cs.CL（2025-12-29）

📊 共 17 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (15) 支柱一：机器人控制 (Robot Control) (1 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (15 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Instruction-Following Evaluation of Large Vision-Language Models	研究表明视觉语言大模型微调后指令遵循能力下降，并提出改进方法。	large language model instruction following
2	Semantic Tree Inference on Text Corpa using a Nested Density Approach together with Large Language Model Embeddings	提出一种基于嵌套密度聚类和LLM嵌入的语义树推断方法，用于文本语料库的语义结构发现。	large language model
3	Scoring, Reasoning, and Selecting the Best! Ensembling Large Language Models via a Peer-Review Process	提出LLM-PeerReview，通过同行评审集成大语言模型，提升生成质量。	large language model
4	ClinDEF: A Dynamic Evaluation Framework for Large Language Models in Clinical Reasoning	提出ClinDEF动态评估框架，用于评估大型语言模型在临床推理中的能力	large language model
5	A Stepwise-Enhanced Reasoning Framework for Large Language Models Based on External Subgraph Generation	提出基于外部子图生成的逐步增强推理框架SGR，提升大语言模型在复杂推理任务中的性能。	large language model
6	AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents	综述：AI Agent中借鉴认知神经科学的记忆系统设计	multimodal
7	Eliciting Behaviors in Multi-Turn Conversations	提出多轮对话行为引导方法以提升评估效果	large language model
8	Anka: A Domain-Specific Language for Reliable LLM Code Generation	提出领域特定语言Anka，提升LLM在复杂数据转换任务中的代码生成可靠性。	large language model
9	Multilingual Hidden Prompt Injection Attacks on LLM-Based Academic Reviewing	多语言隐藏提示注入攻击影响LLM学术评审，不同语言脆弱性差异显著	large language model
10	Reservoir Computing inspired Matrix Multiplication-free Language Model	提出基于储层计算的无矩阵乘法语言模型，降低训练和推理成本。	large language model
11	Close the Loop: Synthesizing Infinite Tool-Use Data via Multi-Agent Role-Playing	InfTool：通过多智能体角色扮演合成无限工具使用数据，提升LLM工具调用能力。	large language model
12	The Big Three in Marriage Talk: LLM-Assisted Analysis of Moral Ethics and Sentiment on Weibo and Xiaohongshu	利用大语言模型分析微博和小红书上的婚姻话题，揭示道德伦理与情感倾向	large language model
13	Single LLM Debate, MoLaCE: Mixture of Latent Concept Experts Against Confirmation Bias	提出MoLaCE，通过混合潜在概念专家解决LLM中的确认偏差问题	large language model
14	Entropy-Guided Token Dropout: Training Autoregressive Language Models with Limited Domain Data	提出EntroDrop，通过熵引导的token dropout解决领域数据受限时自回归语言模型的过拟合问题	large language model
15	AI4Reading: Chinese Audiobook Interpretation System Based on Multi-Agent Collaboration	提出AI4Reading，一个基于多智能体协作的中文有声书解读系统	large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
16	Not too long do read: Evaluating LLM-generated extreme scientific summaries	提出BiomedTLDR数据集，评估大语言模型在生成科研论文极简摘要方面的能力	humanoid large language model	✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
17	Interpretable Safety Alignment via SAE-Constructed Low-Rank Subspace Adaptation	提出基于稀疏自编码器构建低秩子空间适配的安全对齐方法	RLHF large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页