cs.LG（2024-09-11）

📊 共 14 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (7 🔗3) 支柱九：具身大模型 (Embodied Foundation Models) (5 🔗1) 支柱一：机器人控制 (Robot Control) (2 🔗1)

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

#题目一句话要点标签🔗⭐
1 What to align in multimodal contrastive learning? 提出CoMM，通过对比多模态学习实现模态间共享、协同和独特信息的有效对齐。 contrastive learning multimodal ✅
2 Policy Filtration for RLHF to Mitigate Noise in Reward Models 提出策略过滤PPO（PF-PPO）以提升RLHF中奖励模型的信噪比，优化代码生成和数学推理任务。 reinforcement learning policy learning PPO ✅
3 Mamba for Scalable and Efficient Personalized Recommendations 提出FT-Mamba以解决个性化推荐系统的效率问题 Mamba SSM state space model
4 The Role of Deep Learning Regularizations on Actors in Offline RL 在离线强化学习中，对Actor网络应用深度学习正则化可显著提升性能。 reinforcement learning offline RL
5 Online Decision MetaMorphFormer: A Casual Transformer-Based Reinforcement Learning Framework of Universal Embodied Intelligence 提出在线决策MetaMorphFormer，解决具身智能通用性与泛化性难题。 reinforcement learning ✅
6 Mapping the Russian Internet Troll Network on Twitter using a Predictive Model 提出一种预测模型，用于识别和绘制Twitter上俄罗斯网络水军的活动图谱。 predictive model
7 A Continual and Incremental Learning Approach for TinyML On-device Training Using Dataset Distillation and Model Size Adaption 提出一种TinyML设备端持续增量学习算法，结合数据集蒸馏与模型自适应。 distillation

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#题目一句话要点标签🔗⭐
8 Inf-MLLM: Efficient Streaming Inference of Multimodal Large Language Models on a Single GPU Inf-MLLM：在单GPU上实现多模态大语言模型的高效流式推理 large language model multimodal
9 Three-Dimensional, Multimodal Synchrotron Data for Machine Learning Applications 构建用于机器学习的三维多模态同步辐射数据集，助力算法开发 multimodal
10 HESSO: Towards Automatic Efficient and User Friendly Any Neural Network Training and Pruning 提出HESSO：一种自动、高效、用户友好的神经网络训练与剪枝方法 large language model
11 LLM-based feature generation from text for interpretable machine learning 提出基于LLM的文本特征生成方法，为可解释机器学习提供低维、语义化的特征表示。 large language model
12 Representation Tuning 提出表征调优方法，通过微调激活向量提升LLM的安全性，无需在线控制。 large language model ✅

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
13 Multi-Type Preference Learning: Empowering Preference-Based Reinforcement Learning with Equal Preferences 提出多类型偏好学习(MTPL)，通过融合等同偏好提升基于偏好的强化学习效果 locomotion manipulation reinforcement learning ✅
14 AI-Guided Molecular Simulations in VR: Exploring Strategies for Imitation Learning in Hyperdimensional Molecular Systems 利用VR中的AI引导分子模拟：探索超高维分子系统中模仿学习的策略 manipulation imitation learning reward design

⬅️ 返回 cs.LG 首页 · 🏠 返回主页