cs.AI（2025-06-06）

📊 共 25 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (18 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗1) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱一：机器人控制 (Robot Control) (1)

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

#题目一句话要点标签🔗⭐
1 SIGMA: Refining Large Language Model Reasoning via Sibling-Guided Monte Carlo Augmentation 提出SIGMA框架以提升大型语言模型推理能力 large language model chain-of-thought
2 Audio-Aware Large Language Models as Judges for Speaking Styles 提出音频感知大型语言模型作为演讲风格评估工具 large language model instruction following
3 Trajectory Entropy: Modeling Game State Stability from Multimodality Trajectory Prediction 提出轨迹熵以解决多智能体游戏状态稳定性问题 multimodal
4 PersonaAgent: When Large Language Model Agents Meet Personalization at Test Time 提出PersonaAgent以解决个性化响应不足问题 large language model
5 Large Language Models Can Be a Viable Substitute for Expert Political Surveys When a Shock Disrupts Traditional Measurement Approaches 提出大语言模型替代专家政治调查以应对测量中断问题 large language model
6 ScriptDoctor: Automatic Generation of PuzzleScript Games via Large Language Models and Tree Search 提出ScriptDoctor以实现PuzzleScript游戏的自动生成与测试 large language model
7 CP-Bench: Evaluating Large Language Models for Constraint Modelling 提出CP-Bench以解决约束建模评估问题 large language model
8 Research on Personalized Financial Product Recommendation by Integrating Large Language Models and Graph Neural Networks 提出混合框架以解决个性化金融产品推荐问题 large language model
9 DesignBench: A Comprehensive Benchmark for MLLM-based Front-end Code Generation 提出DesignBench以解决现有前端代码生成基准的不足 large language model multimodal ✅
10 Cost-Efficient LLM Training with Lifetime-Aware Tensor Offloading via GPUDirect Storage 提出TERAIO以解决GPU内存扩展的成本效率问题 large language model
11 Leveraging Generative AI for Enhancing Automated Assessment in Programming Education Contests 提出基于生成式AI的自动化编程评估测试用例生成方法 large language model
12 (AI peers) are people learning from the same standpoint: Perception of AI characters in a Collaborative Science Investigation 通过AI角色提升协作科学调查中的学习效果 multimodal
13 Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems 提出Joint-GCG以解决RAG系统的毒化攻击问题 large language model ✅
14 CrimeMind: Simulating Urban Crime with Multi-Modal LLM Agents 提出CrimeMind以解决城市犯罪模拟问题 large language model
15 Small Models, Big Support: A Local LLM Framework for Educator-Centric Content Creation and Assessment with RAG and CAG 提出小型LLM框架以支持教育者内容创作与评估 large language model
16 Explainability in Context: A Multilevel Framework Aligning AI Explanations with Stakeholder with LLMs 提出多层框架以增强AI解释的可信度与可理解性 large language model
17 SafeGenBench: A Benchmark Framework for Security Vulnerability Detection in LLM-Generated Code 提出SafeGenBench以解决LLM生成代码的安全漏洞检测问题 large language model
18 EdgeProfiler: A Fast Profiling Framework for Lightweight LLMs on Edge Using Analytical Model 提出EdgeProfiler以解决轻量级LLMs在边缘计算中的性能评估问题 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 Preference Learning for AI Alignment: a Causal Perspective 提出因果视角的偏好学习方法以解决AI对齐问题 preference learning large language model
20 WhisQ: Cross-Modal Representation Learning for Text-to-Music MOS Prediction 提出WhisQ以解决文本到音乐的MOS预测问题 representation learning multimodal
21 Reflect-then-Plan: Offline Model-Based Planning through a Doubly Bayesian Lens 提出Reflect-then-Plan以解决离线强化学习中的不确定性问题 reinforcement learning offline RL offline reinforcement learning
22 Reinforcement Learning for Autonomous Warehouse Orchestration in SAP Logistics Execution: Redefining Supply Chain Agility 提出强化学习框架以提升SAP物流执行中的仓库调度效率 reinforcement learning
23 When Better Features Mean Greater Risks: The Performance-Privacy Trade-Off in Contrastive Learning 提出LpLA方法以解决对比学习中的隐私泄露问题 contrastive learning ✅

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
24 Proactive Assistant Dialogue Generation from Streaming Egocentric Videos 提出实时对话生成框架以解决视觉输入指导问题 egocentric

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
25 A Synthetic Pseudo-Autoencoder Invites Examination of Tacit Assumptions in Neural Network Design 提出合成伪自编码器以挑战神经网络设计假设 manipulation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页