cs.LG（2024-05-07）

📊 共 13 篇论文 | 🔗 1 篇有代码

🎯 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 🔗1) 支柱八：物理动画 (Physics-based Animation) (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) (7 篇)

#题目一句话要点标签🔗⭐
1 Robust Implementation of Retrieval-Augmented Generation on Edge-based Computing-in-Memory Architectures 提出RoCR框架，利用存内计算加速边缘设备上的检索增强生成。 contrastive learning large language model
2 xLSTM: Extended Long Short-Term Memory xLSTM：通过扩展LSTM结构，提升语言建模性能并实现可扩展性。 state space model large language model
3 Representation Learning of Daily Movement Data Using Text Encoders 提出基于文本编码器的日常活动表征学习方法，用于痴呆症患者的远程健康监测。 representation learning
4 The Curse of Diversity in Ensemble-Based Exploration 揭示并缓解基于集成探索的深度强化学习中存在的“多样性诅咒”现象 reinforcement learning deep reinforcement learning representation learning
5 Ranking-based Client Selection with Imitation Learning for Efficient Federated Learning 提出FedRank，通过模仿学习预训练的排序方法，高效选择联邦学习客户端。 imitation learning
6 SwiftRL: Towards Efficient Reinforcement Learning on Real Processing-In-Memory Systems SwiftRL：探索基于PIM系统的强化学习加速方法 reinforcement learning
7 Proximal Policy Optimization with Adaptive Exploration 提出自适应探索的近端策略优化算法(axPPO)，提升强化学习效率。 reinforcement learning PPO

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

#题目一句话要点标签🔗⭐
8 KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization 提出耦合量化(CQ)，实现KV缓存1比特量化，提升大语言模型推理效率。 large language model
9 Sora Detector: A Unified Hallucination Detection for Large Text-to-Video Models 提出SoraDetector，用于统一检测大型文本生成视频模型中的幻觉问题 large language model multimodal
10 Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics 通过训练动态理论分析逆转诅咒问题 large language model chain-of-thought ✅
11 Interpretable Tensor Fusion 提出InTense，用于可解释的多模态数据融合与表示学习 multimodal

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

#题目一句话要点标签🔗⭐
12 BUDDy: Single-Channel Blind Unsupervised Dereverberation with Diffusion Models 提出基于扩散模型的单通道盲源解混响方法BUDDy PULSE

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

#题目一句话要点标签🔗⭐
13 Scalable physical source-to-field inference with hypernetworks 提出一种可扩展的超网络模型以解决源到场的推断问题 implicit representation

⬅️ 返回 cs.LG 首页 · 🏠 返回主页