cs.LG（2026-07-13）

📊 共 22 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (13 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (7 🔗1) 支柱一：机器人控制 (Robot Control) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (13 篇)

#题目一句话要点标签🔗⭐
1 Surprisingly Simple and Effective Multi-Domain Graph Foundation Model through Graph-to-Table Alignment 提出GTAlign以解决图结构信息捕捉不足问题 large language model foundation model
2 MMRM: A Multiplex Multimodal Representation Model for Product Ranking in E-commerce Search 提出MMRM以解决电商搜索中的多模态信息利用不足问题 large language model multimodal
3 DAG-FM: A Foundation Model for Causal Discovery under Heterogeneous Causal Mechanisms 提出DAG-FM以解决异质因果机制下的因果发现问题 foundation model
4 CDFM: Towards a General-Purpose Causal Discovery Foundation Model 提出CDFM以解决因果发现中的数据异质性问题 foundation model
5 TabPFN beyond Tabular Data: Calibration and Accuracy on Multimodal Embeddings 提出TabPFN作为多模态分类的无梯度头以提升校准和准确性 multimodal ✅
6 A Multi-Agent Framework for Zero-Dimensional Reduced-Order Model Planning 提出Z-COPA框架以解决复杂0D模型规划问题 large language model chain-of-thought
7 From Expressivity to Sample Complexity: Narrow Teachers for Transformers via C-RASP 提出C-RASP构造的样本复杂度界限以优化Transformer学习 large language model
8 Proxy Exploration and Reusable Guidance: A Modular LLM Post-Training Paradigm via Proxy-Guided Update Signals 提出PUST框架以优化大语言模型的后训练过程 large language model
9 Agentic Skill Optimization over Lie Algebroids 提出LASKO框架以优化代理系统技能编辑 large language model
10 HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models 提出HyperSafe框架以解决语言模型安全性恢复问题 large language model ✅
11 PRISM Edit: One Vector for All Temporal Answers 提出PRISM Edit以解决时间信息更新问题 large language model ✅
12 FastTPS: An Optimized Method for LLM Token Phase for AI accelerators 提出FastTPS以解决LLM推理中的内存瓶颈问题 large language model
13 ToolAtlas: Learning Once, Reusing Everywhere with Tool-Side Memory 提出ToolAtlas以解决工具知识共享不足问题 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🔗⭐
14 Time-Lag-Aware Deep Reinforcement Learning for Flexible Job-Shop Scheduling in PPVC Module Factories 提出时间延迟感知深度强化学习以解决模块化工厂的灵活作业车间调度问题 reinforcement learning deep reinforcement learning
15 Active Offline-to-Online Reinforcement Learning 提出主动策略选择以解决有限交互预算下的O2O-RL问题 reinforcement learning offline RL offline reinforcement learning
16 CatRetriever: Contrastive Representation Learning for Slab-to-Bulk Retrieval in Generative Catalyst Discovery 提出CatRetriever以解决催化剂表面与体相结构检索问题 representation learning physically plausible
17 Heuristic Learning for Active Flow Control Using Coding Agents 提出编码智能体的启发式学习以解决主动流动控制问题 reinforcement learning deep reinforcement learning DRL ✅
18 Generalizing Preference-based Reinforcement Learning: a Rationality Model for Incomparability 提出一种理性模型以解决轨迹比较中的不可比性问题 reinforcement learning
19 A Novel Graph Fraud Detector via Grouped Attribute Completion and Confidence-Aware Contrastive Learning 提出GFD-GC框架以解决图欺诈检测中的属性不完整与类别不平衡问题 contrastive learning
20 AeroMELD: A Linear Embedding of Aerosol Populations for Diagnostics and Latent Dynamics 提出AeroMELD框架以改进气溶胶群体的表征与动态学习 latent dynamics

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
21 Velocity Scheduled Flow Matching 提出速度调度流匹配方法以提高样本生成效率 motion planning flow matching

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

#题目一句话要点标签🔗⭐
22 Neural Discovery of Memory and Nonlocal Kernels in Integro-Differential Equations with Constrained Kolmogorov--Arnold Networks 提出基于可微求解器的框架以发现积分微分方程中的记忆和非局部核 spatiotemporal

⬅️ 返回 cs.LG 首页 · 🏠 返回主页