cs.LG（2024-04-15）

📊 共 20 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (12 🔗4) 支柱九：具身大模型 (Embodied Foundation Models) (7 🔗1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (12 篇)

#题目一句话要点标签🔗⭐
1 Exploring Text-to-Motion Generation with Human Preference 通过人类偏好学习提升文本到动作生成的效率 preference learning text-to-motion motion generation ✅
2 Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning 提出FeatLLM框架以解决少样本表格学习问题 predictive model large language model
3 Neuro-Inspired Information-Theoretic Hierarchical Perception for Multimodal Learning 提出信息论启发的分层感知模型以提升多模态学习性能 representation learning multimodal
4 State Space Model for New-Generation Network Alternative to Transformers: A Survey 综述状态空间模型以替代变压器架构解决计算复杂性问题 Mamba SSM state space model ✅
5 A Note on Loss Functions and Error Compounding in Model-based Reinforcement Learning 探讨模型基础强化学习中的损失函数与误差累积问题 reinforcement learning model-based RL
6 Inferring Behavior-Specific Context Improves Zero-Shot Generalization in Reinforcement Learning 提出行为特定上下文推断以改善强化学习中的零-shot泛化 reinforcement learning policy learning ✅
7 ReffAKD: Resource-efficient Autoencoder-based Knowledge Distillation 提出ReffAKD以解决知识蒸馏资源消耗问题 distillation ✅
8 Neighbour-level Message Interaction Encoding for Improved Representation Learning on Graphs 提出邻居级消息交互编码以改善图表示学习 representation learning
9 Higher Replay Ratio Empowers Sample-Efficient Multi-Agent Reinforcement Learning 提高重放比率以增强样本效率的多智能体强化学习 reinforcement learning
10 Learn Your Reference Model for Real Good Alignment 提出信任区域方法以解决大语言模型对齐中的过度优化问题 DPO large language model
11 Efflex: Efficient and Flexible Pipeline for Spatio-Temporal Trajectory Graph Modeling and Representation Learning 提出Efflex以解决时空轨迹图建模与表示学习的效率与灵活性问题 representation learning
12 Hierarchical Decision Making Based on Structural Information Principles 提出基于结构信息原则的SIDM框架以优化层次决策 reinforcement learning policy learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (7 篇)

#题目一句话要点标签🔗⭐
13 EPIC: Effective Prompting for Imbalanced-Class Data Synthesis in Tabular Data Classification via Large Language Models 提出EPIC以解决表格数据分类中的类别不平衡问题 large language model ✅
14 Foundational Challenges in Assuring Alignment and Safety of Large Language Models 识别大型语言模型对齐与安全性保障的18个基础挑战 large language model
15 Quantization of Large Language Models with an Overdetermined Basis 提出基于Kashin表示的量化算法以提升大语言模型性能 large language model
16 LoRAP: Transformer Sub-Layers Deserve Differentiated Structured Compression for Large Language Models 提出LoRAP以优化大语言模型的结构化压缩 large language model
17 Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models 提出Prepacking以优化长语言模型的预填充计算 large language model
18 LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence Parallelism 提出弹性序列并行性以高效服务长上下文大语言模型 large language model
19 The Fault in our Stars: Quality Assessment of Code Generation Benchmarks 评估代码生成基准的质量以提升模型性能 large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
20 Nonlinear sparse variational Bayesian learning based model predictive control with application to PEMFC temperature control 提出非线性稀疏变分贝叶斯学习的模型预测控制方法以解决PEMFC温度控制问题 MPC model predictive control

⬅️ 返回 cs.LG 首页 · 🏠 返回主页