cs.LG（2025-03-27）

📊 共 16 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (8 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱八：物理动画 (Physics-based Animation) (3) 支柱一：机器人控制 (Robot Control) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (8 篇)

#题目一句话要点标签🔗⭐
1 Malicious and Unintentional Disclosure Risks in Large Language Models for Code Generation 评估代码生成大模型中恶意和无意泄露敏感信息的风险 large language model
2 Resource-Efficient Federated Fine-Tuning Large Language Models for Heterogeneous Data 提出HierFedLoRA框架，解决联邦学习微调大模型时的数据异构与资源约束问题。 large language model
3 LeForecast: Enterprise Hybrid Forecast by Time Series Intelligence LeForecast：面向企业级混合预测的时间序列智能平台 foundation model multimodal
4 RocketPPA: Code-Level Power, Performance, and Area Prediction via LLM and Mixture of Experts 提出RocketPPA以解决硬件设计中的PPA估计问题 large language model
5 Scalable Expectation Estimation with Subtractive Mixture Models 提出基于差分表示的无偏重要性采样估计器，加速高维空间中减性混合模型的期望估计。 multimodal
6 Tricking Retrievers with Influential Tokens: An Efficient Black-Box Corpus Poisoning Attack 提出DIGA：一种高效的黑盒语料库投毒攻击方法，用于欺骗检索增强生成系统。 large language model
7 Embedding Domain-Specific Knowledge from LLMs into the Feature Engineering Pipeline 利用LLM领域知识增强特征工程流水线，加速进化计算收敛 large language model
8 Ignite Forecasting with SPARK: An Efficient Generative Framework for Refining LLMs in Temporal Knowledge Graph Forecasting SPARK：一种高效的生成式框架，用于在时序知识图谱预测中优化LLM large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
9 Reward Design for Reinforcement Learning Agents 针对强化学习智能体，提出教师驱动和智能体驱动的自适应奖励函数设计方法。 reinforcement learning reward design reward shaping
10 Generalizable Implicit Neural Representations via Parameterized Latent Dynamics for Baroclinic Ocean Forecasting 提出PINROD，通过参数化潜变量动力学实现可泛化的隐式神经Baroclinic海洋预测 latent dynamics spatiotemporal
11 A tale of two goals: leveraging sequentiality in multi-goal scenarios 提出双目标MDP，利用序列信息提升多目标强化学习的稳定性和效率 reinforcement learning TD3

🔬 支柱八：物理动画 (Physics-based Animation) (3 篇)

#题目一句话要点标签🔗⭐
12 DeepRV: Accelerating spatiotemporal inference with pre-trained neural priors DeepRV：利用预训练神经先验加速时空推理 spatiotemporal
13 Advancing Spatiotemporal Prediction using Artificial Intelligence: Extending the Framework of Geographically and Temporally Weighted Neural Network (GTWNN) for Differing Geographical and Temporal Contexts 扩展GTWNN框架：针对不同时空背景改进犯罪预测模型 spatiotemporal
14 Interpretable Cross-Sphere Multiscale Deep Learning Predicts ENSO Skilfully Beyond 2 Years PTSTnet：可解释跨尺度深度学习模型，ENSO预测能力突破2年 spatiotemporal

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
15 SandboxEval: Towards Securing Test Environment for Untrusted Code SandboxEval：为不可信代码测试环境提供安全保障 manipulation large language model

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

#题目一句话要点标签🔗⭐
16 F-INR: Functional Tensor Decomposition for Implicit Neural Representations 提出F-INR，通过函数张量分解加速高维隐式神经表示训练并提升性能。 neural radiance field

⬅️ 返回 cs.LG 首页 · 🏠 返回主页