cs.LG（2025-07-25）

📊 共 16 篇论文

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (9) 支柱九：具身大模型 (Embodied Foundation Models) (5) 支柱一：机器人控制 (Robot Control) (2)

🔬 支柱二：RL算法与架构 (RL & Architecture) (9 篇)

#题目一句话要点标签🔗⭐
1 Advancing Event Forecasting through Massive Training of Large Language Models: Challenges, Solutions, and Broader Impacts 通过大规模训练大型语言模型提升事件预测能力：挑战、解决方案与广泛影响 reinforcement learning large language model
2 GCL-GCN: Graphormer and Contrastive Learning Enhanced Attributed Graph Clustering Network GCL-GCN：结合Graphormer和对比学习的属性图聚类网络 contrastive learning spatial relationship
3 KD-GAT: Combining Knowledge Distillation and Graph Attention Transformer for a Controller Area Network Intrusion Detection System 提出KD-GAT，结合知识蒸馏与图注意力Transformer用于CAN总线入侵检测 distillation
4 Observations Meet Actions: Learning Control-Sufficient Representations for Robust Policy Generalization 提出BCPO算法，通过学习控制充分表征实现强化学习策略的鲁棒泛化 reinforcement learning policy learning representation learning
5 AGORA: Incentivizing Group Emergence Capability in LLMs via Group Distillation AGORA：通过群体蒸馏激励LLM涌现群体智能，提升复杂推理能力 distillation
6 ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs ProGMLP：一种渐进式GNN到MLP知识蒸馏框架，实现高效的精度-成本权衡 distillation
7 MindSpeed RL: Distributed Dataflow for Scalable and Efficient RL Training on Ascend NPU Cluster MindSpeed RL：昇腾NPU集群上可扩展高效强化学习训练的分布式数据流系统 reinforcement learning large language model
8 Reinforcement Learning via Conservative Agent for Environments with Random Delays 提出保守Agent，解决随机延迟环境下的强化学习问题 reinforcement learning
9 Learning Individual Intrinsic Reward in Multi-Agent Reinforcement Learning via Incorporating Generalized Human Expertise LIGHT：融合人类知识的多智能体强化学习个体奖励学习框架，提升稀疏奖励环境探索效率。 reinforcement learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#题目一句话要点标签🔗⭐
10 Short-Form Video Recommendations with Multimodal Embeddings: Addressing Cold-Start and Bias Challenges 提出基于多模态嵌入的短视频推荐系统，解决冷启动和偏差挑战 multimodal
11 Solar Photovoltaic Assessment with Large Language Model 提出PVAL框架，利用大语言模型提升卫星图像中光伏面板检测的准确性和泛化性。 large language model
12 AI Guided Accelerator For Search Experience 提出AI引导的加速器，通过建模用户搜索轨迹优化电商搜索体验 large language model
13 Step-3 is Large yet Affordable: Model-system Co-design for Cost-effective Decoding Step-3：面向解码成本优化的模型-系统协同设计，实现高性价比的大语言模型 large language model
14 Doubling Your Data in Minutes: Ultra-fast Tabular Data Generation via LLM-Induced Dependency Graphs SPADA：利用LLM诱导的稀疏依赖图实现超快速表格数据生成 large language model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
15 Salsa as a Nonverbal Embodied Language -- The CoMPAS3D Dataset and Benchmarks 提出CoMPAS3D数据集与基准，用于评估社交互动和创造性人形运动生成中的Salsa舞蹈AI。 humanoid motion generation embodied AI
16 Counterfactual Explanations in Medical Imaging: Exploring SPN-Guided Latent Space Manipulation 提出SPN引导的VAE潜在空间操控方法，用于生成医学影像反事实解释。 manipulation

⬅️ 返回 cs.LG 首页 · 🏠 返回主页