cs.LG（2024-12-12）

📊 共 15 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) (9) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#题目一句话要点标签🔗⭐
1 A Wander Through the Multimodal Landscape: Efficient Transfer Learning via Low-rank Sequence Multimodal Adapter 提出Wander：一种低秩序列多模态适配器，用于高效多模态迁移学习 multimodal
2 Toward Foundation Model for Multivariate Wearable Sensing of Physiological Signals 提出NormWear，用于可穿戴生理信号的多变量通用表征学习 foundation model
3 Federated Foundation Models on Heterogeneous Time Series 提出FFTS：一种异构时间序列联邦学习框架，用于训练泛化性强的基础模型 foundation model
4 Explore Theory of Mind: Program-guided adversarial data generation for theory of mind reasoning 提出ExploreToM框架，通过程序引导的对抗数据生成增强LLM的心智理论推理能力 large language model
5 CUAL: Continual Uncertainty-aware Active Learner 提出CUAL以解决持续不确定性感知主动学习问题 foundation model
6 Capturing the Temporal Dependence of Training Data Influence 提出数据价值嵌入方法，捕捉训练数据影响的时序依赖性，解决传统影响函数的局限性。 foundation model
7 CRVQ: Channel-Relaxed Vector Quantization for Extreme Compression of LLMs 提出通道松弛向量量化CRVQ，用于大语言模型极限压缩。 large language model
8 GeLoRA: Geometric Adaptive Ranks For Efficient LoRA Fine-tuning GeLoRA：提出几何自适应秩LoRA微调方法，提升大语言模型微调效率。 large language model
9 MOPI-HFRS: A Multi-objective Personalized Health-aware Food Recommendation System with LLM-enhanced Interpretation MOPI-HFRS：结合LLM解释的多目标个性化健康饮食推荐系统 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
10 Does Representation Matter? Exploring Intermediate Layers in Large Language Models 探索LLM中间层表征质量，发现其优于最终层并揭示架构差异 SSM state space model large language model
11 PickLLM: Context-Aware RL-Assisted Large Language Model Routing 提出PickLLM以解决LLM选择优化问题 reinforcement learning large language model
12 Optimising TinyML with Quantization and Distillation of Transformer and Mamba Models for Indoor Localisation on Edge Devices 针对边缘设备室内定位，提出Transformer和Mamba模型量化与蒸馏的TinyML优化方案 Mamba distillation
13 FAWAC: Feasibility Informed Advantage Weighted Regression for Persistent Safety in Offline Reinforcement Learning 提出FAWAC算法，通过可行性约束优势加权回归实现离线强化学习中的持久安全 reinforcement learning offline reinforcement learning
14 Single-View Graph Contrastive Learning with Soft Neighborhood Awareness 提出SIGNA：一种基于软邻域感知的单视图图对比学习框架，提升节点分类性能。 contrastive learning ✅
15 Optimal Control with Natural Images: Efficient Reinforcement Learning using Overcomplete Sparse Codes 提出基于过完备稀疏编码的强化学习方法，高效解决自然图像序列上的最优控制问题 reinforcement learning

⬅️ 返回 cs.LG 首页 · 🏠 返回主页