cs.AI（2025-06-25）

📊 共 20 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) (11 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (7 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱一：机器人控制 (Robot Control) (1)

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

#题目一句话要点标签🔗⭐
1 Large Language Model-Driven Code Compliance Checking in Building Information Modeling 提出基于大语言模型的建筑信息建模合规检查方法 large language model
2 SV-LLM: An Agentic Approach for SoC Security Verification using Large Language Models 提出SV-LLM以解决SoC安全验证自动化问题 large language model
3 Enterprise Large Language Model Evaluation Benchmark 提出企业大型语言模型评估基准以解决现有评估不足问题 large language model
4 Mitigating Gambling-Like Risk-Taking Behaviors in Large Language Models: A Behavioral Economics Approach to AI Safety 提出风险意识响应生成框架以缓解大型语言模型的赌博行为 large language model
5 iLearnRobot: An Interactive Learning-Based Multi-Modal Robot with Continuous Improvement 提出基于交互学习的多模态机器人系统以提升适应性 large language model
6 CoMind: Towards Community-Driven Agents for Machine Learning Engineering 提出CoMind以解决机器学习工程中的知识孤岛问题 large language model
7 AIMeter: Measuring, Analyzing, and Visualizing Energy and Carbon Footprint of AI Workloads 提出AIMeter以解决AI工作负载的能耗与碳排放测量问题 large language model ✅
8 Poster: Enhancing GNN Robustness for Network Intrusion Detection via Agent-based Analysis 通过代理分析增强GNN在网络入侵检测中的鲁棒性 large language model
9 Tabular Feature Discovery With Reasoning Type Exploration 提出REFeat方法以解决表格数据特征发现问题 large language model
10 Irec: A Metacognitive Scaffolding for Self-Regulated Learning through Just-in-Time Insight Recall: A Conceptual Framework and System Prototype 提出Insight Recall以解决自我调节学习中的反思不足问题 large language model
11 RedCoder: Automated Multi-Turn Red Teaming for Code LLMs 提出RedCoder以解决代码生成模型的安全性评估问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
12 Enhancing Reasoning Capabilities in SLMs with Reward Guided Dataset Distillation 提出AdvDistill以解决小型语言模型推理能力不足问题 distillation large language model
13 R1-Ranker: Teaching LLM Rankers to Reason 提出R1-Ranker以解决LLM排名任务中的推理不足问题 reinforcement learning large language model foundation model
14 Mobile-R1: Towards Interactive Reinforcement Learning for VLM-Based Mobile Agent via Task-Level Rewards 提出Mobile-R1以解决移动代理动态交互不足问题 reinforcement learning offline reinforcement learning ✅
15 Complex Model Transformations by Reinforcement Learning with Uncertain Human Guidance 提出基于强化学习的复杂模型转换方法以应对不确定人类指导问题 reinforcement learning
16 The Decrypto Benchmark for Multi-Agent Reasoning and Theory of Mind 提出Decrypto基准以解决多智能体推理与心智理论问题 reinforcement learning large language model
17 Audio-JEPA: Joint-Embedding Predictive Architecture for Audio Representation Learning 提出Audio-JEPA以解决音频表示学习问题 representation learning
18 GymPN: A Library for Decision-Making in Process Management Systems 提出GymPN以优化流程管理系统中的决策问题 reinforcement learning deep reinforcement learning

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

#题目一句话要点标签🔗⭐
19 Case-based Reasoning Augmented Large Language Model Framework for Decision Making in Realistic Safety-Critical Driving Scenarios 提出基于案例推理的增强型大语言模型框架以解决安全驾驶决策问题 scene understanding large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
20 Vulnerability Disclosure through Adaptive Black-Box Adversarial Attacks on NIDS 提出自适应黑箱对抗攻击以解决网络入侵检测系统的脆弱性问题 manipulation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页