cs.CL（2023-12-05）

📊 共 13 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (13 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (13 篇)

#题目一句话要点标签🔗⭐
1 MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction-Following MUFFIN：通过多方面指令生成，提升大语言模型的指令遵循能力 large language model instruction following
2 Assertion Enhanced Few-Shot Learning: Instructive Technique for Large Language Models to Generate Educational Explanations 提出Assertion Enhanced Few-Shot Learning，提升大语言模型生成教育解释的准确性和质量 large language model
3 Rank-without-GPT: Building GPT-Independent Listwise Rerankers on Open-Source Large Language Models 构建不依赖GPT的Listwise重排序器，提升开源LLM的检索性能 large language model
4 WhisBERT: Multimodal Text-Audio Language Modeling on 100M Words 提出WhisBERT：一种基于1亿词文本-音频数据的多模态语言模型。 multimodal
5 Large Language Models on Graphs: A Comprehensive Survey 综述图上的大语言模型：系统性地回顾了LLM在图数据上的应用场景与技术。 large language model ✅
6 How should the advent of large language models affect the practice of science? 探讨大型语言模型对科学研究实践的影响与未来发展方向 large language model
7 Mismatch Quest: Visual and Textual Feedback for Image-Text Misalignment 提出Mismatch Quest，通过视觉和文本反馈解决图像-文本对齐中的错配问题 large language model visual grounding
8 GPT vs Human for Scientific Reviews: A Dual Source Review on Applications of ChatGPT in Science 对比GPT与人类的科学评论：评估ChatGPT在科学应用中的表现 large language model
9 LLMs for Multi-Modal Knowledge Extraction and Analysis in Intelligence/Safety-Critical Applications 综述LLM在情报/安全关键应用中多模态知识提取与分析的脆弱性与缓解措施 large language model
10 Inherent limitations of LLMs regarding spatial information 揭示大语言模型在2D/3D空间信息处理上的固有局限性，并提出评估框架。 large language model
11 Impact of Tokenization on LLaMa Russian Adaptation 通过词汇替换提升LLaMa模型在俄语上的性能，加速微调与推理。 large language model
12 Decoding Data Quality via Synthetic Corruptions: Embedding-guided Pruning of Code Data 提出基于合成扰动的代码数据质量评估与剪枝方法，提升代码大模型性能。 large language model
13 Efficient Online Data Mixing For Language Model Pre-Training 提出在线数据混合(ODM)算法，提升语言模型预训练效率并优化数据配比。 large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页