cs.AI（2025-05-19）

📊 共 24 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (15 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗1) 支柱一：机器人控制 (Robot Control) (2) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (15 篇)

#题目一句话要点标签🔗⭐
1 MM-PRM: Enhancing Multimodal Mathematical Reasoning with Scalable Step-Level Supervision 提出MM-PRM以解决多模态数学推理中的步骤监督不足问题 large language model multimodal ✅
2 Aneumo: A Large-Scale Multimodal Aneurysm Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks 提出Aneumo数据集以解决脑动脉瘤风险评估问题 multimodal ✅
3 Survey: Multi-Armed Bandits Meet Large Language Models 探讨多臂老虎机算法与大型语言模型的协同潜力 large language model
4 Advancing Software Quality: A Standards-Focused Review of LLM-Based Assurance Techniques 基于大语言模型的SQA技术提升软件质量保障 large language model multimodal
5 Causal Head Gating: A Framework for Interpreting Roles of Attention Heads in Transformers 提出因果头门控方法以解析变换器中注意力头的功能角色 large language model instruction following
6 Unified Cross-modal Translation of Score Images, Symbolic Music, and Performance Audio 提出统一跨模态翻译方法以解决音乐信息检索问题 multimodal
7 Ice Cream Doesn't Cause Drowning: Benchmarking LLMs Against Statistical Pitfalls in Causal Inference 提出CausalPitfalls基准以解决LLMs因果推断中的统计陷阱问题 large language model
8 Security Degradation in Iterative AI Code Generation -- A Systematic Analysis of the Paradox 分析迭代AI代码生成中的安全退化问题 large language model
9 Safety Alignment Can Be Not Superficial With Explicit Safety Signals 通过显式安全信号提升大语言模型的安全对齐能力 large language model
10 Measuring the Faithfulness of Thinking Drafts in Large Reasoning Models 提出系统性反事实干预框架以评估大型推理模型的思维草稿可信度 chain-of-thought
11 Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activations 提出神经反馈范式以量化语言模型的元认知能力 large language model
12 CoT-Kinetics: A Theoretical Modeling Assessing LRM Reasoning Process 提出CoT-Kinetics以评估大规模推理模型的推理过程 large language model
13 AutoMathKG: The automated mathematical knowledge graph based on LLM and vector database 提出AutoMathKG以解决数学知识图谱构建的自动化问题 large language model
14 CompeteSMoE -- Statistically Guaranteed Mixture of Experts Training via Competition 提出CompeteSMoE以解决稀疏专家模型训练中的路由效率问题 large language model ✅
15 LLM-KG-Bench 3.0: A Compass for SemanticTechnology Capabilities in the Ocean of LLMs 提出LLM-KG-Bench 3.0以评估大语言模型在知识图谱领域的能力 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🔗⭐
16 Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards 提出RISE框架以解决强化学习中的自我验证问题 reinforcement learning large language model
17 Warm Up Before You Train: Unlocking General Reasoning in Resource-Constrained Settings 提出双阶段训练策略以解决数据稀缺下的推理能力问题 reinforcement learning distillation chain-of-thought
18 CoIn: Counting the Invisible Reasoning Tokens in Commercial Opaque LLM APIs 提出CoIn框架以解决商业LLM API中的隐性推理令牌计数问题 reinforcement learning large language model ✅
19 Building spatial world models from sparse transitional episodic memories 提出Episodic Spatial World Model以解决稀疏记忆构建空间模型问题 world model
20 Exploiting Symbolic Heuristics for the Synthesis of Domain-Specific Temporal Planning Guidance using Reinforcement Learning 提出利用符号启发式优化时序规划指导的强化学习方法 reinforcement learning
21 QUADS: QUAntized Distillation Framework for Efficient Speech Language Understanding 提出QUADS框架以解决资源受限环境下的语音语言理解问题 distillation

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
22 Large Language Models and Their Applications in Roadway Safety and Mobility Enhancement: A Comprehensive Review 综述大型语言模型在道路安全与出行提升中的应用 sim-to-real large language model foundation model
23 Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis 提出OSWorld-G基准与Jedi数据集以解决GUI基础的自然语言指令映射问题 manipulation foundation model

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

#题目一句话要点标签🔗⭐
24 Direction-Aware Neural Acoustic Fields for Few-Shot Interpolation of Ambisonic Impulse Responses 提出方向感知神经声场以解决少量样本插值问题 PULSE

⬅️ 返回 cs.AI 首页 · 🏠 返回主页