cs.CL（2024-09-16）

📊 共 17 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) (14 🔗2) 支柱一：机器人控制 (Robot Control) (1) 支柱四：生成式动作 (Generative Motion) (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 Semantics Preserving Emoji Recommendation with Large Language Models 提出语义保持的Emoji推荐框架，利用大语言模型提升推荐质量 large language model
2 Do Large Language Models Need a Content Delivery Network? 提出知识传递网络(KDN)，优化LLM推理中KV缓存的管理与传递，提升知识注入效率。 large language model ✅
3 Schrodinger's Memory: Large Language Models 基于量子力学视角，探究大语言模型（LLM）的记忆机制与评估方法 large language model
4 The 20 questions game to distinguish large language models 提出基于“20问”游戏的LLM判别方法，用于检测模型泄露 large language model
5 LLMs4OL 2024 Overview: The 1st Large Language Models for Ontology Learning Challenge LLMs4OL 2024挑战赛：探索大型语言模型在本体学习中的潜力 large language model
6 StruEdit: Structured Outputs Enable the Fast and Accurate Knowledge Editing for Large Language Models StruEdit：结构化输出实现大语言模型知识编辑的快速与准确 large language model
7 LLM-DER:A Named Entity Recognition Method Based on Large Language Models for Chinese Coal Chemical Domain 提出LLM-DER框架，利用大语言模型解决中文煤化工领域命名实体识别难题。 large language model
8 Harnessing Large Language Models: Fine-tuned BERT for Detecting Charismatic Leadership Tactics in Natural Language 微调BERT模型，用于自然语言中领袖魅力的战术检测 large language model
9 Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention Steering AutoPASTA：通过自动注意力引导提升LLM在开放域问答中的可靠性 large language model ✅
10 NaviQAte: Functionality-Guided Web Application Navigation NaviQAte：提出功能引导的Web应用导航方法，提升自动化测试效果。 large language model
11 Self-Attention Limits Working Memory Capacity of Transformer-Based Models Transformer自注意力机制限制了其工作记忆容量，影响N-back任务表现 large language model
12 Improving Multi-candidate Speculative Decoding 提出目标模型引导的多候选推测解码方法，提升大语言模型推理速度。 large language model
13 Householder Pseudo-Rotation: A Novel Approach to Activation Editing in LLMs with Direction-Magnitude Perspective 提出Householder伪旋转，从方向-幅度视角提升LLM激活编辑的安全性和一致性 large language model
14 On the Diagram of Thought 提出思维导图（DoT）框架，提升LLM复杂推理能力，无需外部控制器。 large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
15 From Text to Emoji: How PEFT-Driven Personality Manipulation Unleashes the Emoji Potential in LLMs 利用PEFT驱动的个性操纵，释放LLM中表情符号的潜在能力 manipulation large language model

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
16 Incorporating Classifier-Free Guidance in Diffusion Model-Based Recommendation 提出结合无分类器引导的扩散模型推荐系统，提升推荐性能，尤其在数据稀疏场景下。 classifier-free guidance

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

#题目一句话要点标签🔗⭐
17 Self-Supervised Syllable Discovery Based on Speaker-Disentangled HuBERT 提出一种基于解耦说话人信息的自监督音节发现方法，提升音节分割和单元质量。 representation learning distillation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页