cs.LG（2024-06-14）

📊 共 19 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (12 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (5) 支柱八：物理动画 (Physics-based Animation) (1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#题目一句话要点标签🔗⭐
1 LUMA: A Benchmark Dataset for Learning from Uncertain and Multimodal Data LUMA：一个用于学习不确定和多模态数据的基准数据集 large language model multimodal ✅
2 Semantic Membership Inference Attack against Large Language Models 提出语义成员推理攻击SMIA，提升大型语言模型成员推断攻击效果 large language model
3 Deep Bayesian Active Learning for Preference Modeling in Large Language Models 提出BAL-PM，通过主动学习优化LLM偏好建模，显著降低标注成本。 large language model
4 QQQ: Quality Quattuor-Bit Quantization for Large Language Models QQQ：面向大语言模型的高质量四比特量化，加速推理。 large language model
5 Recent Advances in Federated Learning Driven Large Language Models: A Survey on Architecture, Performance, and Security 综述联邦学习驱动的大语言模型：架构、性能与安全性 large language model
6 Large language model validity via enhanced conformal prediction methods 提出增强型共形预测方法，提升大语言模型输出结果的有效性保证 large language model
7 MiNT: Multi-Network Training for Transfer Learning on Temporal Graphs 提出MiNT：一种用于时序图迁移学习的多网络训练方法 foundation model
8 BEACON: Benchmark for Comprehensive RNA Tasks and Language Models BEACON：RNA任务与语言模型综合基准，提升RNA序列理解能力 foundation model ✅
9 Quantifying Variance in Evaluation Benchmarks 量化评估基准中的方差，为LLM评估提供更可靠的性能比较依据 large language model
10 Evaluating LLM-driven User-Intent Formalization for Verification-Aware Languages 提出一种基于符号测试的规约质量评估方法，用于验证感知语言的用户意图形式化。 large language model
11 Unraveling the Mechanics of Learning-Based Demonstration Selection for In-Context Learning 揭示ICL中基于学习的示例选择机制，提升泛化性和效率。 large language model
12 TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphs TGB 2.0：用于时序知识图谱和异构图学习的基准测试框架 TAMP

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
13 Binary Reward Labeling: Bridging Offline Preference and Reward-Based Reinforcement Learning 提出二元奖励标记法，桥接离线偏好与基于奖励的强化学习 reinforcement learning offline RL offline reinforcement learning
14 DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning DigiRL：通过自主强化学习训练野外设备控制智能体 reinforcement learning offline RL behavior cloning
15 Robust Model-Based Reinforcement Learning with an Adversarial Auxiliary Model 提出基于对抗辅助模型的鲁棒模型强化学习方法，提升策略在扰动环境下的泛化能力。 reinforcement learning world model
16 Disentangled Hyperbolic Representation Learning for Heterogeneous Graphs 提出Dis-H²GCN，解决异构图嵌入中信息混杂和分布不匹配问题 representation learning
17 Misam: Using ML in Dataflow Selection of Sparse-Sparse Matrix Multiplication Misam：利用机器学习进行稀疏矩阵乘法数据流选择优化 reinforcement learning deep reinforcement learning

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

#题目一句话要点标签🔗⭐
18 Brain-Inspired Spike Echo State Network Dynamics for Aero-Engine Intelligent Fault Prediction 提出一种脑启发的Spike-ESN模型，用于提升航空发动机的智能故障预测精度。 spatiotemporal

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
19 A Comprehensive Benchmark on Spectral GNNs: The Impact on Efficiency, Memory, and Effectiveness 对谱图神经网络进行全面基准测试，评估其效率、内存和有效性 manipulation

⬅️ 返回 cs.LG 首页 · 🏠 返回主页