cs.LG（2026-08-19）

📊 共 23 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (9) 支柱二：RL算法与架构 (RL & Architecture) (9 🔗1) 支柱一：机器人控制 (Robot Control) (5)

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

#题目一句话要点标签🔗⭐
1 Role-Conditioned Sub-Token Routing for Efficient Vision-Language-Action Policies 提出Role-Conditioned Sub-Token Routing以解决VLA模型效率问题 vision-language-action VLA multimodal
2 Monroe: A Molecular Foundation Model for In-Context Probabilistic Inference 提出Monroe以解决生物测定活动预测中的数据限制问题 foundation model
3 Training Chemical Plausibility-Aware Large Language Models for Single-Step Retrosynthesis 提出Top-K提示以解决单步逆合成的多样性问题 large language model
4 Harness Continual Learning: Continual Adaptation Beyond Model Parameters 提出Harness Continual Learning以解决模型参数外的持续学习问题 foundation model multimodal
5 Lévy Attention: Single-Pass Predictive Uncertainty for Continuous-Time Attention 提出Lévy Attention以解决时间序列预测的不确定性问题 TAMP
6 Diffusion Models for High-Dimensional Clustered Data: Intrinsic-Dimension Adaptivity via Bayesian Classification 提出扩展的扩散模型以适应高维聚类数据的内在维度 multimodal
7 Computational Measurement of Team-Process Phase Dynamics in Collaborative Virtual Reality 提出计算框架以动态分析协作虚拟现实中的团队过程 large language model
8 Evaluating and Explaining Prompt Sensitivity of LLMs Using Interactions 提出交互分析方法以解决大语言模型的提示敏感性问题 large language model
9 Mechanistic Interpretability of Structure-Aware Numerical Reasoning in LLaMA 3.1 8B 通过机制可解释性研究LLaMA 3.1在数值推理中的结构感知能力 large language model

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

#题目一句话要点标签🔗⭐
10 GEAR: Generative Expansion and Real Anchoring for Two-Stage Distillation of Tabular Foundation Models 提出GEAR框架以解决表格基础模型的延迟和内存问题 distillation foundation model
11 Multi-Agent Off-Policy Deep Reinforcement Learning for Smart Campus Coverage 提出多智能体离线深度强化学习以优化智能校园覆盖问题 reinforcement learning deep reinforcement learning DRL
12 Open-MOPD: Diagnosing and Fixing Capability Imbalance in Multi-Teacher On-Policy Distillation 提出Open-MOPD以解决多教师策略蒸馏中的能力不平衡问题 reinforcement learning distillation instruction following
13 MARCUS: Missing-Aware Region Representation with Contextual Urban Signals for Rent Prediction 提出MARCUS以解决城市区域租金预测中的缺失数据问题 representation learning MAE multimodal
14 Beyond Teacher Likelihood: Group-Calibrated On-Policy Distillation for Long-Context Reasoning 提出群体校准的在线蒸馏方法以解决长上下文推理问题 distillation ✅
15 Continuous-Time Reinforcement Learning for Controlled Hawkes Jump-Diffusions 提出连续时间强化学习方法解决Hawkes跳跃扩散控制问题 reinforcement learning
16 Does Mapping Non-Maximal Probabilities to GMM Components Matter for S-JEPA Encoder Representations? 提出S-JEPA方法以优化GMM组件概率映射问题 JEPA
17 LLM-Powered Predictive Decision-Making for Sustainable Data Center Operations 提出基于LLM的预测调度系统以提升数据中心可持续性 predictive model large language model
18 Adaptive Multi-Agent Feature Selection for Personalized Fall Risk Prevention 提出PAFIR框架以解决个性化跌倒风险预防问题 reinforcement learning multimodal

🔬 支柱一：机器人控制 (Robot Control) (5 篇)

#题目一句话要点标签🔗⭐
19 MLREF: Efficient Module Reuse for Reward Design in Reinforcement Learning via Large Language Models 提出MLREF框架以解决强化学习中的奖励函数设计问题 locomotion manipulation reinforcement learning
20 Decision-Metric Alignment in Latent World Models: Diagnostics and Action-Conditioned Objectives for MPC Planning 提出决策度量对齐方法以优化潜在世界模型中的MPC规划 MPC world model world models
21 Reinforced Planning with Latent World Models 提出强化规划方法以解决多步计划改进问题 manipulation world model world models
22 FedLNS: Leverage LayerNorm Signature Modeling to Mitigate Adversarial Manipulation in Federated LLMs 提出FedLNS以解决联邦学习中的恶意更新问题 manipulation
23 Graphical Design of Interpretable Architectures 提出图形化设计方法以解决可解释架构表示不足问题 manipulation

⬅️ 返回 cs.LG 首页 · 🏠 返回主页