cs.CL（2025-01-09）

📊 共 19 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (15 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (15 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Exploring Large Language Models for Translating Romanian Computational Problems into English	利用大型语言模型提升罗马尼亚信息学竞赛题到英语的翻译质量	large language model
2	The dynamics of meaning through time: Assessment of Large Language Models	评估大型语言模型对历史语义演变的理解能力	large language model
3	A survey of textual cyber abuse detection using cutting-edge language models and large language models	综述：利用前沿语言模型和大型语言模型进行文本网络恶意信息检测	large language model
4	GLaM-Sign: Greek Language Multimodal Lip Reading with Integrated Sign Language Accessibility	GLaM-Sign：集成希腊语手语可访问性的多模态唇语阅读资源	multimodal
5	Leveraging Large Language Models for Zero-shot Lay Summarisation in Biomedicine and Beyond	提出基于大语言模型的两阶段零样本生物医学领域摘要生成框架	large language model
6	Enhancing Human-Like Responses in Large Language Models	提升大型语言模型人情味：融合心理学与多样化数据微调	large language model
7	Investigating Numerical Translation with Large Language Models	提出评估大语言模型在数字翻译中的可靠性以解决安全问题	large language model
8	Stream Aligner: Efficient Sentence-Level Alignment via Distribution Induction	Stream Aligner：通过分布诱导实现高效的句子级对齐	large language model
9	Optimizing Estonian TV Subtitles with Semi-supervised Learning and LLMs	利用半监督学习和LLM优化爱沙尼亚语电视字幕生成	large language model
10	Unlocking In-Context Learning for Natural Datasets Beyond Language Modelling	揭示并促进自回归模型上下文学习能力，拓展至视觉和脑电数据集	large language model
11	FairCoder: Evaluating Social Bias of LLMs in Code Generation	FairCoder：提出用于评估代码生成中LLM社会偏见的新基准	large language model
12	Comparison of Feature Learning Methods for Metadata Extraction from PDF Scholarly Documents	评估NLP、CV和多模态特征学习方法，提升PDF学术文档元数据提取性能。	multimodal
13	SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution	SWE-Fixer：训练开源LLM以高效解决GitHub问题	large language model	✅
14	TreeKV: Smooth Key-Value Cache Compression with Tree Structures	提出TreeKV：一种基于树结构的平滑Key-Value缓存压缩方法，适用于长序列LLM。	large language model
15	Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words	提出基于多义词表示的稀疏自编码器评估方法，揭示现有优化目标与单义特征提取的矛盾。	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	🔗	⭐
16	Step-by-Step Mastery: Enhancing Soft Constraint Following Ability of Large Language Models	提出基于DPO和课程学习的框架，提升LLM对软约束的遵循能力	DPO direct preference optimization curriculum learning	✅
17	Demystifying Domain-adaptive Post-training for Financial LLMs	FINDAP：金融领域LLM领域自适应后训练的系统性研究与Llama-Fin模型	distillation large language model instruction following
18	LLMQuoter: Enhancing RAG Capabilities Through Efficient Quote Extraction From Large Contexts	LLMQuoter：通过高效引用提取增强RAG能力	distillation large language model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
19	Harmonizing Metadata of Language Resources for Enhanced Querying and Accessibility	提出基于链接数据和RDF技术的语言资源元数据统一模型，提升查询和可访问性。	open-vocabulary open vocabulary

⬅️ 返回 cs.CL 首页 · 🏠 返回主页