cs.CL（2025-01-08）

📊 共 15 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) (10 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#题目一句话要点标签🔗⭐
1 Understanding Before Reasoning: Enhancing Chain-of-Thought with Iterative Summarization Pre-Prompting 提出迭代摘要预提示(ISP^2)方法，提升LLM在隐式信息下的推理能力 large language model chain-of-thought ✅
2 Beyond Memorization: Assessing Semantic Generalization in Large Language Models Using Phrasal Constructions 构建评估框架以提升大语言模型的语义泛化能力 large language model
3 Hidden Entity Detection from GitHub Leveraging Large Language Models 利用大语言模型从GitHub中检测隐藏实体，无需大规模训练数据。 large language model
4 End-to-End Bangla AI for Solving Math Olympiad Problem Benchmark: Leveraging Large Language Model Using Integrated Approach 利用集成方法，增强大语言模型解决孟加拉语奥数题 large language model
5 SEO: Stochastic Experience Optimization for Large Language Models 提出随机经验优化（SEO）方法，提升大语言模型在特定任务上的性能。 large language model
6 LLM4SR: A Survey on Large Language Models for Scientific Research LLM4SR：综述性研究，探索大语言模型在科学研究各阶段的应用与影响 large language model ✅
7 Leveraging Log Probabilities in Language Models to Forecast Future Events 利用语言模型对数概率预测未来事件，提升预测准确性 large language model
8 Real-Time Textless Dialogue Generation 提出实时无文本对话生成模型，提升口语对话系统的自然度和流畅性。 large language model ✅
9 Multi-task retriever fine-tuning for domain-specific and efficient RAG 提出多任务检索器微调方法，提升领域特定RAG效率与泛化性。 large language model
10 Small Changes, Large Consequences: Analyzing the Allocational Fairness of LLMs in Hiring Contexts 分析LLM在招聘场景中的分配公平性：微小变动导致巨大偏差 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
11 OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-Time Self-Aware Emotional Speech Synthesis OpenOmni：通过渐进式多模态对齐和实时情感语音合成，推进开源全模态大语言模型。 direct preference optimization large language model multimodal
12 Graph-Based Multimodal Contrastive Learning for Chart Question Answering 提出基于图的多模态对比学习框架，解决图表问答中异构信息融合难题。 contrastive learning large language model multimodal
13 Unlocking Multimodal Mathematical Reasoning via Process Reward Model 提出URSA框架，通过过程奖励模型解锁多模态数学推理能力 reinforcement learning large language model multimodal
14 Quantum-inspired Embeddings Projection and Similarity Metrics for Representation Learning 提出一种量子启发的嵌入投影和相似性度量方法，用于表征学习。 representation learning contrastive learning large language model

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
15 S2 Chunking: A Hybrid Framework for Document Segmentation Through Integrated Spatial and Semantic Analysis 提出S2 Chunking混合框架，融合空间与语义信息提升文档分割效果 spatial relationship

⬅️ 返回 cs.CL 首页 · 🏠 返回主页