cs.LG（2024-06-26）

📊 共 21 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) (10 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (9 🔗2) 支柱一：机器人控制 (Robot Control) (2)

🔬 支柱二：RL算法与架构 (RL & Architecture) (10 篇)

#题目一句话要点标签🔗⭐
1 Preference Elicitation for Offline Reinforcement Learning 提出Sim-OPRL算法，解决离线偏好强化学习中偏好反馈获取难题 reinforcement learning offline RL offline reinforcement learning
2 Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs Step-DPO：面向LLM长链推理的分步偏好优化方法 DPO direct preference optimization large language model ✅
3 Breaking the Barrier: Enhanced Utility and Robustness in Smoothed DRL Agents 提出S-DQN和S-PPO，提升平滑DRL智能体的效用性和鲁棒性 reinforcement learning deep reinforcement learning DRL
4 CREMA: A Contrastive Regularized Masked Autoencoder for Robust ECG Diagnostics across Clinical Domains CREMA：一种对比正则化掩码自编码器，用于跨临床领域的稳健心电图诊断 masked autoencoder MAE foundation model
5 Mental Modeling of Reinforcement Learning Agents by Language Models 利用语言模型对强化学习智能体进行心理建模，探索其行为理解能力 reinforcement learning large language model
6 Mixture of Experts in a Mixture of RL settings 在多任务强化学习中利用专家混合模型提升非平稳环境适应性 reinforcement learning deep reinforcement learning DRL
7 Reinforcement Learning with Intrinsically Motivated Feedback Graph for Lost-sales Inventory Control 提出基于内在激励反馈图的强化学习方法，提升缺货库存控制的样本效率。 reinforcement learning
8 PDFA Distillation via String Probability Queries 提出基于字符串概率查询的PDFA蒸馏算法，用于从神经网络中提取可解释模型。 distillation
9 Bidirectional-Reachable Hierarchical Reinforcement Learning with Mutually Responsive Policies 提出双向可达分层强化学习算法BrHPO，解决传统HRL单向依赖问题。 reinforcement learning
10 Combining Automated Optimisation of Hyperparameters and Reward Shape 提出超参数与奖励函数联合优化方法，提升强化学习在复杂任务中的性能与稳定性。 reinforcement learning deep reinforcement learning

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

#题目一句话要点标签🔗⭐
11 WV-Net: A foundation model for SAR WV-mode satellite imagery trained using contrastive self-supervised learning on 10 million images WV-Net：基于对比自监督学习的SAR WV模式卫星图像基础模型，使用1000万张图像训练。 foundation model
12 ADO-LLM: Analog Design Bayesian Optimization with In-Context Learning of Large Language Models ADO-LLM：结合大语言模型上下文学习的模拟电路设计贝叶斯优化 large language model
13 A Review of Large Language Models and Autonomous Agents in Chemistry 综述：大型语言模型与自主智能体在化学领域的应用与发展 large language model ✅
14 A Survey on Mixture of Experts in Large Language Models 对大型语言模型中混合专家模型（MoE）的综述，旨在系统性地回顾和分类MoE方法。 large language model ✅
15 MolFusion: Multimodal Fusion Learning for Molecular Representations via Multi-granularity Views 提出MolFusion，通过多粒度视图融合学习分子表示，提升药物性质预测。 multimodal
16 Foundational Models for Pathology and Endoscopy Images: Application for Gastric Inflammation 利用病理和内窥镜图像的基础模型辅助胃部炎症诊断 foundation model multimodal
17 Learning to Correct for QA Reasoning with Black-box LLMs 提出CoBB方法，通过训练适配模型提升黑盒LLM的QA推理能力 large language model
18 Few-shot Personalization of LLMs with Mis-aligned Responses 提出Fermi，利用少量样本和偏差响应实现LLM的个性化定制 large language model
19 RouteLLM: Learning to Route LLMs with Preference Data RouteLLM：利用偏好数据学习路由LLM，优化成本与性能的平衡 large language model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
20 Adversarial Search Engine Optimization for Large Language Models 提出针对大语言模型的对抗性搜索引擎优化攻击，操纵LLM偏好选择。 manipulation large language model
21 Jailbreaking LLMs with Arabic Transliteration and Arabizi 利用阿拉伯语音译和Arabizi破解大型语言模型 manipulation large language model

⬅️ 返回 cs.LG 首页 · 🏠 返回主页