cs.LG(2024-03-07)

📊 共 17 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱二:RL算法与架构 (RL & Architecture) (11 🔗1) 支柱九:具身大模型 (Embodied Foundation Models) (4 🔗1) 支柱一:机器人控制 (Robot Control) (1) 支柱三:空间感知与语义 (Perception & Semantics) (1)

🔬 支柱二:RL算法与架构 (RL & Architecture) (11 篇)

#题目一句话要点标签🔗
1 Teaching Large Language Models to Reason with Reinforcement Learning 通过强化学习提升大型语言模型的推理能力 reinforcement learning PPO RLHF
2 Mastering Memory Tasks with World Models 提出Recall to Imagine以解决长期依赖问题 reinforcement learning world model world models
3 Fill-and-Spill: Deep Reinforcement Learning Policy Gradient Methods for Reservoir Operation Decision and Control 提出深度强化学习方法以优化水库运营决策 reinforcement learning deep reinforcement learning DRL
4 Contrastive Continual Learning with Importance Sampling and Prototype-Instance Relation Distillation 提出基于重要性采样的对比持续学习方法以解决灾难性遗忘问题 representation learning contrastive learning distillation
5 Efficient Off-Policy Learning for High-Dimensional Action Spaces 提出Vlearn以解决高维动作空间中的数据低效问题 reinforcement learning deep reinforcement learning policy learning
6 Control-based Graph Embeddings with Data Augmentation for Contrastive Learning 提出基于控制的图嵌入与数据增强以提升对比学习效果 representation learning contrastive learning
7 Aligning GPTRec with Beyond-Accuracy Goals with Reinforcement Learning 提出GPTRec以解决推荐系统中的多样性优化问题 reinforcement learning teacher-student
8 Why Online Reinforcement Learning is Causal 提出因果模型以增强在线强化学习的效果 reinforcement learning offline RL
9 Lightweight Cross-Modal Representation Learning 提出轻量级跨模态表示学习以解决高资源消耗问题 representation learning
10 RL-CFR: Improving Action Abstraction for Imperfect Information Extensive-Form Games with Reinforcement Learning 提出RL-CFR以解决不完全信息扩展形式博弈中的动态动作抽象问题 reinforcement learning
11 Noisy Spiking Actor Network for Exploration 提出噪声脉冲演员网络以解决深度强化学习中的探索问题 reinforcement learning deep reinforcement learning

🔬 支柱九:具身大模型 (Embodied Foundation Models) (4 篇)

#题目一句话要点标签🔗
12 CLIP the Bias: How Useful is Balancing Data in Multimodal Learning? 提出多模态时刻匹配算法以缓解CLIP模型偏见问题 multimodal
13 Enhancing Data Quality in Federated Fine-Tuning of Foundation Models 提出数据质量控制管道以解决联邦微调中的数据质量问题 foundation model
14 Online Adaptation of Language Models with a Memory of Amortized Contexts 提出记忆调节框架以解决大语言模型在线适应问题 large language model
15 Generative AI for Synthetic Data Generation: Methods, Challenges and the Future 利用生成式AI生成合成数据以解决数据稀缺问题 large language model

🔬 支柱一:机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗
16 A mechanism-driven reinforcement learning framework for shape optimization of airfoils 提出机制驱动的强化学习框架以优化翼型形状 manipulation reinforcement learning

🔬 支柱三:空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗
17 Density-Regression: Efficient and Distance-Aware Deep Regressor for Uncertainty Estimation under Distribution Shifts 提出Density-Regression以解决不确定性估计中的效率与距离感知问题 depth estimation

⬅️ 返回 cs.LG 首页 · 🏠 返回主页