cs.LG（2025-06-18）

📊 共 23 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) (10 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (8 🔗2) 支柱八：物理动画 (Physics-based Animation) (2) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱六：视频提取与匹配 (Video Extraction) (1)

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

#题目一句话要点标签🔗⭐
1 PathCoT: Chain-of-Thought Prompting for Zero-shot Pathology Visual Reasoning 提出PathCoT以解决病理视觉推理中的知识缺乏问题 large language model multimodal chain-of-thought
2 HEAL: An Empirical Study on Hallucinations in Embodied Agents Driven by Large Language Models 提出系统性研究以解决大语言模型驱动的具身智能体的幻觉问题 large language model
3 KG-FGNN: Knowledge-guided GNN Foundation Model for Fertilisation-oriented Soil GHG Flux Prediction 提出KG-FGNN以解决农业土壤温室气体排放预测问题 foundation model
4 Descriptor-based Foundation Models for Molecular Property Prediction 提出CheMeleon模型以提高分子性质预测的准确性 foundation model
5 Singular Value Decomposition on Kronecker Adaptation for Large Language Model 提出SoKA以解决大语言模型的参数高效微调问题 large language model
6 VectorEdits: A Dataset and Benchmark for Instruction-Based Editing of Vector Graphics 提出VectorEdits数据集以解决基于指令的矢量图形编辑问题 large language model
7 Fractional Reasoning via Latent Steering Vectors Improves Inference Time Compute 提出分数推理以提升推理时间计算效率 large language model
8 deepSURF: Detecting Memory Safety Vulnerabilities in Rust Through Fuzzing LLM-Augmented Harnesses 提出deepSURF以解决Rust中内存安全漏洞检测问题 large language model
9 Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework 提出PRISM框架以解决神经网络特征多义性问题 large language model
10 Unlocking Post-hoc Dataset Inference with Synthetic Data 提出合成数据生成方法以解决数据集推断问题 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (8 篇)

#题目一句话要点标签🔗⭐
11 AutoRule: Reasoning Chain-of-thought Extracted Rule-based Rewards Improve Preference Learning 提出AutoRule以自动化提取规则改善偏好学习 reinforcement learning preference learning RLHF ✅
12 Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning 提出稳定梯度方法以解决深度强化学习的规模化挑战 reinforcement learning deep reinforcement learning
13 Reward Models in Deep Reinforcement Learning: A Survey 综述深度强化学习中的奖励模型以优化策略 reinforcement learning deep reinforcement learning
14 Minimizing Structural Vibrations via Guided Flow Matching Design Optimization 提出基于引导流匹配的设计优化以减少结构振动 flow matching ✅
15 Heterogeneous Federated Reinforcement Learning Using Wasserstein Barycenters 提出基于Wasserstein重心的异构联邦强化学习算法 reinforcement learning
16 CAWR: Corruption-Averse Advantage-Weighted Regression for Robust Policy Optimization 提出CAWR以解决离线强化学习中的数据腐蚀问题 reinforcement learning offline RL offline reinforcement learning
17 Zero-Shot Reinforcement Learning Under Partial Observability 提出基于记忆的零-shot强化学习以解决部分可观测性问题 reinforcement learning
18 When and How Unlabeled Data Provably Improve In-Context Learning 提出利用未标记数据提升上下文学习能力的方法 linear attention foundation model

🔬 支柱八：物理动画 (Physics-based Animation) (2 篇)

#题目一句话要点标签🔗⭐
19 IDRIFTNET: Physics-Driven Spatiotemporal Deep Learning for Iceberg Drift Forecasting 提出IDRIFTNET以解决冰山漂移预测问题 spatiotemporal
20 Over-squashing in Spatiotemporal Graph Neural Networks 提出时空图神经网络中的过度压缩问题解决方案 spatiotemporal

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

#题目一句话要点标签🔗⭐
21 Creating User-steerable Projections with Interactive Semantic Mapping 提出用户可引导的投影框架以解决语义结构探索问题 semantic mapping semantic map large language model

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
22 Biaxialformer: Leveraging Channel Independence and Inter-Channel Correlations in EEG Signal Decoding for Predicting Neurological Outcomes 提出Biaxialformer以解决EEG信号解码中的通道相关性问题 spatial relationship

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
23 T-SHRED: Symbolic Regression for Regularization and Model Discovery with Transformer Shallow Recurrent Decoders 提出T-SHRED以解决稀疏传感器数据建模问题 sparse sensors

⬅️ 返回 cs.LG 首页 · 🏠 返回主页