cs.LG（2026-08-24）

📊 共 21 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (11 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (9 🔗2) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (11 篇)

#	题目	一句话要点	标签	🔗	⭐
1	LpWM: A Case for Sparse Representations in World Models	提出LpWM以解决动态建模中的稠密表示问题	world model worldmodel world models
2	ReCoG: Reciprocal Co-Evolution for Multimodal Graph Learning	提出ReCoG以解决多模态图学习中的结构与语义耦合问题	representation learning foundation model multimodal
3	RIBOSPAN: A Long-Context RNA Foundation Model for Versatile RNA Modeling	提出RIBOSPAN以解决长序列RNA建模问题	representation learning foundation model
4	Thinking at the Right Size: Amortized Distillation Across Post-Trained LLMs	提出ADAPT框架以优化后训练大语言模型的蒸馏过程	teacher-student distillation large language model
5	MOSH-WM: Mask-Grounded Soft-Hamiltonian Dynamics for Object-Centric World Models	提出MOSH-WM以解决对象中心世界模型的动态监督问题	world model world models	✅
6	Interpretable AI with Local Distillation	提出局部蒸馏方法以提升AI模型的可解释性	distillation foundation model
7	Spiking Neural Networks for Continuous Control: Neuromorphic Reinforcement Learning in Conventional Computing	提出脉冲神经网络以解决连续控制中的强化学习问题	reinforcement learning SAC
8	Macro-Action Topological Navigation under Noisy Localization using Reinforcement Learning	提出基于强化学习的宏观动作拓扑导航以解决噪声定位问题	reinforcement learning
9	How to Train a Critic Stably and Efficiently	提出最佳实践评论优化方法以解决评论训练不稳定问题	reinforcement learning large language model	✅
10	Graph Representation Learning of Lightweight IoT Ciphers	提出图表示学习方法以提升轻量级IoT密码的差分分析	representation learning
11	FedCC: Towards Addressing Label Distribution Skews in Distillation-Based Federated Learning	提出FedCC以解决蒸馏基础联邦学习中的标签分布偏斜问题	distillation

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#	题目	一句话要点	标签	🔗	⭐
12	From Multimodal Observation to Interpretable Suggestions: Counterfactual Time-Expanded Relational Modeling of Surgical Teams	提出时间扩展关系建模框架以改善外科团队协作	multimodal
13	Do Time-Series Foundation Models Pay Off for Industrial Monitoring? A Cost-Aware Empirical Study	评估时间序列基础模型在工业监控中的应用价值	foundation model
14	MetaCaster: Meta-Harness-Optimized Agent for End-to-End Few-Shot Learning of Lightweight Time Series Forecasters	提出MetaCaster以解决轻量级时间序列预测的少样本学习问题	foundation model multimodal
15	Hierarchical Exponential-Gaussian Mixtures for Watch-Time Distribution Prediction	提出层次化指数-高斯混合模型以解决观看时间预测问题	multimodal	✅
16	Reservoir of Importance: Learning Semi-Structured Sparsity with Differentiable Subset Sampling	提出Reservoir of Importance以解决大语言模型稀疏性问题	large language model
17	ST$^2$U: Stateful Test-Time Unlearning via Restricted Knowledge Boundary Control	提出ST$^2$U以解决大语言模型的状态性测试时遗忘问题	large language model
18	SplitLite: Low-Rank Residual Compression for Split Learning	提出SplitLite以解决分布式学习中的通信成本问题	large language model
19	A Physical Response-and-Memory Model for Muon Optimization	提出物理响应与记忆模型以优化Muon算法	large language model
20	Hierarchy-Aware Supervised Uncertainty Estimation for Black-box LLM Taxonomic Reasoning	提出层次感知监督不确定性估计以解决黑箱LLM分类推理问题	large language model	✅

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

#	题目	一句话要点	标签	🔗	⭐
21	Beyond Point Predictions: Uncertainty-Aware Satellite Poverty Mapping for Public Policy	提出不确定性感知的卫星贫困映射方法以支持公共政策	spatiotemporal

⬅️ 返回 cs.LG 首页 · 🏠 返回主页