cs.LG（2023-11-22）

📊 共 15 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (8 🔗3) 支柱九：具身大模型 (Embodied Foundation Models) (6) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (8 篇)

#题目一句话要点标签🔗⭐
1 Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model 提出D3PO方法以解决扩散模型奖励模型训练问题 reinforcement learning diffusion policy RLHF ✅
2 Curriculum Learning and Imitation Learning for Model-free Control on Financial Time-series 提出课程学习与模仿学习以解决金融时间序列控制问题 imitation learning curriculum learning distillation
3 Guided Flows for Generative Modeling and Decision Making 提出无分类器引导流以提升生成模型性能 reinforcement learning offline reinforcement learning flow matching
4 Revisiting Supervision for Continual Representation Learning 重新审视监督在持续表征学习中的作用 representation learning ✅
5 Multi-Objective Bayesian Optimization with Active Preference Learning 提出基于贝叶斯优化的主动偏好学习方法以解决多目标优化问题 preference learning
6 Probabilistic Inference in Reinforcement Learning Done Right 提出VAPOR方法以解决强化学习中的状态-动作最优性推断问题 reinforcement learning
7 Representation Learning in a Decomposed Encoder Design for Bio-inspired Hebbian Learning 提出模块化框架以增强生物启发的Hebbian学习的表示学习能力 representation learning
8 White-Box Transformers via Sparse Rate Reduction: Compression Is All There Is? 提出CRATE架构以优化数据压缩与稀疏表示 representation learning MAE ✅

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

#题目一句话要点标签🔗⭐
9 Prompt Risk Control: A Rigorous Framework for Responsible Deployment of Large Language Models 提出Prompt Risk Control以解决大语言模型部署中的风险问题 large language model
10 Transfer Attacks and Defenses for Large Language Models on Coding Tasks 提出基于提示的防御方法以增强LLM在编码任务中的鲁棒性 large language model
11 Large Language Model-Enhanced Algorithm Selection: Towards Comprehensive Algorithm Representation 引入大语言模型提升算法选择以解决自动化机器学习问题 large language model
12 LIMIT: Less Is More for Instruction Tuning Across Evaluation Paradigms 提出LIMIT方法以优化指令调优效果 large language model instruction following
13 FedFN: Feature Normalization for Alleviating Data Heterogeneity Problem in Federated Learning 提出FedFN以解决联邦学习中的数据异质性问题 foundation model
14 Confidant: Customizing Transformer-based LLMs via Collaborative Edge Training 提出Confidant以解决移动边缘设备上LLM定制问题 large language model

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
15 Robust Errant Beam Prognostics with Conditional Modeling for Particle Accelerators 提出条件建模方法以解决粒子加速器故障预测问题 PULSE

⬅️ 返回 cs.LG 首页 · 🏠 返回主页