cs.LG（2024-10-03）

📊 共 12 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (7) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (7 篇)

#题目一句话要点标签🔗⭐
1 ColaCare: Enhancing Electronic Health Record Modeling through Large Language Model-Driven Multi-Agent Collaboration ColaCare：基于大语言模型驱动的多智能体协作增强电子病历建模 large language model
2 Rethinking VLMs and LLMs for Image Classification 提出轻量级LLM路由，提升视觉任务在VLM中的分类精度与效率 large language model
3 MMP: Towards Robust Multi-Modal Learning with Masked Modality Projection 提出掩码模态投影MMP，增强多模态学习在模态缺失场景下的鲁棒性 multimodal
4 DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation DaWin：免训练的动态权重插值方法，提升模型在分布偏移下的鲁棒性 foundation model
5 AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML AutoML-Agent：一个用于全流程AutoML的多智能体LLM框架 large language model
6 LLMCO2: Advancing Accurate Carbon Footprint Prediction for LLM Inferences 提出LLMCO2以解决LLM推理碳足迹预测问题 large language model
7 Dynamic Gradient Alignment for Online Data Mixing 提出动态梯度对齐(DGA)算法，优化LLM预训练数据混合，提升特定任务性能。 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🔗⭐
8 CPFD: Confidence-aware Privileged Feature Distillation for Short Video Classification 提出置信度感知的特权特征蒸馏方法CPFD，提升短视频分类精度。 distillation multimodal
9 Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting TSFlow：结合高斯过程先验的Flow Matching模型，用于概率时间序列预测。 flow matching
10 C-MORL: Multi-Objective Reinforcement Learning through Efficient Discovery of Pareto Front 提出C-MORL算法，高效发现多目标强化学习中的帕累托前沿 reinforcement learning

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

#题目一句话要点标签🔗⭐
11 DecTrain: Deciding When to Train a Monocular Depth DNN Online DecTrain：一种自适应单目深度估计DNN在线训练决策算法 monocular depth

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
12 Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models 提出自适应投影引导（APG），解决扩散模型中高引导尺度下的过饱和与伪影问题 classifier-free guidance

⬅️ 返回 cs.LG 首页 · 🏠 返回主页