cs.CL（2025-01-25）

📊 共 15 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) (12 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#题目一句话要点标签🔗⭐
1 MDEval: Evaluating and Enhancing Markdown Awareness in Large Language Models 提出MDEval以评估和提升大型语言模型的Markdown意识 large language model ✅
2 Using Large Language Models for education managements in Vietnamese with low resources 提出VietEduFrame框架，利用LLM解决越南语低资源教育管理问题 large language model
3 Figurative-cum-Commonsense Knowledge Infusion for Multimodal Mental Health Meme Classification 提出M3H框架，通过常识知识增强多模态模型，提升心理健康Meme分类性能。 multimodal
4 Speech Translation Refinement using Large Language Models 利用大型语言模型改进语音翻译，实现联合优化与上下文感知。 large language model
5 Cross-modal Context Fusion and Adaptive Graph Convolutional Network for Multimodal Conversational Emotion Recognition 提出跨模态上下文融合与自适应图卷积网络用于多模态对话情感识别 multimodal
6 New Evaluation Paradigm for Lexical Simplification 提出一种新的词汇简化评估范式，解决现有数据集无法评估LLM简化句子的难题。 large language model chain-of-thought
7 AKVQ-VL: Attention-Aware KV Cache Adaptive 2-Bit Quantization for Vision-Language Models 提出AKVQ-VL以解决多模态模型KV缓存过大问题 large language model multimodal
8 SEAL: Scaling to Emphasize Attention for Long-Context Retrieval SEAL：通过缩放注意力权重提升长文本检索的大模型性能 large language model
9 Option-ID Based Elimination For Multiple Choice Questions 提出基于选项ID的消除方法以提升多项选择题性能 large language model
10 Are Human Interactions Replicable by Generative Agents? A Case Study on Pronoun Usage in Hierarchical Interactions 研究表明：大型语言模型驱动的生成Agent在模拟层级交互中的代词使用与人类存在显著差异 large language model
11 Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads Task-KV：通过注意力头语义区分实现任务感知的KV缓存优化 large language model
12 LongReason: A Synthetic Long-Context Reasoning Benchmark via Context Expansion 提出LongReason：通过上下文扩展构建的长文本推理合成基准 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🔗⭐
13 You Only Prune Once: Designing Calibration-Free Model Compression With Policy Learning 提出PruneNet，通过策略学习实现免校准数据集的模型压缩 policy learning large language model
14 Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning 提出MMOA-RAG，通过多智能体强化学习优化检索增强生成，提升问答准确性。 reinforcement learning large language model
15 Knowledge Hierarchy Guided Biological-Medical Dataset Distillation for Domain LLM Training 提出知识层级引导的生物医学数据集蒸馏框架，用于领域LLM训练。 distillation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页