cs.LG（2026-11-02）

📊 共 32 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (16 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (13 🔗3) 支柱一：机器人控制 (Robot Control) (1) 支柱四：生成式动作 (Generative Motion) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (16 篇)

#题目一句话要点标签🔗⭐
1 Zero-shot time-series foundation models against the Khepri v1.5 baselines for 96-hour carbon-intensity forecasts in nine Nordic bidding zones: a preregistered comparison 提出零-shot时间序列基础模型以提高碳强度预测精度 foundation model TAMP
2 Evaluating Uncertainty Calibration in Probabilistic Time Series Foundation Models 提出不确定性校准框架以提升时间序列基础模型的可靠性 foundation model
3 A Common Language for Dynamic Graphs: Interaction Tokenization Enables Foundation Models 提出CL-DGFM以解决动态图预测中的交互表示问题 foundation model
4 Hybrid Federated Learning for Multimodal Fusion under Missing Modalities and Site Heterogeneity 提出混合联邦学习以解决多模态融合中的缺失模态和站点异质性问题 multimodal
5 Investigating the effects of the patch size in Time Series Foundation Models 研究补丁大小对时间序列基础模型的影响 foundation model
6 HistoTx: Early fusion of H&E images and spatial transcriptomics at varying spatial transcriptomics resolution with self-supervised learning 提出HistoTx以实现H&E图像与空间转录组早期融合 foundation model multimodal
7 Pretraining Data Scale Reverses the Muon-AdamW Fine-Tuning Gap 研究发现预训练数据规模逆转Muon-AdamW微调差距 large language model
8 Neural Actor--Critic Learning with Minimax Critics and Reflected Langevin Sampling 提出神经演员-评论家方法以解决连续动作策略的优化问题 multimodal
9 EventGPT: Next-Event Pretraining on Banking Customer Histories 提出EventGPT以解决银行客户事件预测问题 multimodal
10 ENGINE: Endogenous Variational MultiScale Optimization for Zeroth-Order LLM Fine-Tuning 提出ENGINE以解决高维LLM优化中的梯度方差问题 large language model ✅
11 LaBraM at Scale: Scaling Data and Models for EEG Pretraining 扩展LaBraM以提升EEG预训练模型的表现 foundation model
12 Utility-Aware Generative Recommendation: Utility-Enriched Semantic Codes and Utility-Guided Decoding 提出UAGR以解决生成推荐中的效用不足问题 multimodal
13 SynForecast: Controlled Synthetic Time Series for Forecasting Research 提出SynForecast以解决合成时间序列生成的控制性问题 foundation model
14 POD-CNF: reduced order modeling of parametrized stochastic PDEs via normalizing flows and proper orthogonal decomposition 提出POD-CNF以解决参数化随机偏微分方程的建模问题 multimodal
15 Evolving Explanations: Complexity-Adaptive Refinement of Faithful Explanations for Symbolic Regression 提出复杂性自适应框架以改进符号回归的可信解释 large language model
16 Adaptive Localization of Knowledge Negation for Continual LLM Unlearning 提出自适应知识否定定位方法以解决持续LLM遗忘问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (13 篇)

#题目一句话要点标签🔗⭐
17 Efficient Detailed Scheduling of Multiproduct Pipelines using Action-Decoupled Deep Reinforcement Learning 提出动作解耦的深度强化学习框架以优化多产品管道调度 reinforcement learning deep reinforcement learning PPO
18 Inferring Transferable Rewards via Active Inverse Reinforcement Learning 提出主动逆强化学习以推断可转移奖励 reinforcement learning inverse reinforcement learning
19 Diagonal Equivalence in State Space Models: Characterization, Retrieval Rank, and Selective Extensions 提出对角等价的状态空间模型以提升多输入多输出性能 Mamba SSM state space model
20 The Cost of Mismatch: Noise Amplification in Zeroth-Order Reinforcement Learning 提出ZO-BOLT以解决零阶强化学习中的噪声放大问题 reinforcement learning large language model ✅
21 DeepWaveRL: Self-Supervised Full Waveform Inversion via Reinforcement Learning 提出DeepWaveRL以解决全波形反演中的梯度获取问题 reinforcement learning policy learning
22 Not All Reasoning Generalizes: A Case Study on Learning Generalizable Reasoning Strategies in RLVR 提出RLVR框架以解决推理策略泛化问题 reinforcement learning large language model ✅
23 Bridging Neural Tangent Kernel Analysis and Reinforcement Learning for Deep Function Approximation 将神经切线核分析与强化学习结合以优化深度函数逼近 reinforcement learning
24 An Axiomatic Framework for Reinforcement Learning in Open Multi-Agent Systems 提出公理框架以解决开放多智能体系统中的强化学习问题 reinforcement learning ✅
25 Forecasting How RLHF Responds to Reward-Model Edits Before Training 提出预测RLHF对奖励模型编辑响应的方法以优化训练 RLHF
26 CARE: Contrastive Representation Learning with Environment-Invariance Regularization for Behavioural Intention Prediction 提出CARE框架以解决轨迹行为意图预测中的环境变化问题 representation learning
27 Replay for LLM Continual Learning with Multi-Teacher On-Policy Distillation 提出多教师在线蒸馏方法以解决持续学习中的知识遗忘问题 distillation
28 Whitened Advantage Summation Policy Optimization: Correlation-Aware Aggregation for Multi-Reward Reinforcement Learning 提出WAS-PO以解决多奖励强化学习中的相关性问题 reinforcement learning
29 Beyond $L_\infty$-Norm Sets: Synthesizing Interpretable Non-Uniform Uncertainty Sets for Evaluation-Time State-Adversarial Robustness 提出性能退化非均匀不确定性集以解决DRL政策脆弱性问题 reinforcement learning deep reinforcement learning DRL

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
30 From PID to Reinforcement Learning in Building HVAC Control: A Control-Architecture Review of Tuning Strategies, Formulations, and Deployment Trade-offs 提出强化学习与PID控制结合以优化建筑HVAC系统 model predictive control reinforcement learning

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
31 Online Class Posteriors for Interpretable and Controllable Discrete Diffusion 提出在线类后验以实现可解释和可控的离散扩散模型 classifier-free guidance

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

#题目一句话要点标签🔗⭐
32 Architecture-Aware Mixed Precision for Replica-Exchange Training of Geometry-Aware Neural Operators with Uncertainty Quantification 提出架构感知混合精度以提升几何感知神经算子的训练效率 AMP

⬅️ 返回 cs.LG 首页 · 🏠 返回主页