cs.CL（2023-10-18）

📊 共 22 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (18 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱六：视频提取与匹配 (Video Extraction) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (18 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Concept-Guided Chain-of-Thought Prompting for Pairwise Comparison Scoring of Texts with Large Language Models	提出概念引导的链式思维提示以解决文本对比评分问题	large language model chain-of-thought
2	Non-Intrusive Adaptation: Input-Centric Parameter-efficient Fine-Tuning for Versatile Multimodal Modeling	提出AdaLink以解决大规模模型适应性问题	large language model multimodal
3	Chain-of-Thought Tuning: Masked Language Models can also Think Step By Step in Natural Language Understanding	提出Chain-of-Thought Tuning以提升Masked Language Models的自然语言理解能力	large language model chain-of-thought
4	Quantifying Self-diagnostic Atomic Knowledge in Chinese Medical Foundation Model: A Computational Analysis	量化中国医学基础模型中的自诊断原子知识以提升用户自诊断能力	foundation model	✅
5	Learning Co-Speech Gesture for Multimodal Aphasia Type Detection	提出多模态图神经网络以解决失语症类型检测问题	multimodal
6	REMARK-LLM: A Robust and Efficient Watermarking Framework for Generative Large Language Models	提出REMARK-LLM以解决生成文本水印的鲁棒性与效率问题	large language model
7	Evaluating the Symbol Binding Ability of Large Language Models for Multiple-Choice Questions in Vietnamese General Education	评估大型语言模型在越南多选题中的符号绑定能力	large language model
8	MusicAgent: An AI Agent for Music Understanding and Generation with Large Language Models	提出MusicAgent以解决音乐处理任务整合问题	large language model
9	The Curious Case of Hallucinatory (Un)answerability: Finding Truths in the Hidden States of Over-Confident Large Language Models	探讨LLMs在处理（不）可回答查询中的表现与改进	large language model
10	A Comprehensive Evaluation of Large Language Models on Legal Judgment Prediction	提出基于大语言模型的法律判决预测方法以解决法律领域应用挑战	large language model	✅
11	Systematic Assessment of Factual Knowledge in Large Language Models	提出框架系统评估大型语言模型的事实知识	large language model
12	MAGNIFICo: Evaluating the In-Context Learning Ability of Large Language Models to Generalize to Novel Interpretations	提出MAGNIFICo评估LLMs在上下文学习中的新解读能力	large language model
13	Eliminating Reasoning via Inferring with Planning: A New Framework to Guide LLMs' Non-linear Thinking	提出IEP框架以引导LLMs进行非线性思维	large language model chain-of-thought
14	SPEED: Speculative Pipelined Execution for Efficient Decoding	提出SPEED以解决生成式大语言模型推理延迟问题	large language model foundation model
15	Fast Multipole Attention: A Scalable Multilevel Attention Mechanism for Text and Images	提出快速多极注意力机制以解决长序列处理问题	multimodal	✅
16	Measuring Pointwise $\mathcal{V}$-Usable Information In-Context-ly	提出在上下文中测量点对点$ ext{V}$-可用信息的方法以提升学习效率	large language model
17	Pseudointelligence: A Unifying Framework for Language Model Evaluation	提出伪智能框架以优化语言模型评估	large language model
18	Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning	提出反射调优方法以提升大语言模型的指令调优效果	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	🔗	⭐
19	LACMA: Language-Aligning Contrastive Learning with Meta-Actions for Embodied Instruction Following	提出LACMA以解决机器人在未见环境中的指令跟随问题	contrastive learning instruction following	✅
20	Why Softmax Attention Outperforms Linear Attention	探讨软max注意力优于线性注意力的原因	linear attention
21	Multi-view Contrastive Learning for Entity Typing over Knowledge Graphs	提出多视角对比学习方法以解决知识图谱实体类型推断问题	contrastive learning

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
22	MISAR: A Multimodal Instructional System with Augmented Reality	提出MISAR以解决增强现实中的多模态信息整合问题	egocentric large language model multimodal	✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页