cs.CL（2024-09-13）

📊 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) (10 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱四：生成式动作 (Generative Motion) (1) 支柱五：交互与反应 (Interaction & Reaction) (1)

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

#题目一句话要点标签🔗⭐
1 Eir: Thai Medical Large Language Models Eir-8B：面向泰国医疗场景的80亿参数大语言模型 large language model chain-of-thought
2 Contextual Evaluation of Large Language Models for Classifying Tropical and Infectious Diseases 针对热带传染病分类，论文提出利用上下文信息优化大语言模型性能的方法。 large language model
3 KodeXv0.1: A Family of State-of-the-Art Financial Large Language Models KodeXv0.1：金融领域专用大语言模型，超越GPT-4金融问答能力。 large language model
4 Large Language Model Can Transcribe Speech in Multi-Talker Scenarios with Versatile Instructions 提出MT-LLM以解决多说话者场景下的语音转录问题 large language model ✅
5 When Context Leads but Parametric Memory Follows in Large Language Models 研究大型语言模型在知识一致场景下上下文与参数记忆的知识分配策略 large language model
6 Optimizing Ingredient Substitution Using Large Language Models to Enhance Phytochemical Content in Recipes 利用大型语言模型优化食材替换，提升食谱中的植物化学物含量 large language model
7 Fingerprint Vector: Enabling Scalable and Efficient Model Fingerprint Transfer via Vector Addition 提出指纹向量方法，通过向量加法实现大规模模型指纹的高效迁移。 large language model
8 Your Weak LLM is Secretly a Strong Teacher for Alignment 利用弱LLM作为对齐的强大教师，降低对齐成本并提升自动化程度 large language model
9 Cracking the Code: Multi-domain LLM Evaluation on Real-World Professional Exams in Indonesia 提出IndoCareer数据集，评估LLM在印尼真实职业考试中的多领域能力 large language model
10 LLM-Powered Grapheme-to-Phoneme Conversion: Benchmark and Case Study 提出基于LLM的字素音素转换方法，提升波斯语等低资源语言的语音合成效果 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🔗⭐
11 Expediting and Elevating Large Language Model Reasoning via Hidden Chain-of-Thought Decoding 提出基于语义对齐的隐藏思维链解码方法，加速并提升大语言模型推理能力。 contrastive learning large language model chain-of-thought
12 AIPO: Improving Training Objective for Iterative Preference Optimization 提出AIPO，通过改进训练目标解决迭代偏好优化中的长度利用问题。 PPO large language model ✅

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
13 ReCLAP: Improving Zero Shot Audio Classification by Describing Sounds ReCLAP：通过描述声音改进零样本音频分类 open-vocabulary open vocabulary

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
14 Investigating Disentanglement in a Phoneme-level Speech Codec for Prosody Modeling 提出基于音素级语音编码的解耦韵律建模方法，实现细粒度韵律控制。 VQ-VAE

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
15 Pronoun Logic 提出一种基于形式逻辑的代词表达方法，旨在促进性别认同和尊重。 ReMoS

⬅️ 返回 cs.CL 首页 · 🏠 返回主页