cs.LG（2023-10-20）

📊 共 12 篇论文

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (7) 支柱九：具身大模型 (Embodied Foundation Models) (4) 支柱五：交互与反应 (Interaction & Reaction) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
1 Contrastive Preference Learning: Learning from Human Feedback without RL 提出对比偏好学习以解决人类反馈优化问题 reinforcement learning preference learning RLHF
2 Interpretable Deep Reinforcement Learning for Optimizing Heterogeneous Energy Storage Systems 提出可解释深度强化学习优化异构能源存储系统 reinforcement learning deep reinforcement learning
3 Towards Understanding How Transformers Learn In-context Through a Representation Learning Lens 通过表征学习视角探讨Transformer的上下文学习机制 representation learning contrastive learning large language model
4 Reward Shaping for Happier Autonomous Cyber Security Agents 提出奖励塑形方法以提升自主网络安全代理的训练效率 reinforcement learning deep reinforcement learning reward shaping
5 Spectral-Aware Augmentation for Enhanced Graph Representation Learning 提出GASSER以解决图对比学习中的频谱信息损失问题 representation learning contrastive learning
6 Automatic Unit Test Data Generation and Actor-Critic Reinforcement Learning for Code Synthesis 提出自动化单元测试数据生成与演员-评论家强化学习以提升代码合成能力 reinforcement learning PPO
7 A Better Match for Drivers and Riders: Reinforcement Learning at Lyft 提出在线强化学习算法以优化Lyft的司机与乘客匹配 reinforcement learning

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

#题目一句话要点标签🔗⭐
8 Foundation Model's Embedded Representations May Detect Distribution Shift 提出方法检测基础模型的分布偏移以提升迁移学习效果 foundation model
9 Enhancing Illicit Activity Detection using XAI: A Multimodal Graph-LLM Framework 提出多模态图-大语言模型框架以增强金融网络中的非法活动检测 multimodal
10 pFedLoRA: Model-Heterogeneous Personalized Federated Learning with LoRA Tuning 提出pFedLoRA以解决模型异构个性化联邦学习问题 large language model
11 Equivariant Transformer is all you need 提出对称等变注意力以改善自学习蒙特卡洛方法的接受率 large language model

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
12 Salted Inference: Enhancing Privacy while Maintaining Efficiency of Split Inference in Mobile Computing 提出盐分推理以解决移动计算中的输出隐私问题 OMOMO

⬅️ 返回 cs.LG 首页 · 🏠 返回主页