cs.LG（2025-06-26）

📊 共 40 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (18 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (16 🔗1) 支柱八：物理动画 (Physics-based Animation) (4) 支柱五：交互与反应 (Interaction & Reaction) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (18 篇)

#题目一句话要点标签🔗⭐
1 SMMILE: An Expert-Driven Benchmark for Multimodal Medical In-Context Learning 提出SMMILE基准以解决多模态医学任务学习问题 large language model multimodal
2 BMFM-DNA: A SNP-aware DNA foundation model to capture variant effects 提出BMFM-DNA以解决DNA变异效应捕捉问题 large language model foundation model ✅
3 Multi-task parallelism for robust pre-training of graph foundation models on multi-source, multi-fidelity atomistic modeling data 提出多任务并行方法以增强图基础模型的鲁棒性 foundation model
4 CaloHadronic: a diffusion model for the generation of hadronic showers 提出CaloHadronic以解决高粒度探测器中粒子淋浴模拟问题 Aloha
5 Multimodal Misinformation Detection Using Early Fusion of Linguistic, Visual, and Social Features 提出多模态特征早期融合方法以检测虚假信息 multimodal
6 Distributed Cross-Channel Hierarchical Aggregation for Foundation Models 提出D-CHAG以解决图像通道聚合计算效率低下问题 foundation model
7 Scalable Bayesian Low-Rank Adaptation of Large Language Models via Stochastic Variational Subspace Inference 提出ScalaBL以解决大语言模型的不确定性量化问题 large language model
8 DynamicBench: Evaluating Real-Time Report Generation in Large Language Models 提出DynamicBench以解决实时信息处理评估问题 large language model
9 Chain-of-Thought Enhanced Shallow Transformers for Wireless Symbol Detection 提出CHOOSE框架以解决无线符号检测中的计算资源限制问题 chain-of-thought
10 Large Language Model Agent for Modular Task Execution in Drug Discovery 提出模块化框架以优化药物发现中的关键任务 large language model
11 DiLoCoX: A Low-Communication Large-Scale Training Framework for Decentralized Cluster 提出DiLoCoX以解决大规模分散集群训练中的低通信问题 large language model foundation model
12 mTSBench: Benchmarking Multivariate Time Series Anomaly Detection and Model Selection at Scale 提出mTSBench以解决多变量时间序列异常检测的基准问题 large language model
13 Early Stopping Tabular In-Context Learning 提出早停机制以提升表格上下文学习的推理效率 foundation model
14 Latent Prototype Routing: Achieving Near-Perfect Load Balancing in Mixture-of-Experts 提出潜在原型路由以解决混合专家模型负载不均问题 large language model
15 Zero-Shot Learning for Obsolescence Risk Forecasting 提出零样本学习方法以解决电子元件过时风险预测问题 large language model
16 Enhancing LLM Tool Use with High-quality Instruction Data from Knowledge Graph 利用知识图谱生成高质量指令数据以提升LLM工具使用能力 large language model
17 EraRAG: Efficient and Incremental Retrieval Augmented Generation for Growing Corpora 提出EraRAG以解决动态语料库更新效率问题 large language model ✅
18 Model State Arithmetic for Machine Unlearning 提出MSA算法以解决机器遗忘中的数据影响问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (16 篇)

