cs.AI（2024-09-27）

📊 共 12 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) (6 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗1) 支柱一：机器人控制 (Robot Control) (1)

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

#	题目	一句话要点	标签	🔗	⭐
1	Align$^2$LLaVA: Cascaded Human and Large Language Model Preference Alignment for Multi-modal Instruction Curation	Align$^2$LLaVA：通过级联的人类与LLM偏好对齐，实现多模态指令数据的精细化筛选	large language model multimodal instruction following	✅
2	Multimodal Trajectory Prediction for Autonomous Driving on Unstructured Roads using Deep Convolutional Network	提出一种基于深度卷积网络的多模态轨迹预测方法，用于非结构化道路的自动驾驶。	multimodal	✅
3	Code Vulnerability Repair with Large Language Model using Context-Aware Prompt Tuning	提出上下文感知Prompt Tuning，提升LLM在代码漏洞修复中的性能	large language model
4	Mitigating Selection Bias with Node Pruning and Auxiliary Options	提出Bias Node Pruning和Auxiliary Option Injection，缓解LLM选择偏差问题。	large language model
5	KALE-LM-Chem: Vision and Practice Toward an AI Brain for Chemistry	构建化学AI大脑：提出KALE-LM-Chem系列模型，提升化学领域智能水平	large language model
6	Data Analysis in the Era of Generative AI	探索生成式AI重塑数据分析：设计考量与挑战	multimodal

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
7	"Oh LLM, I'm Asking Thee, Please Give Me a Decision Tree": Zero-Shot Decision Tree Induction and Embedding with Large Language Models	利用大语言模型零样本生成决策树，提升小样本表格数据预测性能。	predictive model large language model	✅
8	Beyond Single-Audio: Advancing Multi-Audio Processing in Audio Large Language Models	提出MALLM模型，解决音频大语言模型在多音频处理中的能力不足问题	MAE large language model
9	Toward Universal and Interpretable World Models for Open-ended Learning Agents	提出一种通用且可解释的世界模型，用于开放式学习智能体	world model
10	Cost-Aware Dynamic Cloud Workflow Scheduling using Self-Attention and Evolutionary Reinforcement Learning	提出基于自注意力机制和进化强化学习的云工作流动态调度方法，降低成本。	reinforcement learning
11	Refutation of Spectral Graph Theory Conjectures with Search Algorithms)	利用搜索算法反驳谱图理论猜想	reinforcement learning deep reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
12	Learning from Demonstration with Implicit Nonlinear Dynamics Models	提出一种基于隐式非线性动力学模型的模仿学习方法，解决策略执行中的误差累积问题。	manipulation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页