cs.AI（2025-06-30）

📊 共 30 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) (22 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (6) 支柱八：物理动画 (Physics-based Animation) (1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (22 篇)

#题目一句话要点标签🔗⭐
1 Multimodal, Multi-Disease Medical Imaging Foundation Model (MerMED-FM) 提出MerMED-FM以解决多模态医学影像分析的准确性问题 foundation model multimodal
2 Interactive Reasoning: Visualizing and Controlling Chain-of-Thought Reasoning in Large Language Models 提出交互推理以优化大型语言模型的思维链输出 large language model chain-of-thought
3 AI Risk-Management Standards Profile for General-Purpose AI (GPAI) and Foundation Models 提出AI风险管理标准以应对通用人工智能的挑战 large language model foundation model
4 SoK: Semantic Privacy in Large Language Models 提出生命周期框架以解决大型语言模型的语义隐私问题 large language model multimodal
5 Software Engineering for Large Language Models: Research Status, Challenges and the Road Ahead 系统分析大语言模型开发生命周期中的软件工程挑战与解决方案 large language model
6 Agent4S: The Transformation of Research Paradigms from the Perspective of Large Language Models 提出Agent4S以解决AI4S研究效率低下问题 large language model
7 How large language models judge and influence human cooperation 评估大型语言模型对人类合作的影响与判断 large language model
8 Towards Building Private LLMs: Exploring Multi-Node Expert Parallelism on Apple Silicon for Mixture-of-Experts Large Language Model 提出多节点专家并行方法以解决私有大语言模型构建的成本与可扩展性问题 large language model
9 Evaluating Multi-Agent Defences Against Jailbreaking Attacks on Large Language Models 提出多代理系统以应对大型语言模型的越狱攻击 large language model
10 Fuzzing: Randomness? Reasoning! Efficient Directed Fuzzing via Large Language Models 提出RandLuzz以解决模糊测试中的随机性问题 large language model
11 MMReason: An Open-Ended Multi-Modal Multi-Step Reasoning Benchmark for MLLMs Toward AGI 提出MMReason基准以评估多模态大语言模型的推理能力 large language model multimodal ✅
12 Thinking About Thinking: SAGE-nano's Inverse Reasoning for Self-Aware Language Models 提出逆向推理框架以提升语言模型的自我解释能力 large language model chain-of-thought
13 Epitome: Pioneering an Experimental Platform for AI-Social Science Integration 提出Epitome平台以促进人工智能与社会科学的深度融合 large language model foundation model
14 "Before, I Asked My Mom, Now I Ask ChatGPT": Visual Privacy Management with Generative AI for Blind and Low-Vision People 提出生成性AI以解决盲人和低视力者的视觉隐私管理问题 multimodal
15 ChatGPT produces more "lazy" thinkers: Evidence of cognitive engagement decline 研究表明ChatGPT可能导致学生认知参与度下降 large language model
16 Teaching Programming in the Age of Generative AI: Insights from Literature, Pedagogical Proposals, and Student Perspectives 提出以可视化模拟增强编程教学以应对生成式AI挑战 large language model
17 Performance of LLMs on Stochastic Modeling Operations Research Problems: From Theory to Practice 评估大型语言模型在随机建模运筹学问题上的表现 large language model
18 Towards the "Digital Me": A vision of authentic Conversational Agents powered by personal Human Digital Twins 提出人类数字双胞胎系统以实现真实的对话代理 large language model
19 The Impact of AI on Educational Assessment: A Framework for Constructive Alignment 提出基于建设性对齐理论的AI教育评估框架 large language model
20 PokéAI: A Goal-Generating, Battle-Optimizing Multi-agent System for Pokemon Red 提出PokéAI以解决宝可梦红版游戏中的自主决策问题 large language model
21 ChemActor: Enhancing Automated Extraction of Chemical Synthesis Actions with LLM-Generated Data 提出ChemActor以解决化学合成过程自动提取问题 large language model ✅
22 State and Memory is All You Need for Robust and Reliable AI Agents 提出SciBORG框架以解决复杂科学工作流中的记忆与规划问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
23 Reinforcement Learning for Automated Cybersecurity Penetration Testing 提出基于强化学习的自动化网络安全渗透测试方法 reinforcement learning penetration
24 Self-correcting Reward Shaping via Language Models for Reinforcement Learning Agents in Games 提出自校正奖励塑形方法以解决强化学习代理的奖励设计问题 reinforcement learning reward shaping
25 BlackBoxToBlueprint: Extracting Interpretable Logic from Legacy Systems using Reinforcement Learning and Counterfactual Analysis 提出一种新方法从遗留系统中提取可解释逻辑 reinforcement learning
26 SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning 提出SPIRAL框架以解决自我监督的推理能力培养问题 reinforcement learning
27 Scaling Self-Supervised Representation Learning for Symbolic Piano Performance 提出自监督表示学习方法以提升符号钢琴表演生成能力 representation learning
28 A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents 提出R2A2架构以应对大型模型代理的安全风险 world model large language model

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

#题目一句话要点标签🔗⭐
29 Industrial brain: a human-like autonomous neuro-symbolic cognitive decision-making system 提出工业大脑以解决工业链韧性预测与规划问题 spatiotemporal

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
30 Feature Integration Spaces: Joint Training Reveals Dual Encoding in Neural Network Representations 提出双重编码机制以提升神经网络可解释性 manipulation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页