cs.CL（2025-01-26）

📊 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 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1)

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

#题目一句话要点标签🔗⭐
1 Large Language Models as Theory of Mind Aware Generative Agents with Counterfactual Reflection 提出ToM-agent，赋予LLM生成式Agent在开放域对话中模拟心智理论的能力 large language model
2 SEAL: Speech Embedding Alignment Learning for Speech Large Language Model with Retrieval-Augmented Generation 提出SEAL：通过语音嵌入对齐学习实现语音大语言模型的检索增强生成。 large language model multimodal
3 Transformer-Based Multimodal Knowledge Graph Completion with Link-Aware Contexts 提出基于Transformer的多模态知识图谱补全方法，利用链接感知上下文提升性能。 multimodal
4 Semantic Layered Embedding Diffusion in Large Language Models for Multi-Contextual Consistency 提出语义分层嵌入扩散（SLED）机制，提升大型语言模型的多上下文一致性。 large language model
5 Adapting Biomedical Abstracts into Plain language using Large Language Models 利用大型语言模型将生物医学摘要改编为通俗易懂的语言 large language model
6 Error Classification of Large Language Models on Math Word Problems: A Dynamically Adaptive Framework 提出动态自适应框架，用于大规模语言模型在数学应用题上的错误分类。 large language model
7 Cross-Cultural Fashion Design via Interactive Large Language Models and Diffusion Models 提出LLM引导的扩散模型，用于生成具有文化多样性的时尚设计内容 large language model
8 The Potential of Large Language Models in Supply Chain Management: Advancing Decision-Making, Efficiency, and Innovation 利用大型语言模型提升供应链管理决策、效率与创新能力 large language model
9 TensorLLM: Tensorising Multi-Head Attention for Enhanced Reasoning and Compression in LLMs TensorLLM：通过张量化多头注意力提升LLM推理能力与压缩率 large language model
10 Evaluating the Effectiveness of XAI Techniques for Encoder-Based Language Models 评估XAI技术在Encoder语言模型中的有效性，LIME表现突出 large language model
11 SCP-116K: A High-Quality Problem-Solution Dataset and a Generalized Pipeline for Automated Extraction in the Higher Education Science Domain 提出SCP-116K：一个高质量的理科高等教育领域问题-解答数据集，以及通用的自动抽取流程。 large language model ✅
12 Instruction Tuning for Story Understanding and Generation with Weak Supervision 提出弱到强指令调优方法，提升故事理解与生成性能 large language model
13 OpenCharacter: Training Customizable Role-Playing LLMs with Large-Scale Synthetic Personas OpenCharacter：利用大规模合成角色数据训练可定制的角色扮演LLM 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 Data-adaptive Safety Rules for Training Reward Models 提出数据自适应安全规则方法，提升奖励模型训练效果 reinforcement learning RLHF large language model
15 ARWKV: Pretrain is not what we need, an RNN-Attention-Based Language Model Born from Transformer 提出ARWKV模型以提升RNN的表达能力和效率 distillation foundation model ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页