cs.LG（2024-01-24）

📊 共 11 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

#	题目	一句话要点	标签
1	SpacTor-T5: Pre-training T5 Models with Span Corruption and Replaced Token Detection	提出SpacTor-T5以提高大语言模型预训练效率	large language model
2	VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks	提出VisualWebArena以评估多模态代理在视觉网络任务中的表现	multimodal
3	What Large Language Models Know and What People Think They Know	提出改进LLM解释以缩小用户信心与模型信心差距	large language model
4	Supporting Sensemaking of Large Language Model Outputs at Scale	提出多响应展示方法以支持大语言模型输出的理解	large language model
5	Speech foundation models on intelligibility prediction for hearing-impaired listeners	提出轻量化预测模型以提升听障人士的语音可懂度	foundation model
6	Masked Particle Modeling on Sets: Towards Self-Supervised High Energy Physics Foundation Models	提出Masked Particle Modeling以解决高能物理数据表示学习问题	foundation model
7	Finetuning Foundation Models for Joint Analysis Optimization	提出联合分析优化的基础模型微调方法以提升高能物理性能	foundation model
8	Prompt Design and Engineering: Introduction and Advanced Methods	提出提示设计与工程方法以优化大型语言模型的应用	large language model chain-of-thought

#	题目	一句话要点	标签	🔗
9	EMP: Effective Multidimensional Persistence for Graph Representation Learning	提出有效的多维持久性框架以解决图表示学习中的数据分析问题	representation learning
10	The Definitive Guide to Policy Gradients in Deep Reinforcement Learning: Theory, Algorithms and Implementations	全面概述深度强化学习中的策略梯度算法	reinforcement learning deep reinforcement learning	✅
11	Symbolic Equation Solving via Reinforcement Learning	提出基于强化学习的符号方程求解方法	reinforcement learning