cs.CL（2025-06-13）

📊 共 36 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (29 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗2) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (29 篇)

#题目一句话要点标签🔗⭐
1 Are Multimodal Large Language Models Pragmatically Competent Listeners in Simple Reference Resolution Tasks? 探讨多模态大语言模型在简单指称解析任务中的实用能力 large language model multimodal
2 Unsupervised Document and Template Clustering using Multimodal Embeddings 提出无监督文档与模板聚类方法以解决文档组织问题 multimodal
3 code_transformed: The Influence of Large Language Models on Code 研究LLM对代码风格的影响及其特征分析 large language model
4 Persona-driven Simulation of Voting Behavior in the European Parliament with Large Language Models 利用大语言模型模拟欧洲议会投票行为 large language model ✅
5 Supernova Event Dataset: Interpreting Large Language Models' Personality through Critical Event Analysis 提出超新星事件数据集以解析大型语言模型的个性 large language model
6 LoRA-Gen: Specializing Large Language Model via Online LoRA Generation 提出LoRA-Gen框架以提升边缘模型的任务适应性 large language model
7 InfoFlood: Jailbreaking Large Language Models with Information Overload 提出InfoFlood以解决大语言模型的安全漏洞问题 large language model
8 Generative Representational Learning of Foundation Models for Recommendation 提出RecFound框架以解决推荐系统中的多任务学习问题 foundation model
9 On the Effectiveness of Integration Methods for Multimodal Dialogue Response Retrieval 提出多模态对话响应检索集成方法以提升系统性能 multimodal
10 Predicting Early-Onset Colorectal Cancer with Large Language Models 利用大型语言模型预测早发性结直肠癌 large language model
11 Instruction Tuning and CoT Prompting for Contextual Medical QA with LLMs 提出指令调优与CoT提示以提升医学问答性能 large language model chain-of-thought
12 Aligning MLLM Benchmark With Human Preferences via Structural Equation Modeling 提出结构方程模型框架以解决多模态大语言模型评估问题 large language model multimodal
13 The Behavior Gap: Evaluating Zero-shot LLM Agents in Complex Task-Oriented Dialogs 提出全面评估框架以解决零-shot LLM代理在复杂任务对话中的行为差距问题 large language model
14 Long-Short Alignment for Effective Long-Context Modeling in LLMs 提出长短对齐方法以解决长上下文建模问题 large language model ✅
15 Are LLMs Good Text Diacritizers? An Arabic and Yorùbá Case Study 提出MultiDiac数据集以提升阿拉伯语和约鲁巴语的文本加音效果 large language model
16 Personalized LLM Decoding via Contrasting Personal Preference 提出CoPe以解决大语言模型个性化解码问题 large language model
17 Relational Schemata in BERT Are Inducible, Not Emergent: A Study of Performance vs. Competence in Language Models 探讨BERT中的关系模式可诱导性而非自发性 large language model
18 Towards Understanding the Cognitive Habits of Large Reasoning Models 提出CogTest以评估大型推理模型的认知习惯 chain-of-thought ✅
19 KoGEC : Korean Grammatical Error Correction with Pre-trained Translation Models 提出KoGEC以解决韩语语法错误纠正问题 large language model
20 A Rigorous Evaluation of LLM Data Generation Strategies for Low-Resource Languages 系统评估低资源语言的LLM数据生成策略 large language model
21 Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache 提出FourierAttention以解决大语言模型的内存效率问题 large language model
22 Post Persona Alignment for Multi-Session Dialogue Generation 提出后置个性对齐方法以解决多会话对话生成问题 large language model
23 A Hybrid Multi-Agent Prompting Approach for Simplifying Complex Sentences 提出混合多智能体提示方法以简化复杂句子 large language model
24 SceneGram: Conceptualizing and Describing Tangrams in Scene Context 提出SceneGram数据集以研究场景上下文对概念化的影响 multimodal
25 From Persona to Person: Enhancing the Naturalness with Multiple Discourse Relations Graph Learning in Personalized Dialogue Generation 提出MUDI以解决个性化对话生成中的自然性问题 large language model
26 Lag-Relative Sparse Attention In Long Context Training 提出Lag-Relative Sparse Attention以解决长上下文训练中的计算复杂性问题 large language model
27 AbsenceBench: Language Models Can't Tell What's Missing 提出AbsenceBench以评估语言模型缺失信息识别能力 large language model
28 Efficient Long-Context LLM Inference via KV Cache Clustering 提出Chelsea框架以解决长上下文LLM推理中的KV缓存问题 large language model
29 Computational Analysis of Climate Policy 构建PALLM系统以分析气候政策的影响 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
30 Improving Large Language Model Safety with Contrastive Representation Learning 提出对比表示学习框架以增强大型语言模型的安全性 representation learning large language model ✅
31 DART: Distilling Autoregressive Reasoning to Silent Thought 提出DART以解决自回归推理的计算开销问题 distillation large language model chain-of-thought
32 Agent-RLVR: Training Software Engineering Agents via Guidance and Environment Rewards 提出Agent-RLVR以解决复杂软件工程任务中的奖励稀疏问题 reinforcement learning large language model
33 Maximally-Informative Retrieval for State Space Model Generation 提出RICO方法以优化状态空间模型生成中的信息检索 state space model
34 Configurable Preference Tuning with Rubric-Guided Synthetic Data 提出可配置偏好调优框架以解决静态偏好限制问题 DPO direct preference optimization ✅

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

#题目一句话要点标签🔗⭐
35 Large Language Models for History, Philosophy, and Sociology of Science: Interpretive Uses, Methodological Challenges, and Critical Perspectives 探讨大型语言模型在科学史、哲学与社会学中的应用与挑战 affordance large language model

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
36 AutoGen Driven Multi Agent Framework for Iterative Crime Data Analysis and Prediction 提出LUCID-MA框架以实现犯罪数据的迭代分析与预测 spatiotemporal

⬅️ 返回 cs.CL 首页 · 🏠 返回主页