cs.LG（2026-09-16）

📊 共 18 篇论文 | 🔗 1 篇有代码

🎯 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) (9 🔗1)

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

#题目一句话要点标签🔗⭐
1 Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening 提出SP$^3$O以解决PPO中的价值平坦化问题 reinforcement learning PPO large language model
2 The Attention Within: Consensus Dynamics in Selective State Space Models 提出选择性状态空间模型以解决变压器效率问题 Mamba SSM state space model
3 CoRe-MARL: Cooperative Redistribution Under Unknown Dynamics Using Recurrent Multi-Agent Reinforcement Learning 提出CoRe-MARL框架以解决应急管理中的资源再分配问题 reinforcement learning PPO
4 RLLBC-Lib: An Educational Code Library for Reinforcement Learning and Learning-Based Control 提出RLLBC-Lib以降低强化学习学习门槛 reinforcement learning
5 Comprehensive reconstruction of collider events with hypergraph representation learning and graph-conditioned diffusion 提出VyPER框架以解决粒子对撞机事件重建问题 representation learning
6 Online Robust Reinforcement Learning Through Monte-Carlo Planning 提出一种鲁棒的蒙特卡洛树搜索以解决动态模型不确定性问题 reinforcement learning
7 Label-free steering: Compressing test-time reinforcement learning into bias-only subspaces 提出无标签偏置引导方法以解决测试时强化学习问题 reinforcement learning
8 Trajectory Learnability for Offline On-Policy Distillation with Imperfect Teachers 提出基于成功教师的轨迹学习信号以优化离线蒸馏 distillation
9 APGEM: Adaptive Policy-Guided Error Mitigation for Quantum Reinforcement Learning on a Real-World CVRP Case Study 提出APGEM以解决量子强化学习中的误差缓解问题 reinforcement learning

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

#题目一句话要点标签🔗⭐
10 Benchmarking Tabular Foundation Models as Surrogates in Expensive Evolutionary Optimization 提出TabPFN作为代理模型以解决昂贵优化问题 foundation model
11 FoundAna: A GNN-assisted Foundation Model for Graph Anomaly Detection 提出FoundAna以解决图异常检测的跨图泛化问题 foundation model ✅
12 Higher-order pruning of experts in mixture-of-experts language models 提出HOPE方法以优化混合专家语言模型的专家剪枝 instruction following
13 Preventing Model Collapse: A Fisher-Rao Perspective on the Dynamics of Training with Synthetic Data 基于Fisher-Rao视角提出防止模型崩溃的新方法 large language model
14 Weakening Neurons: An Input-Output Functionality in Transformers with Outsize Influence 提出弱化神经元分析方法以揭示变压器模型功能 large language model
15 Peak-Aware Short-Term Load Forecasting Across Distribution Grid Aggregation Levels 提出峰值感知短期负荷预测以解决配电网聚合层次问题 foundation model
16 Bias Amplification in Multi-Agent Network: How Biased Agents Shape Opinions and Rhetoric 研究偏见在多智能体网络中的传播机制 large language model
17 Behavioral Fingerprinting and Navigation Prediction in Web Browsing 提出基于行为指纹的用户识别与导航预测方法 large language model
18 iMINDBench: iEEG Multi-Institution Neural Decoding Benchmark 提出iMINDBench以解决iEEG解码基准评估问题 foundation model

⬅️ 返回 cs.LG 首页 · 🏠 返回主页