#题目一句话要点标签🔗⭐
19 Flow-Based Single-Step Completion for Efficient and Expressive Policy Learning 提出单步完成策略以提高离线强化学习效率 reinforcement learning policy learning offline RL
20 Quantum Reinforcement Learning Trading Agent for Sector Rotation in the Taiwan Stock Market 提出混合量子-经典强化学习框架以解决台湾股市的行业轮换问题 reinforcement learning PPO reward design
21 Explainable AI for Radar Resource Management: Modified LIME in Deep Reinforcement Learning 提出DL-LIME以提升雷达资源管理中的可解释性与性能 reinforcement learning deep reinforcement learning
22 DKGCM: A Spatio-Temporal Prediction Model for Traffic Flow by Fusing Spatial Node Clustering Method and Fourier Bidirectional Mamba Mechanism 提出DKGCM模型以解决交通流预测中的时空关系问题 reinforcement learning Mamba spatiotemporal
23 APO: Enhancing Reasoning Ability of MLLMs via Asymmetric Policy Optimization 提出不对称策略优化以提升多模态大语言模型的推理能力 reinforcement learning large language model multimodal ✅
24 Complexity-aware fine-tuning 提出复杂性感知微调方法以提升大语言模型性能 distillation large language model chain-of-thought
25 TRIDENT: Tri-Modal Molecular Representation Learning with Taxonomic Annotations and Local Correspondence 提出TRIDENT框架以整合多模态信息提升分子属性预测 representation learning multimodal
26 Optimal Single-Policy Sample Complexity and Transient Coverage for Average-Reward Offline RL 提出单策略样本复杂度以解决平均奖励离线强化学习问题 reinforcement learning offline RL offline reinforcement learning
27 M3PO: Massively Multi-Task Model-Based Policy Optimization 提出M3PO以解决单任务样本效率低和多任务泛化差问题 reinforcement learning PPO world model
28 RL-Selector: Reinforcement Learning-Guided Data Selection via Redundancy Assessment 提出RL-Selector以解决数据冗余导致的训练效率低下问题 reinforcement learning
29 Risk-Averse Total-Reward Reinforcement Learning 提出风险规避的总回报强化学习算法以解决MDP问题 reinforcement learning
30 rQdia: Regularizing Q-Value Distributions With Image Augmentation 提出rQdia通过图像增强正则化Q值分布以提升深度强化学习性能 reinforcement learning deep reinforcement learning SAC
31 NaLaFormer: Norm-Aware Linear Attention for Transformer Models 提出Norm-Aware Linear Attention以解决线性注意力的熵缺失问题 linear attention
32 Efficient Skill Discovery via Regret-Aware Optimization 提出基于后悔感知优化的高效技能发现方法 reinforcement learning policy learning representation learning
33 Strict Subgoal Execution: Reliable Long-Horizon Planning in Hierarchical Reinforcement Learning 提出严格子目标执行框架以解决长时间规划问题 reinforcement learning
34 Interpretable Representation Learning for Additive Rule Ensembles 提出可解释的表示学习方法以改进加法规则集 representation learning

🔬 支柱八：物理动画 (Physics-based Animation) (4 篇)

#题目一句话要点标签🔗⭐
35 Storm Surge in Color: RGB-Encoded Physics-Aware Deep Learning for Storm Surge Forecasting 提出RGB编码的深度学习方法以提高风暴潮预测精度 spatiotemporal
36 Modification of a Numerical Method Using FIR Filters in a Time-dependent SIR Model for COVID-19 提出FIR滤波器改进算法以优化COVID-19传播预测 PULSE
37 AGTCNet: A Graph-Temporal Approach for Principled Motor Imagery EEG Classification 提出AGTCNet以解决脑机接口EEG分类中的时空依赖问题 spatiotemporal
38 Forecasting Geopolitical Events with a Sparse Temporal Fusion Transformer and Gaussian Process Hybrid: A Case Study in Middle Eastern and U.S. Conflict Dynamics 提出STFT-VNNGP以解决地缘政治事件预测中的数据稀疏问题 spatiotemporal

🔬 支柱五：交互与反应 (Interaction & Reaction) (2 篇)

#题目一句话要点标签🔗⭐
39 Deception Detection in Dyadic Exchanges Using Multimodal Machine Learning: A Study on a Swedish Cohort 提出多模态机器学习以提高双人交互中的欺骗检测准确性 dyadic interaction multimodal
40 Why Neural Network Can Discover Symbolic Structures with Gradient-based Training: An Algebraic and Geometric Foundation for Neurosymbolic Reasoning 提出神经网络训练动态下符号结构的发现机制 OMOMO

⬅️ 返回 cs.LG 首页 · 🏠 返回主页