cs.LG（2025-04-12）

📊 共 15 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (9 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (4 🔗1) 支柱一：机器人控制 (Robot Control) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (9 篇)

#题目一句话要点标签🔗⭐
1 NetTAG: A Multimodal RTL-and-Layout-Aligned Netlist Foundation Model via Text-Attributed Graph NetTAG：提出一种多模态RTL和Layout对齐的网表基础模型，通过文本属性图融合门电路语义和图结构。 representation learning large language model foundation model
2 Efficient Implementation of Reinforcement Learning over Homomorphic Encryption 提出基于同态加密的强化学习高效实现，用于云端隐私保护的控制策略合成。 reinforcement learning OMOMO
3 Synthetic Aircraft Trajectory Generation Using Time-Based VQ-VAE 提出基于时频VQ-VAE的合成飞机轨迹生成方法，解决空管数据稀缺问题。 representation learning VQ-VAE spatiotemporal
4 Laser Scan Path Design for Controlled Microstructure in Additive Manufacturing with Integrated Reduced-Order Phase-Field Modeling and Deep Reinforcement Learning 提出一种基于相场模型和深度强化学习的激光扫描路径优化方法，用于控制增材制造中的微观结构。 reinforcement learning deep reinforcement learning DRL
5 Repetitive Contrastive Learning Enhances Mamba's Selectivity in Time Series Prediction 提出重复对比学习(RCL)以增强Mamba在时间序列预测中的选择性 Mamba contrastive learning
6 A Champion-level Vision-based Reinforcement Learning Agent for Competitive Racing in Gran Turismo 7 提出基于视觉的强化学习赛车智能体，在GT7中达到冠军级水平 reinforcement learning deep reinforcement learning
7 Towards More Efficient, Robust, Instance-adaptive, and Generalizable Sequential Decision making 针对不确定性环境，提出更高效、鲁棒、自适应和泛化的序贯决策方法 reinforcement learning large language model
8 Towards Optimal Differentially Private Regret Bounds in Linear MDPs 提出基于LSVI-UCB++的差分隐私线性MDP后悔界优化算法 reinforcement learning offline RL
9 InterQ: A DQN Framework for Optimal Intermittent Control 提出InterQ，通过DQN框架实现离散时间随机线性系统的最优间歇控制 reinforcement learning deep reinforcement learning ✅

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#题目一句话要点标签🔗⭐
10 Multimodal 3D Genome Pre-training 提出MIX-HIC，首个融合3D基因组结构和表观基因组信息的3D基因组多模态预训练模型。 foundation model multimodal
11 Exploring Modality Disruption in Multimodal Fake News Detection 提出FND-MoE框架，解决多模态假新闻检测中模态干扰问题。 multimodal
12 Type-Constrained Code Generation with Language Models 提出类型约束解码方法，提升语言模型代码生成的正确性和可编译性 large language model
13 Detecting Instruction Fine-tuning Attacks on Language Models using Influence Function 利用影响函数检测语言模型指令微调攻击 large language model ✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
14 Deconfounded Reasoning for Multimodal Fake News Detection via Causal Intervention 提出CIMDD框架，通过因果干预解决多模态假新闻检测中的混淆因素问题 manipulation multimodal

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

#题目一句话要点标签🔗⭐
15 Mixture of Group Experts for Learning Invariant Representations 提出混合组专家模型(MoGE)，通过组稀疏正则化提升MoE模型的专家多样性和性能。 MoGe

⬅️ 返回 cs.LG 首页 · 🏠 返回主页