cs.LG（2025-01-06）

📊 共 14 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) (7) 支柱九：具身大模型 (Embodied Foundation Models) (5 🔗2) 支柱一：机器人控制 (Robot Control) (2)

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Knowledge Distillation with Adapted Weight	提出基于自适应权重知识蒸馏(KD-AIF)框架，提升模型鲁棒性与可解释性。	teacher-student distillation
2	Seeing the Whole in the Parts in Self-Supervised Representation Learning	CO-SSL通过对齐局部与全局表征，提升自监督学习的性能和鲁棒性	representation learning
3	SALT: Sales Autocompletion Linked Business Tables Dataset	SALT：销售自动补全关联业务表数据集，促进企业级表格数据研究	representation learning foundation model
4	LOHA: Direct Graph Spectral Contrastive Learning Between Low-pass and High-pass Views	LOHA：提出低通-高通视图间图谱对比学习框架，提升图神经网络性能。	contrastive learning
5	Randomly Sampled Language Reasoning Problems Elucidate Limitations of In-Context Learning	通过随机语言推理问题揭示了上下文学习的局限性	world model chain-of-thought
6	GraphDART: Graph Distillation for Efficient Advanced Persistent Threat Detection	提出GraphDART以解决复杂图谱下APT检测效率问题	distillation
7	Learn A Flexible Exploration Model for Parameterized Action Markov Decision Processes	FLEXplore：学习灵活探索模型，提升参数化动作MDP中的强化学习效率	reinforcement learning model-based RL

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
8	Multimodal Machine Learning Can Predict Videoconference Fluidity and Enjoyment	利用多模态机器学习预测视频会议的流畅度和愉悦感	multimodal
9	ChronoSense: Exploring Temporal Understanding in Large Language Models with Time Intervals of Events	ChronoSense：构建时序理解基准，评估大语言模型对事件时间间隔的理解能力	large language model	✅
10	A Soft Sensor Method with Uncertainty-Awareness and Self-Explanation Based on Large Language Models Enhanced by Domain Knowledge Retrieval	提出基于大语言模型的软传感器以解决传统方法的局限性	large language model
11	Multi-Modal One-Shot Federated Ensemble Learning for Medical Data with Vision Large Language Model	FedMME：利用视觉大语言模型的多模态单次联邦集成学习框架，提升医疗数据诊断精度。	large language model
12	From Tables to Time: How TabPFN-v2 Outperforms Specialized Time Series Forecasting Models	TabPFN-v2在时间序列预测中超越专用模型：结合特征工程实现高效预测	foundation model	✅

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
13	The Power of Negative Zero: Datatype Customization for Quantized Large Language Models	RaZeR：通过重映射负零优化量化大语言模型的数据类型定制	manipulation large language model
14	Horizon Generalization in Reinforcement Learning	提出基于规划不变性的强化学习方法，提升目标条件RL的horizon泛化能力	domain randomization reinforcement learning

⬅️ 返回 cs.LG 首页 · 🏠 返回主页