cs.CL（2026-06-23）

📊 共 24 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (21 🔗5) 支柱二：RL算法与架构 (RL & Architecture) (1 🔗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) (21 篇)

#题目一句话要点标签🔗⭐
1 AI-PAVE-Br: Leveraging Large Language Models for Enhanced Product Attribute Value Extraction through a Golden Set Approach 提出AI-PAVE-Br以解决巴西电商产品属性值提取问题 large language model
2 BehaviorBench: Benchmarking Foundation Models for Behavioral Science Tasks 提出BehaviorBench基准以评估行为科学任务中的基础模型表现 foundation model ✅
3 PORTER: Language-Grounded Event Representations for Portable Structured EHR Foundation Models 提出PORTER以解决电子健康记录模型的词汇限制问题 foundation model
4 CAVEWOMAN: How Large Language Models Behave Under Linguistic Input and Output Compression 提出Cavewoman协议以评估语言模型在输入输出压缩下的表现 large language model ✅
5 On the Stability of Prompt Ranking in Large Language Model Evaluation 提出稳定性感知选择策略以解决提示排名不稳定问题 large language model
6 Same Lesson, Different Story: Cross-Lingual Reconstruction of Cultural Narratives in Large Language Models 提出多语言评估框架以解决文化叙事重建问题 large language model
7 MedBench v5: A Dynamic, Process-Oriented, and Hallucination-Aware Benchmark for Clinical Multimodal Models 提出MedBench v5以解决临床多模态模型评估中的动态性与幻觉检测问题 multimodal
8 Sentence-Level Contextual Entrainment in Large Language Models 扩展上下文共鸣至句子级别以提升语言模型性能 large language model
9 AVOC: Enhancing Hour-Level Audio-Video Understanding in Omni-Modal LLMs via Retrieval-Inspired Token Compression 提出AVOC以解决长视频理解中的信息冗余问题 large language model multimodal
10 To Compare, or Not to Compare: On Methodological Practices in Evaluating Social Bias 提出统一框架以解决社交偏见评估方法碎片化问题 large language model chain-of-thought
11 Privacy-Preserving RAG via Multi-Agent Semantic Rewriting: Achieving Confidentiality Without Compromising Contextual Fidelity 提出多代理语义重写框架以解决隐私保护问题 large language model ✅
12 Poster: Exploring the Limits of Audio-Based Detection of Turkish Phone Call Scams 提出多模态数据集以支持土耳其电话诈骗检测 large language model
13 The African Language Tax: Quantifying the Cost, Latency, and Context Penalty of Tokenizing African Languages in Frontier LLMs 量化非洲语言在前沿大模型中的分词成本与延迟 large language model
14 Pigeonholing: Bad prompts hurt models to collapse and make mistakes 提出新方法缓解模型在不良上下文中的性能下降问题 large language model
15 Are We Ready For An Agent-Native Memory System? 提出一种系统化的代理原生记忆系统评估框架 large language model ✅
16 DREAM: Dense Retrieval Embeddings via Autoregressive Modeling 提出DREAM以解决密集检索嵌入模型训练中的监督问题 large language model
17 Cross-Lingual Exploration for Parametric Knowledge 提出跨语言探索策略以提升参数知识获取效率 large language model
18 AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning 提出AGORA基准以解决文档推理中的归档问题 large language model
19 Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning 提出EDV框架以解决自我确认陷阱问题 large language model ✅
20 AutoSpecNER: A Fine-Grained Named Entity Recognition Dataset for Vehicle Specification Extraction 提出AutoSpecNER以解决汽车广告信息提取问题 large language model
21 VieSpeaker: A Large-Scale Vietnamese Speaker Recognition Dataset Beyond Visual Dependency 提出VieSpeaker以解决越南语说话人识别数据不足问题 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🔗⭐
22 Qwen-AgentWorld: Language World Models for General Agents 提出Qwen-AgentWorld以推动通用智能体的语言世界建模 world model world models foundation model ✅

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
23 Posterior Refinement: Fast Language Generation via Any-Order Flow Maps 提出FMLM+以解决非自回归生成模型的效率与质量问题 MDM

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

#题目一句话要点标签🔗⭐
24 ComputeFHE: A Privacy-Preserving General-Purpose Computation Library 提出ComputeFHE以解决全同态加密计算复杂性问题 OMOMO

⬅️ 返回 cs.CL 首页 · 🏠 返回主页