cs.LG（2025-06-25）

📊 共 27 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) (13 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (12 🔗1) 支柱一：机器人控制 (Robot Control) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (13 篇)

#题目一句话要点标签🔗⭐
1 A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools 综述基础模型在材料科学中的应用与挑战 large language model foundation model multimodal
2 A foundation model with multi-variate parallel attention to generate neuronal activity 提出多变量并行注意力机制以解决iEEG信号预测问题 foundation model ✅
3 Q-resafe: Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models 提出Q-resafe框架以解决量化大语言模型的安全风险问题 large language model ✅
4 Zero-Shot Attribution for Large Language Models: A Distribution Testing Approach 提出零-shot归属工具Anubis以解决代码归属问题 large language model
5 MIRAGE: A Benchmark for Multimodal Information-Seeking and Reasoning in Agricultural Expert-Guided Conversations 提出MIRAGE基准以解决农业领域多模态信息检索与推理问题 multimodal
6 Omniwise: Predicting GPU Kernels Performance with LLMs 提出Omniwise以解决GPU内核性能预测问题 large language model
7 Leaner Training, Lower Leakage: Revisiting Memorization in LLM Fine-Tuning with LoRA 提出LoRA微调方法以降低大语言模型的记忆泄露风险 large language model
8 Characterization and Mitigation of Training Instabilities in Microscaling Formats 提出微缩格式训练不稳定性缓解方法以提升模型性能 large language model ✅
9 Test-time Scaling Techniques in Theoretical Physics -- A Comparison of Methods on the TPBench Dataset 提出符号弱验证框架以提升物理问题的测试时间扩展效果 large language model
10 Automatic Demonstration Selection for LLM-based Tabular Data Classification 提出自动演示选择算法以优化表格数据分类 large language model
11 TESSERA: Temporal Embeddings of Surface Spectra for Earth Representation and Analysis 提出TESSERA以解决卫星地球观测时间序列信息损失问题 foundation model
12 DipSVD: Dual-importance Protected SVD for Efficient LLM Compression 提出DipSVD以解决大语言模型压缩性能不足问题 large language model
13 Echo State Transformer: Attention Over Finite Memories 提出回声状态变换器以解决Transformer计算复杂度问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (12 篇)

#题目一句话要点标签🔗⭐
14 scMamba: A Scalable Foundation Model for Single-Cell Multi-Omics Integration Beyond Highly Variable Feature Selection 提出scMamba以解决单细胞多组学整合中的特征选择问题 Mamba contrastive learning foundation model
15 Multimodal Representation Learning and Fusion 提出多模态表示学习与融合方法以解决信息理解问题 representation learning multimodal
16 PlaceFM: A Training-free Geospatial Foundation Model of Places using Large-Scale Point of Interest Data 提出PlaceFM以解决城市地理空间表示学习的灵活性不足问题 representation learning foundation model ✅
17 Multi-Objective Reinforcement Learning for Cognitive Radar Resource Management 提出多目标强化学习以优化认知雷达资源管理 reinforcement learning deep reinforcement learning SAC
18 Asymmetric REINFORCE for off-Policy Reinforcement Learning: Balancing positive and negative rewards 提出不对称REINFORCE算法以平衡正负奖励 reinforcement learning large language model
19 POLAR: A Pessimistic Model-based Policy Learning Algorithm for Dynamic Treatment Regimes 提出POLAR以解决动态治疗方案优化中的不确定性问题 reinforcement learning policy learning offline reinforcement learning
20 Tackling Data Heterogeneity in Federated Learning through Knowledge Distillation with Inequitable Aggregation 提出知识蒸馏与不平等聚合以解决联邦学习中的数据异质性问题 teacher-student distillation
21 Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration 提出双重探索的模仿学习算法以实现超越专家的表现 reinforcement learning imitation learning
22 Reinforcement Learning Increases Wind Farm Power Production by Enabling Closed-Loop Collaborative Control 提出强化学习控制以提升风电场发电效率 reinforcement learning
23 Permutation Equivariant Neural Controlled Differential Equations for Dynamic Graph Representation Learning 提出置换等变神经控制微分方程以提升动态图表示学习 representation learning
24 Learning-Based Resource Management in Integrated Sensing and Communication Systems 提出约束深度强化学习以优化雷达通信系统的资源管理 reinforcement learning deep reinforcement learning
25 Autonomous Cyber Resilience via a Co-Evolutionary Arms Race within a Fortified Digital Twin Sandbox 提出对抗性韧性共演框架以解决工业控制系统安全问题 reinforcement learning deep reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
26 Empowering Digital Agriculture: A Privacy-Preserving Framework for Data Sharing and Collaborative Research 提出隐私保护框架以促进数字农业中的数据共享与合作研究 manipulation
27 Hear No Evil: Detecting Gradient Leakage by Malicious Servers in Federated Learning 提出客户端检测机制以应对联邦学习中的恶意梯度泄露问题 manipulation

⬅️ 返回 cs.LG 首页 · 🏠 返回主页