cs.CL（2023-12-28）

📊 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) (13 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (2)

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

#题目一句话要点标签🔗⭐
1 AQUALLM: Audio Question Answering Data Generation Using Large Language Models AQUALLM：利用大型语言模型生成音频问答数据，提升模型泛化性。 large language model ✅
2 LLM4Causal: Democratized Causal Tools for Everyone via Large Language Model LLM4Causal：通过大语言模型为所有人提供普适的因果推断工具 large language model
3 AI Content Self-Detection for Transformer-based Large Language Models 提出AI内容自检测方法，评估Transformer大语言模型识别自身生成内容的能力 large language model
4 Spike No More: Stabilizing the Pre-training of Large Language Models 稳定大语言模型预训练：通过控制梯度范数避免损失尖峰 large language model
5 Evaluating the Performance of Large Language Models for Spanish Language in Undergraduate Admissions Exams 评估大型语言模型在西班牙语本科入学考试中的表现 large language model
6 MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model Evaluation 提出MR-GSM8K基准，用于评估大语言模型的元推理能力 large language model
7 MathPile: A Billion-Token-Scale Pretraining Corpus for Math 提出MathPile：一个十亿级别token规模的数学预训练语料库，提升数学推理能力。 foundation model
8 Experiential Co-Learning of Software-Developing Agents 提出Experiential Co-Learning框架，提升LLM智能体在软件开发中的协同效率。 large language model ✅
9 Virtual Scientific Companion for Synchrotron Beamlines: A Prototype 提出用于同步辐射光束线的虚拟科学助手原型，通过自然语言控制实验。 large language model
10 BBScore: A Brownian Bridge Based Metric for Assessing Text Coherence 提出BBScore以解决文本连贯性评估问题 large language model
11 How Far Are LLMs from Believable AI? A Benchmark for Evaluating the Believability of Human Behavior Simulation 提出SimulateBench，评估LLM在模拟人类行为时的可信度 large language model
12 Structured Packing in LLM Training Improves Long Context Utilization 提出SPLiCe结构化数据填充方法，提升LLM长文本上下文利用率 large language model
13 Length Extrapolation of Transformers: A Survey from the Perspective of Positional Encoding 综述Transformer长度外推方法，聚焦位置编码视角下的技术方案。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
14 Adversarial Representation with Intra-Modal and Inter-Modal Graph Contrastive Learning for Multimodal Emotion Recognition 提出AR-IIGCN以解决多模态情感识别中的特征异质性问题 representation learning contrastive learning multimodal
15 Beyond Output Matching: Bidirectional Alignment for Enhanced In-Context Learning 提出双向对齐(BiAlign)方法，提升小模型在上下文学习中的能力。 distillation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页