cs.LG（2025-08-13）

📊 共 33 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) (19 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (13 🔗1) 支柱八：物理动画 (Physics-based Animation) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (19 篇)

#题目一句话要点标签🔗⭐
1 FM4NPP: A Scaling Foundation Model for Nuclear and Particle Physics 提出FM4NPP以解决粒子物理实验数据稀疏问题 large language model foundation model
2 EGGS-PTP: An Expander-Graph Guided Structured Post-training Pruning Method for Large Language Models 提出EGGS-PTP以解决大语言模型的计算与内存挑战 large language model foundation model
3 Data-Driven Discovery of Interpretable Kalman Filter Variants through Large Language Models and Genetic Programming 通过大语言模型和遗传编程提出可解释的卡尔曼滤波器变体 large language model
4 SYNAPSE-G: Bridging Large Language Models and Graph Learning for Rare Event Classification 提出SYNAPSE-G以解决稀有事件分类中的数据稀缺问题 large language model
5 Less is More: Learning Graph Tasks with Just LLMs 提出利用大型语言模型解决图任务的新方法 large language model chain-of-thought
6 TimeMKG: Knowledge-Infused Causal Reasoning for Multivariate Time Series Modeling 提出TimeMKG以解决多变量时间序列建模中的知识缺失问题 large language model multimodal
7 DeepFeatIoT: Unifying Deep Learned, Randomized, and LLM Features for Enhanced IoT Time Series Sensor Data Classification in Smart Industries 提出DeepFeatIoT以解决IoT传感器数据分类问题 large language model TAMP
8 Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models 提出噪声超网络以解决扩散模型推理效率问题 large language model ✅
9 Benchmark-Driven Selection of AI: Evidence from DeepSeek-R1 提出基准驱动的AI选择方法以提升推理模型性能 large language model
10 Pre-trained Transformer-models using chronic invasive electrophysiology for symptom decoding without patient-individual training 提出基于预训练Transformer模型的症状解码方法以解决个体化训练问题 foundation model
11 Constrained Decoding of Diffusion LLMs with Context-Free Grammars 提出扩散模型的约束解码方法以解决语法约束问题 large language model
12 Dynamic Mixture-of-Experts for Incremental Graph Learning 提出动态专家混合模型以解决增量图学习问题 TAMP
13 Beyond Naïve Prompting: Strategies for Improved Zero-shot Context-aided Forecasting with LLMs 提出四种策略以提升LLMs在零-shot情境下的预测能力 large language model
14 Next Edit Prediction: Learning to Predict Code Edits from Context and Interaction History 提出下一编辑预测以解决代码编辑体验不足问题 large language model ✅
15 Modern Neural Networks for Small Tabular Datasets: The New Default for Field-Scale Digital Soil Mapping? 提出现代神经网络以解决小型表格数据集的土壤属性预测问题 foundation model
16 HierMoE: Accelerating MoE Training with Hierarchical Token Deduplication and Expert Swap 提出HierMoE以解决MoE模型训练中的通信与负载不均问题 large language model
17 Decentralized Rank Scheduling for Energy-Constrained Multi-Task Federated Fine-Tuning in Edge-Assisted IoV Networks 提出去中心化排名调度解决边缘IoV网络中的多任务联邦微调问题 foundation model
18 Enhancing Memory Recall in LLMs with Gauss-Tin: A Hybrid Instructional and Gaussian Replay Approach 提出Gauss-Tin以解决大语言模型的灾难性遗忘问题 large language model
19 NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs 提出NeuronTune以解决大型语言模型的安全与效用平衡问题 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🔗⭐
20 From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation 提出CAD-RL以解决CAD代码生成中的逻辑推理与精度问题 reinforcement learning policy learning large language model
21 Nested-ReFT: Efficient Reinforcement Learning for Large Language Model Fine-Tuning via Off-Policy Rollouts 提出Nested-ReFT以解决大语言模型微调的高计算成本问题 reinforcement learning large language model
22 Beyond Scaling Law: A Data-Efficient Distillation Framework for Reasoning 提出数据高效蒸馏框架以优化推理能力 reinforcement learning policy learning distillation
23 EEGDM: EEG Representation Learning via Generative Diffusion Model 提出EEGDM以解决EEG信号表示学习挑战 representation learning large language model foundation model ✅
24 Edge General Intelligence Through World Models and Agentic AI: Fundamentals, Solutions, and Challenges 提出世界模型以增强边缘通用智能的自主决策能力 world model representation learning foundation model
25 Quantum-Inspired DRL Approach with LSTM and OU Noise for Cut Order Planning Optimization 提出量子启发的深度强化学习方法以优化切割顺序规划 reinforcement learning deep reinforcement learning DRL
26 GeoMAE: Masking Representation Learning for Spatio-Temporal Graph Forecasting with Missing Values 提出GeoMAE以解决城市智能系统中的缺失数据问题 predictive model representation learning
27 Apriel-Nemotron-15B-Thinker 提出Apriel-Nemotron-15B-Thinker以降低大语言模型的内存消耗 reinforcement learning large language model
28 Reasoning Steps as Curriculum: Using Depth of Thought as a Difficulty Signal for Tuning LLMs 提出深度思维作为难度信号以优化大语言模型训练 curriculum learning chain-of-thought
29 Goal Discovery with Causal Capacity for Efficient Reinforcement Learning 提出因果能力目标发现框架以提升强化学习效率 reinforcement learning
30 Large-Small Model Collaborative Framework for Federated Continual Learning 提出大小模型协作框架以解决联邦持续学习问题 distillation foundation model
31 HKT: A Biologically Inspired Framework for Modular Hereditary Knowledge Transfer in Neural Networks 提出HKT框架以优化小型神经网络的知识传递 distillation optical flow
32 A Unified Contrastive-Generative Framework for Time Series Classification 提出CoGenT框架以解决多变量时间序列分类中的对比与生成学习问题 MAE contrastive learning

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

#题目一句话要点标签🔗⭐
33 CoBAD: Modeling Collective Behaviors for Human Mobility Anomaly Detection 提出CoBAD以解决人类移动异常检测中的集体行为建模问题 spatiotemporal ✅

⬅️ 返回 cs.LG 首页 · 🏠 返回主页