cs.LG（2025-01-17）
📊 共 17 篇论文 | 🔗 3 篇有代码
🎯 兴趣领域导航
支柱九：具身大模型 (Embodied Foundation Models) (7 🔗2)
支柱二：RL算法与架构 (RL & Architecture) (7 🔗1)
支柱八：物理动画 (Physics-based Animation) (3)
🔬 支柱九：具身大模型 (Embodied Foundation Models) (7 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Explainable artificial intelligence (XAI): from inherent explainability to large language models | 提出可解释人工智能方法以解决黑箱模型透明性问题 | large language model | ||
| 2 | Accelerating Large Language Models through Partially Linear Feed-Forward Network | TARDIS：通过部分线性化前馈网络加速大型语言模型 | large language model | ||
| 3 | MultiPruner: Balanced Structure Removal in Foundation Models | MultiPruner：一种用于基础模型中平衡结构移除的多维度剪枝方法 | foundation model | ✅ | |
| 4 | Interpretable Steering of Large Language Models with Feature Guided Activation Additions | 提出FGAA，通过特征引导激活添加实现对大语言模型的可解释性操控。 | large language model | ||
| 5 | New Fashion Products Performance Forecasting: A Survey on Evolutions, Models and Emerging Trends | 针对新时尚产品性能预测，提出基于学习的策略分类与综述，应对行业可持续发展挑战。 | multimodal | ||
| 6 | Differentiable Adversarial Attacks for Marked Temporal Point Processes | 提出PERMTPP，一种可微的对抗攻击方法，用于攻防时序点过程模型。 | TAMP | ||
| 7 | 4bit-Quantization in Vector-Embedding for RAG | 提出RAG中向量嵌入的4比特量化方法，降低内存占用并加速搜索。 | large language model | ✅ |
🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 8 | An Innovative Data-Driven and Adaptive Reinforcement Learning Approach for Context-Aware Prescriptive Process Monitoring | 提出FORLAPS框架，通过强化学习优化业务流程执行路径，实现情境感知的规范性流程监控。 | reinforcement learning offline reinforcement learning reward shaping | ||
| 9 | Enhancing UAV Path Planning Efficiency Through Accelerated Learning | 提出基于加速学习的无人机路径规划方法，提升效率并降低存储需求。 | reinforcement learning deep reinforcement learning DRL | ||
| 10 | Wasserstein Adaptive Value Estimation for Actor-Critic Reinforcement Learning | 提出WAVE以解决深度强化学习中的不稳定性问题 | reinforcement learning deep reinforcement learning | ||
| 11 | A Tensor Low-Rank Approximation for Value Functions in Multi-Task Reinforcement Learning | 提出基于张量低秩近似的多任务强化学习值函数优化方法 | reinforcement learning | ||
| 12 | ACCEPT: Diagnostic Forecasting of Battery Degradation Through Contrastive Learning | 提出ACCEPT模型以解决锂离子电池退化预测问题 | contrastive learning | ||
| 13 | PaSa: An LLM Agent for Comprehensive Academic Paper Search | PaSa：基于LLM Agent的综合学术论文搜索，显著提升搜索质量。 | reinforcement learning large language model | ✅ | |
| 14 | Sparse Binary Representation Learning for Knowledge Tracing | 提出SBRKT模型，通过学习稀疏二元表示的辅助知识概念增强知识追踪性能。 | representation learning |
🔬 支柱八：物理动画 (Physics-based Animation) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 15 | Adaptive Spatiotemporal Augmentation for Improving Dynamic Graph Learning | 提出STAA以解决动态图学习中的噪声边缘问题 | spatiotemporal | ||
| 16 | Temporal Graph MLP Mixer for Spatio-Temporal Forecasting | 提出T-GMM模型，解决时空预测中缺失数据下的长期依赖建模问题 | spatiotemporal | ||
| 17 | Convex Physics Informed Neural Networks for the Monge-Ampère Optimal Transport Problem | 提出基于凸物理信息神经网络的Monge-Ampère最优传输问题求解方法 | AMP |