cs.LG（2026-09-25）

📊 共 27 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (13 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (12 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱一：机器人控制 (Robot Control) (1)

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

#题目一句话要点标签🔗⭐
1 WorldTS: World Modeling for Multimodal Covariate-aware Time Series Forecasting 提出WorldTS框架以解决多模态时间序列预测问题 world model world models latent dynamics
2 Self-Supervised Representation Learning: From Spectral Foundation Models to Auroral Emission Spectra 提出自监督学习方法以提升极光光谱分类精度 representation learning masked autoencoder foundation model
3 I Act Therefore I Am: When Is JEPA's Action-Conditioning Enough to Learn Causal Mechanisms? 提出A-JEPA以解决因果机制学习问题 world model world models JEPA
4 PORL: Pretrained Offline Reinforcement Learning for the Job Shop Scheduling Problem 提出PORL以解决作业车间调度问题 reinforcement learning offline RL offline reinforcement learning
5 HySTAR: Anchored Hypergraphs for Stable Credit Assignment in Cooperative Multi-Agent Reinforcement Learning 提出HySTAR以解决合作多智能体强化学习中的信用分配问题 reinforcement learning representation learning spatiotemporal
6 User Model Extraction via Belief Self-Distillation 提出信念自蒸馏方法以提取用户模型 distillation large language model
7 MOPD-Router: Rethinking Teacher Routing in Multi-Teacher On-Policy Distillation 提出MOPD-Router以解决多教师蒸馏中的路由问题 teacher-student distillation ✅
8 Aligning One-Step Generative Models with Reward-Weighted Transport Distillation 提出奖励加权传输蒸馏方法以优化一步生成模型 distillation
9 More Sensors Only One Field: Rethinking Continual Spatio-Temporal Forecasting 提出STFO以解决传感器扩展下的时空预测问题 MAE spatial relationship ✅
10 A Flatness-Generalization Relation in the Teacher-Student Tree-Committee Machine 提出教师-学生树委员会机器的平坦性推广关系以研究泛化能力 teacher-student
11 Synth-JEPA: Joint Embedding Prediction for Renderer-Free Synthesizer Parameter Search 提出Synth-JEPA以解决合成器参数搜索中的渲染依赖问题 JEPA
12 LipSSM: Structurally Lipschitz-Bounded Cascaded State-Space Model via Metric Transfer between Consecutive SSM Layers 提出LipSSM以解决深度神经网络鲁棒性不足问题 SSM
13 Causal Retention in Interactive Agents: Interface Factorization and Selective Adaptation 提出因果保留机制以提升交互智能体的适应性 world model world models

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#题目一句话要点标签🔗⭐
14 EAServe: Encode-Aware Disaggregated Serving for Multimodal Large Language Models 提出EAServe以解决多模态大语言模型服务中的资源分配问题 large language model multimodal
15 The Linear Representation Hypothesis for Vision-Language-Action Models 提出线性表示假设以解决视觉-语言-动作模型的动态挑战 vision-language-action VLA large language model
16 Benchmarking Attention for Tabular Foundation Models 提出基准测试以优化表格基础模型的注意力机制 foundation model ✅
17 New LoRA Skills Should Read but Never Write 提出READ方法以解决LoRA适配器组合问题 large language model
18 BeatGraph: Self-Supervised Heartbeat Graphs for Infant ECG Representations from the Home Environment 提出BeatGraph以解决婴儿心电图表示问题 foundation model
19 Nonparametric In-Context Learning under Growing Geometric Complexity: Minimax Optimality and Local Geometry-Adaptivity of Transformers 提出一种新的变换器模型以解决复杂几何数据的非参数学习问题 large language model
20 Towards Understanding LLM-Based Log Anomaly Detection: An Empirical Study of Performance, Efficiency, and Robustness 通过实证研究揭示LLM在日志异常检测中的性能与效率 large language model
21 Aurora-X: Built for Extreme Time Series Forecasting 提出Aurora-X以解决时间序列预测的通用性与灵活性问题 foundation model
22 A Comprehensive Study of Content Representations for Speech Synthesis 提出统一生成框架以比较语音合成内容表示 multimodal
23 Towards Understanding Momentum Acceleration in River-Valley Loss Landscape 研究动量加速在河谷损失景观中的作用 large language model
24 CacheReforge: Bounded Recovery for Stale KV Caches under Evolving Adapters 提出CacheReforge以解决过时KV缓存带来的模型输出失真问题 large language model
25 Skill Profiling with Attributable Reasoning (SPAR): A Wearable Analysis System for Boxing 提出SPAR系统以解决拳击动作分析不足的问题 foundation model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
26 Scaling Density Functional Theory with Gaussian Splatting 提出GS-DFT以解决传统DFT计算的规模限制问题 3D gaussian splatting gaussian splatting splatting

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
27 Trust Guided Decision Transformer 提出信任引导决策变换器以解决长时间回放中的上下文漂移问题 locomotion decision transformer

⬅️ 返回 cs.LG 首页 · 🏠 返回主页