cs.CL（2024-09-10）

📊 共 21 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (20 🔗3) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (20 篇)

#题目一句话要点标签🔗⭐
1 RNR: Teaching Large Language Models to Follow Roles and Rules 提出RNR以提升大语言模型的角色与规则遵循能力 large language model instruction following
2 Larger Language Models Don't Care How You Think: Why Chain-of-Thought Prompting Fails in Subjective Tasks 大型语言模型在主观任务中Chain-of-Thought推理失效：推理先验固化后验预测 large language model chain-of-thought ✅
3 LLaMA-Omni: Seamless Speech Interaction with Large Language Models LLaMA-Omni：基于开源LLM的无缝语音交互模型，实现低延迟高质量语音对话。 large language model
4 Knowing When to Ask -- Bridging Large Language Models and Data 提出结合数据源的LLM增强方法，提升数值和统计事实的准确性 large language model
5 E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning E2LLM：提出Encoder扩展的大语言模型，用于长文本理解与推理 large language model
6 Sortformer: A Novel Approach for Permutation-Resolved Speaker Supervision in Speech-to-Text Systems Sortformer：一种用于语音转文本系统中置换解析说话人监督的新方法 large language model multimodal TAMP
7 LaMsS: When Large Language Models Meet Self-Skepticism LaMsS：结合自怀疑精神的大语言模型，缓解幻觉问题 large language model
8 MoRE: A Mixture of Reflectors Framework for Large Language Model-Based Sequential Recommendation 提出MoRE框架，通过混合反射器解耦用户行为，提升LLM在序列推荐中的性能。 large language model ✅
9 Enhancing Large Language Models with Domain-Specific Knowledge: The Case in Topological Materials TopoChat：利用领域知识增强大语言模型在拓扑材料领域的应用 large language model
10 Can Large Language Models Unlock Novel Scientific Research Ideas? 评估大语言模型生成科研新思路能力，并提出自动评估指标IAScore和Idea Distinctness Index large language model
11 Deep Learning and Large Language Models for Audio and Text Analysis in Predicting Suicidal Acts in Chinese Psychological Support Hotlines 利用大语言模型分析心理热线音频与文本以预测自杀行为 large language model
12 MathGLM-Vision: Solving Mathematical Problems with Multi-Modal Large Language Model MathGLM-Vision：利用多模态大语言模型解决数学问题 large language model
13 Accelerating Large Language Model Pretraining via LFR Pedagogy: Learn, Focus, and Review 提出LFR教学法，加速大语言模型预训练，显著降低训练成本。 large language model
14 A Practice of Post-Training on Llama-3 70B with Optimal Selection of Additional Language Mixture Ratio 针对Llama-3 70B，通过优化语言混合比例进行后训练，提升中文能力。 large language model
15 Medal Matters: Probing LLMs' Failure Cases Through Olympic Rankings 通过奥运奖牌榜探究大语言模型在排序推理上的失败案例 large language model
16 What is the Role of Small Models in the LLM Era: A Survey 综述LLM时代小模型角色：协作与竞争视角分析 large language model ✅
17 Fine-tuning and Prompt Engineering with Cognitive Knowledge Graphs for Scholarly Knowledge Organization 利用认知知识图谱微调和提示工程，实现学术知识的有效组织与管理 large language model
18 Extracting Paragraphs from LLM Token Activations 通过LLM Token激活值提取段落信息，探索模型上下文理解能力 large language model
19 Inference is All You Need: Self Example Retriever for Cross-domain Dialogue State Tracking with ChatGPT 提出一种基于ChatGPT自示例检索的跨领域对话状态跟踪方法，无需参数更新。 chain-of-thought
20 SHAPE-IT: Exploring Text-to-Shape-Display for Generative Shape-Changing Behaviors with LLMs 提出SHAPE-IT，利用LLM实现文本驱动的动态形状显示生成 large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
21 Decomposition of surprisal: Unified computational model of ERP components in language processing 提出基于信息论的语言处理ERP成分统一计算模型，解释N400和P600信号。 manipulation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页