cs.LG（2025-04-20）

📊 共 14 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) (7 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱一：机器人控制 (Robot Control) (2) 支柱八：物理动画 (Physics-based Animation) (1)

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

#题目一句话要点标签🔗⭐
1 Diffusion-based supervised learning of generative models for efficient sampling of multimodal distributions 提出基于扩散模型的监督学习方法，高效采样多峰分布，解决贝叶斯推断难题。 multimodal
2 Efficient Split Federated Learning for Large Language Models over Communication Networks 提出SflLLM框架，通过拆分联邦学习和LoRA高效微调边缘端大语言模型 large language model
3 NoWag: A Unified Framework for Shape Preserving Compression of Large Language Models NoWag：一种统一的LLM压缩框架，保持模型结构并实现高效压缩 large language model ✅
4 Deep Learning with Pretrained 'Internal World' Layers: A Gemma 3-Based Modular Architecture for Wildfire Prediction 提出基于Gemma 3预训练“内部世界”层的模块化架构，用于野火预测。 multimodal
5 Evaluating Temporal Plasticity in Foundation Time Series Models for Incremental Fine-tuning 评估时间序列基础模型的时间可塑性，用于增量微调 foundation model
6 SlimPipe: Memory-Thrifty and Efficient Pipeline Parallelism for Long-Context LLM Training SlimPipe：面向长文本LLM训练的内存高效流水线并行方法 large language model
7 Less is More: Adaptive Coverage for Synthetic Training Data 提出基于最大覆盖的自适应采样算法，提升合成数据训练分类器性能 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
8 M-TabNet: A Multi-Encoder Transformer Model for Predicting Neonatal Birth Weight from Multimodal Data M-TabNet：多编码器Transformer模型，用于多模态数据预测新生儿出生体重 MAE multimodal
9 LoRe: Personalizing LLMs via Low-Rank Reward Modeling 提出LoRe：通过低秩奖励建模个性化大型语言模型 reinforcement learning RLHF large language model
10 Reinforcement Learning from Multi-level and Episodic Human Feedback 提出基于多级和情景式人类反馈的强化学习算法，提升复杂任务学习效率。 reinforcement learning
11 Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data FedSSD：联邦学习中基于选择性自蒸馏的非独立同分布数据学习方法 distillation

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
12 Pairwise or Pointwise? Evaluating Feedback Protocols for Bias in LLM-Based Evaluation 揭示LLM评估中反馈协议的偏见：成对偏好易受干扰，绝对评分更稳健 manipulation reinforcement learning large language model
13 Surrogate Fitness Metrics for Interpretable Reinforcement Learning 提出基于代理适应度指标的强化学习可解释性优化框架 trajectory optimization reinforcement learning

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

#题目一句话要点标签🔗⭐
14 Diffusion-Driven Inertial Generated Data for Smartphone Location Classification 提出基于扩散模型的惯性数据生成方法，用于提升智能手机定位分类性能。 motion tracking

⬅️ 返回 cs.LG 首页 · 🏠 返回主页