cs.LG(2024-03-02)

📊 共 12 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) (8 🔗4) 支柱二:RL算法与架构 (RL & Architecture) (3) 支柱七:动作重定向 (Motion Retargeting) (1)

🔬 支柱九:具身大模型 (Embodied Foundation Models) (8 篇)

#题目一句话要点标签🔗
1 ICC: Quantifying Image Caption Concreteness for Multimodal Dataset Curation 提出图像标题具体性度量以优化多模态数据集筛选 foundation model multimodal
2 OpenGraph: Towards Open Graph Foundation Models 提出OpenGraph以解决图学习中的泛化问题 large language model foundation model
3 Analysis of Privacy Leakage in Federated Large Language Models 分析联邦大语言模型中的隐私泄露问题 large language model
4 Evaluating Large Language Models as Virtual Annotators for Time-series Physical Sensing Data 利用大型语言模型作为虚拟标注者解决时间序列数据标注问题 large language model
5 AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks 提出AutoDefense以解决大语言模型的监狱突破攻击问题 large language model instruction following
6 NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention 提出NoMAD-Attention以解决CPU上大语言模型推理效率问题 large language model
7 Dissecting Language Models: Machine Unlearning via Selective Pruning 提出选择性修剪方法以实现大语言模型的机器遗忘 large language model
8 Coupled generator decomposition for fusion of electro- and magnetoencephalography data 提出耦合生成器分解以融合脑电与脑磁数据 multimodal

🔬 支柱二:RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗
9 Continuous Mean-Zero Disagreement-Regularized Imitation Learning (CMZ-DRIL) 提出CMZ-DRIL以解决模仿学习中的数据稀缺问题 reinforcement learning imitation learning
10 Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning 提出高效情节记忆利用以解决合作多智能体强化学习问题 reinforcement learning
11 Teaching MLP More Graph Information: A Three-stage Multitask Knowledge Distillation Framework 提出三阶段多任务蒸馏框架以解决图神经网络推理效率问题 distillation

🔬 支柱七:动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗
12 COOL: A Conjoint Perspective on Spatio-Temporal Graph Neural Network for Traffic Forecasting 提出COOL以解决交通预测中的时空关系建模问题 spatial relationship

⬅️ 返回 cs.LG 首页 · 🏠 返回主页