cs.CL（2023-12-15）

📊 共 19 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (14 🔗3) 支柱一：机器人控制 (Robot Control) (3) 支柱四：生成式动作 (Generative Motion) (1 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (14 篇)

#	题目	一句话要点	标签	🔗	⭐
1	SMILE: Multimodal Dataset for Understanding Laughter in Video with Language Models	提出SMILE数据集，利用语言模型解决视频中理解笑声原因的任务	large language model multimodal	✅
2	Low-resource classification of mobility functioning information in clinical sentences using large language models	利用大型语言模型进行临床语句中行动功能信息的低资源分类	large language model foundation model
3	ProCoT: Stimulating Critical Thinking and Writing of Students through Engagement with Large Language Models (LLMs)	提出ProCoT方法，通过学生与大语言模型互动，提升批判性思维和写作能力，并防止作弊。	large language model chain-of-thought
4	Faithful Persona-based Conversational Dataset Generation with Large Language Models	提出基于大型语言模型的生成器-评论家框架，用于生成高质量的、基于角色设定的对话数据集。	large language model
5	Binary Code Summarization: Benchmarking ChatGPT/GPT-4 and Other Large Language Models	BinSum：评估ChatGPT/GPT-4等大型语言模型在二进制代码摘要任务中的性能	large language model
6	LoRAMoE: Alleviate World Knowledge Forgetting in Large Language Models via MoE-Style Plugin	LoRAMoE：通过MoE风格插件缓解大语言模型中的世界知识遗忘	large language model
7	Taxonomy-based CheckList for Large Language Model Evaluation	提出基于分类的CheckList方法，用于评估大型语言模型中的偏见问题	large language model
8	Extending Context Window of Large Language Models via Semantic Compression	提出基于语义压缩的LLM上下文窗口扩展方法，无需微调即可处理6-8倍长度文本。	large language model
9	Marathon: A Race Through the Realm of Long Context with Large Language Models	Marathon：提出长文本大语言模型评测基准，解决现有基准不足。	large language model	✅
10	Red AI? Inconsistent Responses from GPT3.5 Models on Political Issues in the US and China	揭示GPT3.5在美中政治议题上双语回答的不一致性，暗示潜在政治倾向	large language model
11	Catwalk: A Unified Language Model Evaluation Framework for Many Datasets	Catwalk：一个统一的语言模型评估框架，适用于多种数据集	large language model	✅
12	LLaMAntino: LLaMA 2 Models for Effective Text Generation in Italian Language	LLaMAntino：面向意大利语的LLaMA 2高效文本生成模型	large language model
13	No-Skim: Towards Efficiency Robustness Evaluation on Skimming-based Language Models	提出No-Skim框架以评估基于滑模的语言模型的鲁棒性	large language model
14	A Review of Repository Level Prompting for LLMs	综述：针对大型语言模型的仓库级提示工程，提升代码生成能力	large language model

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
15	Does GPT-4 surpass human performance in linguistic pragmatics?	GPT-4在语言语用学理解上超越人类表现，展现通用AI潜力	humanoid humanoid robot large language model
16	RDR: the Recap, Deliberate, and Respond Method for Enhanced Language Understanding	提出RDR方法，通过回顾、审议和响应机制增强语言理解能力，提升模型鲁棒性。	manipulation
17	Picking the Underused Heads: A Network Pruning Perspective of Attention Head Selection for Fusing Dialogue Coreference Information	提出基于网络剪枝的注意力头选择方法，融合对话共指信息以提升对话摘要质量。	manipulation

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
18	Topic-VQ-VAE: Leveraging Latent Codebooks for Flexible Topic-Guided Document Generation	提出Topic-VQ-VAE，利用VQ-VAE的潜在码本进行灵活的主题引导文档生成。	VQ-VAE	✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
19	ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent	提出ReST meets ReAct框架，通过自提升学习解决多步推理LLM Agent的复杂问答问题	reinforcement learning distillation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页