cs.LG（2026-09-10）

📊 共 18 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (10) 支柱二：RL算法与架构 (RL & Architecture) (6) 支柱一：机器人控制 (Robot Control) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#题目一句话要点标签🔗⭐
1 Evaluating Time-Series Foundation Models and Multimodal Dietary Context for CGM Forecasting 提出多模态饮食背景下的CGM预测方法以提升糖尿病管理 foundation model multimodal
2 Bidirectional Multimodal Fusion of Sky Images and Time-Series for Solar Forecasting with Large Language Models 提出SolCloudLLM以解决短期光伏发电预测中的多模态融合问题 large language model multimodal
3 CausalArena: Benchmarking Causal Discovery in the Foundation Model Era 提出CausalArena以解决因果发现评估的多样性问题 foundation model
4 Geospatial Foundation Models Capture Health-Relevant Dimensions of Place Beyond Conventional Social Risk Indices 提出地理基础模型以捕捉健康相关的地理特征 foundation model
5 LILA: Calibration-Free Structured Pruning of Large Language Models via Latent Spectral Geometry 提出LILA以解决大语言模型结构化剪枝中的校准问题 large language model
6 The information geometry of large language models is shared, learned, and controllable 提出几何结构以控制大型语言模型行为 large language model
7 Why Does Post-Training Quantization Work? 探讨后训练量化为何有效以提升大语言模型性能 large language model
8 Musec: MomentUm SpEctral Clipping for Stable Muon-type Training 提出MomentUm SpEctral Clipping以解决Muon训练不稳定问题 large language model
9 REVA: Reusable Evidence View Aggregation for Context-Efficient RAG Serving 提出REVA框架以解决RAG服务中的上下文效率问题 large language model
10 EMMI: Edge Multi-Modal Intelligence for Communication-Efficient MLLM Inference via Fused Representation Compression 提出EMMI以解决边缘设备上多模态大语言模型推理的通信效率问题 multimodal

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
11 Measuring the Value of World-Model Updates: A Counterfactual Utility Protocol for Continual Adaptation 提出分叉账本以评估世界模型更新的价值 world model world models
12 A Dataset and Model for Imputing Water Surface Elevation on a Large and Extremely Sparse Spatiotemporal Graph 提出AmazonSWE数据集与模型以解决水面高度估计问题 state space model spatiotemporal
13 Near-Optimal Reinforcement Learning with Multi-Step Transition Lookahead 提出多步转移前瞻的近似最优强化学习方法 reinforcement learning
14 When does a spectral prior help graph learning? Connectivity-loss estimation under road-network disruptions 提出基于图神经网络的连接损失估计方法以应对道路网络中断问题 MAE zero-shot transfer
15 HERALD: High-Fidelity Exemplar Retrieval with Adaptive Landmark Distillation for Heterophily-Aware Graph Condensation 提出HERALD以解决异质图的图凝聚问题 distillation
16 T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks 提出T1模型以解决长时间任务中的终端任务问题 reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
17 Topological Necessities: Mechanism-Invariant Strategic Subgoals for Cross-Embodiment Goal-Conditioned Control 提出拓扑必要性以解决跨体态目标条件控制问题 humanoid reinforcement learning cross-embodiment

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

#题目一句话要点标签🔗⭐
18 A Dynamic Fusion Large Language Model for Traffic Flow Prediction 提出动态融合大语言模型以解决交通流预测问题 spatiotemporal large language model

⬅️ 返回 cs.LG 首页 · 🏠 返回主页