cs.LG（2026-07-06）

📊 共 23 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) (17 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (3 🔗1) 支柱四：生成式动作 (Generative Motion) (1) 支柱五：交互与反应 (Interaction & Reaction) (1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (17 篇)

#题目一句话要点标签🔗⭐
1 Context-Constrained Transfer Learning for Tabular Foundation Models via Data Distillation 提出TL-ANDI以解决TFMs在迁移学习中的限制问题 distillation foundation model
2 Qantara: Bridge-Flow Training for Multi-Paradigm JEPA Control 提出Qantara以实现多范式JEPA控制 flow matching world model world models
3 Integrating Neural Encoders in Bayesian Generalized Linear Mixed Models for Multimodal Data 提出神经编码器与贝叶斯广义线性混合模型结合以解决多模态数据分析问题 representation learning multimodal
4 FUSE: FK-Steered Multi-Modal Flow Matching for Efficient Simulation-Based Posterior Estimation 提出FUSE以解决多模态流匹配的后验估计问题 flow matching multimodal
5 Weak-to-Strong Generalization via Direct On-Policy Distillation 提出直接在线策略蒸馏以解决强化学习模型训练瓶颈问题 reinforcement learning distillation
6 Relational Multi-Agent Reinforcement Learning for Dynamic Pricing in High-Speed Railway Markets 提出基于关系图的多智能体强化学习以解决高铁市场动态定价问题 reinforcement learning representation learning ✅
7 Platonic Projection Structures: Operator-Induced Observability in Representation Learning 提出Platonic投影结构以解决表示学习中的可观测性问题 representation learning distillation
8 RL-Ballast: Ship Ballast Water Path Planning and Clog Prediction via Reinforcement Learning 提出RL-Ballast以解决船舶压载水路径规划与堵塞预测问题 reinforcement learning deep reinforcement learning
9 KinEMbed: Decoding Kinematics from Electromyography via Cross-Modal Contrastive Learning 提出KinEMbed以解决从表面肌电图解码手部运动学问题 representation learning contrastive learning
10 RSPO: Reward-Swap Policy Optimization for Multi-Turn LLM Agents 提出RSPO以解决多轮交互任务中的稀疏奖励问题 reinforcement learning PPO large language model
11 CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents 提出CompactionRL以解决长时间跨度强化学习中的上下文限制问题 reinforcement learning
12 Non-Convex Sparse Reinforcement Learning via Non-Monotone Inclusions 提出非凸稀疏强化学习方法以解决特征选择问题 reinforcement learning
13 Multi-Turn On-Policy Distillation with Prefix Replay 提出Replayed-Prefix On-Policy Distillation解决多回合蒸馏问题 distillation
14 Trust Region Policy Distillation 提出信任区域策略蒸馏以解决不稳定训练问题 distillation
15 Beyond the Need for Speed: Energy-Aware Code Generation via Simulation-Guided Reinforcement Learning 提出能量感知代码生成方法以优化软件能效 reinforcement learning
16 Fitted Occupancy-Ratio Evaluation without Bellman Completeness 提出拟合占用比评估方法以解决离线强化学习中的分布偏移问题 reinforcement learning offline reinforcement learning
17 Adaptive Inference Batching using Policy Gradients 利用强化学习实现自适应推理批处理以优化系统性能 reinforcement learning PPO

🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)

#题目一句话要点标签🔗⭐
18 Beyond Modality Fusion: Deep Ensembles for Multimodal Classification 提出深度集成方法以解决多模态分类中的模态融合问题 multimodal
19 When Do Foundation Models Pay Off? A Break-Even Analysis of Pretrained Time Series Forecasters 提出基础模型的盈亏平衡分析以优化时间序列预测 foundation model ✅
20 Train Smarter, Not Longer: Memorization-Guided Data Reuse for Efficient LLM Training 提出记忆引导的数据重用方法以提高LLM训练效率 large language model

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
21 What Does a Discrete Diffusion Model Learn? 提出离散扩散模型的学习机制以优化数据熵 MDM

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
22 Layer-Parallel Inference Reduces Encrypted Nonlinear Depth in Transformers 提出结构化牛顿层并行以降低变换器的加密非线性深度 OMOMO

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
23 Decomposition for Bayesian Networks: Local and Parallel Inference 提出基于d-分解树的贝叶斯网络推理框架以提高计算效率 manipulation

⬅️ 返回 cs.LG 首页 · 🏠 返回主页