17 Am I Being Treated Fairly? A Conceptual Framework for Individuals to Ascertain Fairness 提出个人公平性评估框架，使用户能够质疑和验证ADM系统的决策公平性 affordance

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

#题目一句话要点标签🔗⭐
18 Advancing Air Quality Monitoring: TinyML-Based Real-Time Ozone Prediction with Cost-Effective Edge Devices 提出基于TinyML的低成本实时臭氧预测系统，提升城市空气质量监测能力 PULSE

⬅️ 返回 cs.AI 首页 · 🏠 返回主页