cs.AI（2023-10-13）

📊 共 14 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) (10 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (4)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#题目一句话要点标签🔗⭐
1 EasyGen: Easing Multimodal Generation with BiDiffuser and LLMs 提出EasyGen以解决多模态生成效率低下问题 large language model multimodal ✅
2 Improving Large Language Models in Event Relation Logical Prediction 提出三种方法提升大型语言模型的事件关系逻辑推理能力 large language model ✅
3 Split-and-Denoise: Protect large language model inference with local differential privacy 提出Split-N-Denoise框架以解决大语言模型推理隐私问题 large language model
4 A Case-Based Persistent Memory for a Large Language Model 提出基于案例的持久记忆以增强大型语言模型的智能 large language model
5 CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules 提出CodeChain以解决复杂编程任务的模块化代码生成问题 large language model chain-of-thought
6 Ranking LLM-Generated Loop Invariants for Program Verification 提出重排序方法以优化LLM生成的循环不变式 large language model ✅
7 Evaluating Machine Perception of Indigeneity: An Analysis of ChatGPT's Perceptions of Indigenous Roles in Diverse Scenarios 探讨大型语言模型对土著角色的偏见分析 large language model
8 A ML-LLM pairing for better code comment classification 提出ML-LLM配对以提升代码注释分类性能 large language model
9 SAI: Solving AI Tasks with Systematic Artificial Intelligence in Communication Network 提出SAI框架以解决智能移动网络中的复杂AI任务 large language model
10 Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs 提出动态稀疏无训练方法以解决稀疏LLM微调问题 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
11 Leveraging Optimal Transport for Enhanced Offline Reinforcement Learning in Surgical Robotic Environments 提出最优传输奖励标记以解决手术机器人离线强化学习问题 reinforcement learning policy learning offline RL
12 Hybrid Reinforcement Learning for Optimizing Pump Sustainability in Real-World Water Distribution Networks 提出混合强化学习以优化水分配网络中的泵调度问题 reinforcement learning
13 HierarchicalContrast: A Coarse-to-Fine Contrastive Learning Framework for Cross-Domain Zero-Shot Slot Filling 提出HierarchicalContrast框架以解决跨域零样本槽填充问题 contrastive learning
14 Evading Community Detection via Counterfactual Neighborhood Search 提出反事实邻域搜索以解决社区成员隐藏问题 reinforcement learning deep reinforcement learning

⬅️ 返回 cs.AI 首页 · 🏠 返回主页