cs.LG（2024-12-11）

📊 共 16 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) (9 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#题目一句话要点标签🔗⭐
1 From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons 提出通用具身智能体GEA，利用多模态LLM解决跨领域具身智能任务 embodied AI generalist agent large language model
2 GAMED: Knowledge Adaptive Multi-Experts Decoupling for Multimodal Fake News Detection 提出GAMED，通过知识自适应多专家解耦进行多模态假新闻检测。 multimodal ✅
3 Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning 提出少数群体感知评估框架，揭示LLM卸载中被低估的隐私风险 large language model
4 Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting 针对LLM时间序列预测的对抗攻击框架，揭示模型脆弱性 large language model ✅
5 Towards LLM-based optimization compilers. Can LLMs learn how to apply a single peephole optimization? Reasoning is all LLMs need! 研究表明，具备增强推理能力的大语言模型更擅长汇编代码的窥孔优化任务 large language model chain-of-thought
6 HARP: A challenging human-annotated math reasoning benchmark 提出HARP：一个更具挑战性的人工标注数学推理基准 large language model ✅
7 Generative Semantic Communication: Architectures, Technologies, and Applications 提出基于LLM的生成式语义通信系统，实现信息再生并大幅降低通信开销。 large language model
8 TurboAttention: Efficient Attention Approximation For High Throughputs LLMs 提出TurboAttention以提高大语言模型的推理效率 large language model
9 Federated In-Context LLM Agent Learning 提出FICAL：一种保护隐私的联邦上下文LLM Agent学习方法 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
10 Bootstrapping Heterogeneous Graph Representation Learning via Large Language Models: A Generalized Approach 提出一种基于LLM的异构图表示学习通用方法，无需预处理和类型信息。 representation learning large language model
11 Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning 提出基于隐空间安全约束策略的离线强化学习方法，提升安全性和奖励。 reinforcement learning offline reinforcement learning
12 Numerical Analysis of HiPPO-LegS ODE for Deep State Space Models 针对深度状态空间模型，论文分析了HiPPO-LegS ODE的数值性质。 state space model
13 REPEAT: Improving Uncertainty Estimation in Representation Learning Explainability 提出REPEAT以解决表示学习可解释性中的不确定性估计问题 representation learning
14 SINERGYM -- A virtual testbed for building energy optimization with Reinforcement Learning Sinergym：用于建筑能源优化强化学习的开源虚拟测试平台 reinforcement learning
15 IRL for Restless Multi-Armed Bandits with Applications in Maternal and Child Health 提出WHIRL算法，利用逆强化学习解决母婴健康领域受限资源分配问题。 reinforcement learning inverse reinforcement learning ✅

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
16 Learning Physics Informed Neural ODEs With Partial Measurements 提出基于物理信息神经ODE的部分测量动态系统学习框架 spatiotemporal

⬅️ 返回 cs.LG 首页 · 🏠 返回主页