cs.AI（2025-04-12）

📊 共 10 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) (6 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱八：物理动画 (Physics-based Animation) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)

#题目一句话要点标签🔗⭐
1 Continuum-Interaction-Driven Intelligence: Human-Aligned Neural Architecture via Crystallized Reasoning and Fluid Generation 提出基于连续交互驱动的智能架构，融合晶态推理与流态生成，实现类人对齐。 large language model chain-of-thought
2 SIFT-50M: A Large-Scale Multilingual Dataset for Speech Instruction Fine-Tuning 提出SIFT-50M：用于语音指令微调的大规模多语言数据集 large language model instruction following
3 BrainPrompt: Multi-Level Brain Prompt Enhancement for Neurological Condition Identification BrainPrompt：多层次脑提示增强的神经系统疾病识别框架 large language model ✅
4 Linguistic Comparison of AI- and Human-Written Responses to Online Mental Health Queries 对比分析AI与人类在在线心理健康社区的回复，揭示AI在共情和个性化方面的局限性。 large language model
5 Privacy Preservation in Gen AI Applications 针对生成式AI应用的隐私保护，提出防御数据泄露攻击的隐私保护框架 large language model
6 Towards Stepwise Domain Knowledge-Driven Reasoning Optimization and Reflection Improvement 提出领域知识驱动的逐步推理优化框架，提升LLM在专业领域的推理能力 chain-of-thought

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
7 Application of Contrastive Learning on ECG Data: Evaluating Performance in Japanese and Classification with Around 100 Labels 利用对比学习和日语语言模型，实现高精度心电图多标签分类。 contrastive learning multimodal
8 A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems 综述LLM推理前沿：推理规模化、学习推理及Agent系统 reinforcement learning PPO large language model

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

#题目一句话要点标签🔗⭐
9 Graph Learning-Driven Multi-Vessel Association: Fusing Multimodal Data for Maritime Intelligence 提出图学习驱动的多船只关联方法，融合多模态数据以提升海事智能。 spatiotemporal multimodal

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

#题目一句话要点标签🔗⭐
10 Semantic Commit: Helping Users Update Intent Specifications for AI Memory at Scale 提出SemanticCommit，辅助用户大规模更新AI记忆中的意图规范。 affordance

⬅️ 返回 cs.AI 首页 · 🏠 返回主页