cs.LG（2025-09-21）

📊 共 12 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (6) 支柱九：具身大模型 (Embodied Foundation Models) (4 🔗2) 支柱四：生成式动作 (Generative Motion) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Causal Representation Learning from Multimodal Clinical Records under Non-Random Modality Missingness	针对临床记录缺失场景，提出因果表征学习框架，提升多模态融合效果。	representation learning contrastive learning large language model
2	GRPOformer: Advancing Hyperparameter Optimization via Group Relative Policy Optimization	GRPOformer：通过群组相对策略优化提升超参数优化性能	reinforcement learning large language model
3	The Complexity of Finding Local Optima in Contrastive Learning	证明对比学习中局部最优解的复杂性	contrastive learning
4	TraceHiding: Scalable Machine Unlearning for Mobility Data	提出TraceHiding框架以解决移动数据的机器遗忘问题	teacher-student distillation
5	On the Limits of Tabular Hardness Metrics for Deep RL: A Study with the Pharos Benchmark	研究表明表格型硬度指标难以有效评估深度强化学习环境难度，并提出Pharos基准。	reinforcement learning deep reinforcement learning
6	NeuFACO: Neural Focused Ant Colony Optimization for Traveling Salesman Problem	提出NeuFACO，结合神经启发式与蚁群优化求解旅行商问题	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	🔗	⭐
7	PTQTP: Post-Training Quantization to Trit-Planes for Large Language Models	提出PTQTP：一种面向大语言模型的后训练三元平面量化方法，实现高效推理。	large language model	✅
8	Adaptive Graph Convolution and Semantic-Guided Attention for Multimodal Risk Detection in Social Networks	提出自适应图卷积和语义引导注意力机制，用于社交网络中的多模态风险检测	multimodal
9	TSGym: Design Choices for Deep Multivariate Time-Series Forecasting	TSGym：通过细粒度组件选择与自动模型构建，提升多元时间序列预测性能。	large language model foundation model	✅
10	SignalLLM: A General-Purpose LLM Agent Framework for Automated Signal Processing	提出SignalLLM：一个面向自动化信号处理的通用LLM Agent框架	large language model

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
11	Ultra-short-term solar power forecasting by deep learning and data reconstruction	提出基于深度学习和数据重构的超短期太阳能发电功率预测方法	penetration

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

#	题目	一句话要点	标签	🔗	⭐
12	Dendritic Resonate-and-Fire Neuron for Effective and Efficient Long Sequence Modeling	提出D-RF神经元模型，有效且高效地处理长序列建模任务。	spatiotemporal

⬅️ 返回 cs.LG 首页 · 🏠 返回主页