cs.LG（2023-12-31）
📊 共 5 篇论文
🎯 兴趣领域导航
🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Balanced Multi-modal Federated Learning via Cross-Modal Infiltration | 提出FedCMI框架，通过跨模态渗透解决多模态联邦学习中的模态不平衡问题 | multimodal | ||
| 2 | Viz: A QLoRA-based Copyright Marketplace for Legally Compliant Generative AI | Viz：一种基于QLoRA的版权市场，用于合规生成式AI | large language model | ||
| 3 | Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws | 修正Chinchilla缩放法则，考虑推理成本优化大语言模型训练 | large language model |
🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 4 | Online Symbolic Music Alignment with Offline Reinforcement Learning | 提出基于离线强化学习的在线符号音乐对齐方法 | reinforcement learning offline RL offline reinforcement learning | ||
| 5 | HQ-VAE: Hierarchical Discrete Representation Learning with Variational Bayes | HQ-VAE：提出基于变分贝叶斯的层级离散表示学习框架，提升重建质量。 | representation learning VQ-VAE |