cs.LG（2023-11-28）

📊 共 14 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

#	题目	一句话要点	标签	🔗
1	Training Chain-of-Thought via Latent-Variable Inference	提出通过潜变量推断训练链式思维以提升LLM性能	large language model chain-of-thought
2	Debiasing Multimodal Models via Causal Information Minimization	通过因果信息最小化提出多模态模型去偏见方法	multimodal	✅
3	Large Language Models Suffer From Their Own Output: An Analysis of the Self-Consuming Training Loop	分析自消耗训练循环对大型语言模型的影响	large language model
4	MultiModal-Learning for Predicting Molecular Properties: A Framework Based on Image and Graph Structures	提出MolIG框架以解决药物分子属性预测问题	multimodal
5	Personalized Predictions of Glioblastoma Infiltration: Mathematical Models, Physics-Informed Neural Networks and Multimodal Scans	提出基于物理信息神经网络的个性化胶质母细胞瘤浸润预测方法	multimodal
6	SoUnD Framework: Analyzing (So)cial Representation in (Un)structured (D)ata	提出SoUnD框架以分析非结构化数据中的社会表征	foundation model
7	ClimateX: Do LLMs Accurately Assess Human Expert Confidence in Climate Statements?	提出ClimateX数据集以评估LLMs对气候声明的专家信心判断	large language model
8	Fast and Efficient 2-bit LLM Inference on GPU: 2/4/16-bit in a Weight Matrix with Asynchronous Dequantization	提出混合精度量化与异步解量化以提升LLM推理效率	large language model

#	题目	一句话要点	标签
9	Digital Twin-Enhanced Deep Reinforcement Learning for Resource Management in Networks Slicing	提出数字双胞胎增强深度强化学习以解决网络切片资源管理问题	reinforcement learning deep reinforcement learning DRL
10	An Investigation of Time Reversal Symmetry in Reinforcement Learning	提出时间反转对称性以降低强化学习样本复杂度	reinforcement learning
11	Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective	提出基于核方法的触发模式生成以增强数据蒸馏的后门攻击能力	distillation
12	FedAL: Black-Box Federated Knowledge Distillation Enabled by Adversarial Learning	提出FedAL以解决客户端数据异构性问题	distillation
13	Goal-conditioned Offline Planning from Curious Exploration	提出基于好奇探索的目标条件离线规划方法	reinforcement learning deep reinforcement learning
14	XAI for time-series classification leveraging image highlight methods	提出基于图像高亮方法的时间序列分类可解释性模型	teacher-student distillation