cs.LG（2025-09-04）

📊 共 26 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (14 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (10) 支柱一：机器人控制 (Robot Control) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (14 篇)

#题目一句话要点标签🔗⭐
1 Vehicle-to-Infrastructure Collaborative Spatial Perception via Multimodal Large Language Models 提出基于BEV注入的多模态大语言模型，提升V2I通信链路质量预测精度。 large language model multimodal
2 Multimodal Deep Learning for ATCO Command Lifecycle Modeling and Workload Prediction 提出多模态深度学习框架，用于空管指挥生命周期建模与工作负荷预测 multimodal
3 Delta Activations: A Representation for Finetuned Large Language Models 提出Delta Activations，通过激活值变化表征微调后的大语言模型，实现模型聚类、选择与合并。 large language model ✅
4 IPA: An Information-Reconstructive Input Projection Framework for Efficient Foundation Model Adaptation 提出IPA：一种信息重构的输入投影框架，用于高效地微调预训练模型。 foundation model ✅
5 PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference PagedEviction：用于高效大语言模型推理的结构化块级KV缓存剪枝 large language model
6 COBRA: Multimodal Sensing Deep Learning Framework for Remote Chronic Obesity Management via Wrist-Worn Activity Monitoring COBRA：基于腕戴式多模态传感器的远程慢性肥胖管理深度学习框架 multimodal
7 MEUV: Achieving Fine-Grained Capability Activation in Large Language Models via Mutually Exclusive Unlock Vectors MEUV：通过互斥解锁向量实现大语言模型中细粒度的能力激活 large language model
8 Finetuning AI Foundation Models to Develop Subgrid-Scale Parameterizations: A Case Study on Atmospheric Gravity Waves 微调AI基础模型，为大气重力波开发次网格尺度参数化方案 foundation model
9 ChronoGraph: A Real-World Graph-Based Multivariate Time Series Dataset ChronoGraph：一个基于真实微服务依赖图的多变量时间序列数据集，用于预测和异常检测。 foundation model
10 Characteristic Energy Behavior Profiling of Non-Residential Buildings 提出一种数据驱动的非住宅建筑能耗行为建模方法，用于评估能源系统脆弱性和基准测试。 multimodal
11 One-Embedding-Fits-All: Efficient Zero-Shot Time Series Forecasting by a Model Zoo ZooCast：利用模型动物园，实现高效的零样本时间序列预测 foundation model
12 KubeGuard: LLM-Assisted Kubernetes Hardening via Configuration Files and Runtime Logs Analysis KubeGuard：利用LLM分析配置与日志，增强Kubernetes安全性 large language model
13 Privacy Risks in Time Series Forecasting: User- and Record-Level Membership Inference 针对时间序列预测模型的用户和记录级别成员推理隐私风险研究 large language model
14 TAGAL: Tabular Data Generation using Agentic LLM Methods TAGAL：利用Agentic LLM方法生成高质量表格数据，无需额外训练。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (10 篇)

#题目一句话要点标签🔗⭐
15 Towards a Unified View of Large Language Model Post-Training 统一大语言模型后训练视角，提出混合后训练算法HPT，提升数学推理能力。 reinforcement learning large language model
16 RL's Razor: Why Online Reinforcement Learning Forgets Less 揭示RL的“奥卡姆剃刀”：在线强化学习在微调中能更好保留先验知识 reinforcement learning large language model foundation model
17 Rethinking the long-range dependency in Mamba/SSM and transformer models 从理论角度分析Mamba/SSM和Transformer的长程依赖建模能力 Mamba SSM
18 Meta-Inverse Reinforcement Learning for Mean Field Games via Probabilistic Context Variables 提出基于概率上下文变量的元逆强化学习方法，解决均值场博弈中异构智能体的奖励函数推断问题 reinforcement learning inverse reinforcement learning
19 Wavelet Fourier Diffuser: Frequency-Aware Diffusion Model for Reinforcement Learning 提出Wavelet Fourier Diffuser，解决离线强化学习中轨迹频率偏移问题。 reinforcement learning offline reinforcement learning
20 Data-Augmented Quantization-Aware Knowledge Distillation 提出数据增强感知的量化知识蒸馏方法，提升低比特模型精度 distillation
21 Connections between reinforcement learning with feedback,test-time scaling, and diffusion guidance: An anthology 揭示强化学习、测试时缩放与扩散引导的内在联系，提出重采样对齐方法。 reinforcement learning
22 Resource-Aware Neural Network Pruning Using Graph-based Reinforcement Learning 提出基于图强化学习的资源感知型神经网络剪枝方法，提升剪枝效率。 reinforcement learning
23 What Fundamental Structure in Reward Functions Enables Efficient Sparse-Reward Learning? 提出PAMC以解决稀疏奖励学习中的效率问题 reinforcement learning offline RL dreamer
24 Parking Availability Prediction via Fusing Multi-Source Data with A Self-Supervised Learning Enhanced Spatio-Temporal Inverted Transformer 提出SST-iTransformer，融合多源数据和自监督学习，用于精准预测停车位可用性。 representation learning MAE

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
25 Unobtrusive In-Situ Measurement of Behavior Change by Deep Metric Similarity Learning of Motion Patterns 提出基于深度度量相似性学习的非侵入式行为变化测量方法，用于XR环境中用户行为分析。 manipulation affordance
26 DRtool: An Interactive Tool for Analyzing High-Dimensional Clusterings 提出DRtool以解决高维聚类分析中的可视化与诊断问题 manipulation

⬅️ 返回 cs.LG 首页 · 🏠 返回主页