cs.LG（2024-06-20）

📊 共 22 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) (7 🔗1) 支柱一：机器人控制 (Robot Control) (2) 支柱四：生成式动作 (Generative Motion) (1) 支柱八：物理动画 (Physics-based Animation) (1)

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

#题目一句话要点标签🔗⭐
1 Optimizing Novelty of Top-k Recommendations using Large Language Models and Reinforcement Learning 利用大语言模型和强化学习优化Top-k推荐的新颖性 reinforcement learning large language model
2 PostMark: A Robust Blackbox Watermark for Large Language Models 提出PostMark：一种针对大型语言模型的鲁棒黑盒水印方案，无需访问模型logits。 distillation large language model ✅
3 Revealing Vision-Language Integration in the Brain with Multimodal Networks 利用多模态网络揭示大脑中的视觉-语言融合机制 contrastive learning multimodal
4 Urban-Focused Multi-Task Offline Reinforcement Learning with Contrastive Data Sharing 提出MODA，通过对比数据共享解决城市多任务离线强化学习中的数据稀疏和异构问题。 reinforcement learning offline RL offline reinforcement learning
5 Bayesian Inverse Reinforcement Learning for Non-Markovian Rewards 提出基于贝叶斯逆强化学习的非马尔可夫奖励函数学习方法 reinforcement learning inverse reinforcement learning
6 A General Control-Theoretic Approach for Reinforcement Learning: Theory and Algorithms 提出一种基于控制理论的强化学习方法，提升策略学习的质量与效率。 reinforcement learning
7 Advantage Alignment Algorithms 提出优势对齐算法，解决通用博弈中智能体合作的帕累托次优问题。 reinforcement learning large language model
8 DeciMamba: Exploring the Length Extrapolation Potential of Mamba DeciMamba：探索Mamba模型在长度外推方面的潜力 Mamba
9 Revealing the Learning Process in Reinforcement Learning Agents Through Attention-Oriented Metrics 提出注意力导向指标ATOMs，揭示强化学习智能体在训练过程中的学习模式。 reinforcement learning
10 Revisiting Modularity Maximization for Graph Clustering: A Contrastive Learning Perspective 提出MAGI框架，利用对比学习视角下的模块度最大化进行图聚类，提升性能和可扩展性。 contrastive learning
11 ME-IGM: Individual-Global-Max in Maximum Entropy Multi-Agent Reinforcement Learning ME-IGM：最大熵多智能体强化学习中基于个体-全局最大化原则的算法 reinforcement learning

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

#题目一句话要点标签🔗⭐
12 Multi-modal Transfer Learning between Biological Foundation Models 提出IsoFormer，利用多模态生物序列信息预测RNA转录异构体表达水平。 large language model foundation model
13 Data-Centric AI in the Age of Large Language Models 针对大语言模型，提出以数据为中心的人工智能研究视角 large language model
14 LTSM-Bundle: A Toolbox and Benchmark on Large Language Models for Time Series Forecasting LTSM-Bundle：用于时间序列预测的大语言模型工具箱与基准测试 large language model
15 Synthesizing Multimodal Electronic Health Records via Predictive Diffusion Models 提出EHRPD，一种基于预测扩散模型的电子病历数据生成方法，解决现有方法在时间建模和表征学习上的不足。 multimodal
16 Jailbreaking as a Reward Misspecification Problem 提出基于奖励函数误设的LLM越狱攻击方法，提升对抗样本生成效果。 large language model
17 Demystifying Language Model Forgetting with Low-rank Example Associations 利用低秩示例关联揭示并缓解语言模型微调中的遗忘现象 large language model ✅
18 Causal Inference with Latent Variables: Recent Advances and Future Prospectives 综述：潜变量因果推断研究进展与未来展望 large language model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
19 Equivariant Offline Reinforcement Learning 提出SO(2)等变离线强化学习，提升低数据量机器人操作任务性能 manipulation reinforcement learning policy learning
20 Constrained Meta Agnostic Reinforcement Learning 提出C-MAML，解决Meta-RL在受限环境中快速适应的问题 locomotion reinforcement learning

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
21 Data-Driven Computing Methods for Nonlinear Physics Systems with Geometric Constraints 提出一种数据驱动框架，融合物理先验与机器学习解决非线性物理系统问题 physically plausible

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

#题目一句话要点标签🔗⭐
22 Physics-informed neural networks for parameter learning of wildfire spreading 提出基于物理信息神经网络的野火蔓延参数学习方法，用于构建野火数字孪生。 spatiotemporal

⬅️ 返回 cs.LG 首页 · 🏠 返回主页