cs.CL（2026-08-05）

📊 共 28 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) (19 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱一：机器人控制 (Robot Control) (1) 支柱五：交互与反应 (Interaction & Reaction) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (19 篇)

#题目一句话要点标签🔗⭐
1 RESPClinBench: Benchmarking Multimodal Clinical Decision-Making and Longitudinal Disease Management in Respiratory Specialty Care 提出RESPClinBench以解决呼吸专科临床决策不足问题 large language model multimodal
2 ODRA: Synthesizing Cognitive Behavioral Therapy Sessions with Structured Chain-Of-Thought and Dynamic Patient Resistance 提出ODRA框架以解决合成认知行为疗法会话中的患者抵抗问题 chain-of-thought
3 When Absence Is Evidence: Evaluating Completeness-Sensitive Negative Reasoning in Large Language Models 提出CROWN-QA以解决大语言模型的完整性敏感负推理问题 large language model
4 IslamicTurathBench: A Multi-Task, Multi-Discipline Benchmark for Evaluating Large Language Models on the Islamic Scholarly Tradition (turath) 提出IslamicTurathBench以评估大型语言模型在伊斯兰学术传统中的表现 large language model
5 Causal Evidence Extraction and Triangulation in Crisis Reports using Large Language Models: A ReliefWeb-based Study 提出基于大语言模型的因果证据提取与三角测量方法以解决人道主义报告中的信息整合问题 large language model
6 DataRx: Missingness-Aware Sampling for Safer Large Language Model Task-Specific Fine-Tuning 提出DataRx以解决大语言模型任务特定微调中的安全性问题 large language model
7 Protoreasoning in Tiny Transformers 提出原型推理方法以提升小型变换器的推理能力 large language model chain-of-thought
8 Easy to Complete, Hard to Choose: Investigating LLM Performance on the ProverbIT Benchmark 提出ProverbIT基准以评估LLM对意大利谚语的理解能力 large language model chain-of-thought
9 Does Out-of-Sight Equal Out-of-Mind in CoT Monitorability? 提出基于提示干预的CoT监控方法以提高模型可监控性 large language model chain-of-thought
10 Representing Visual Evidence for Item Difficulty Prediction: Visual Textualization and Image-Native Modeling 提出视觉证据表示方法以解决项目难度预测问题 large language model
11 Chained Recursive Language Models for Multi-Iteration Reasoning 提出链式递归语言模型以解决多轮推理问题 large language model
12 D$^2$F-ReAG: Dynamic Decomposition and Filtering for Multi-Hop Reasoning-Augmented Generation 提出D2F-ReAG以解决多跳推理生成中的知识依赖问题 large language model
13 Spoken Function Calling: A New Perspective on Spoken Language Understanding for Large Audio Language Models 提出口语功能调用以解决开放领域语音理解问题 large language model
14 Strengthening Target-Language Features: SAE-Based Steering for Multilingual Inference 提出基于稀疏自编码器的多语言推理引导方法 large language model
15 Skill-Use: Can LLMs Actually Use Skills in Agentic Harnesses? 提出Skill-Use基准以评估LLM在技能应用中的能力 large language model
16 When Memory Lies: An Empirical Study of Spatial Memory Staleness in VLM Agents 研究空间记忆过时性以提升VLM代理的安全性 visual grounding
17 K-EXAONE 2.0 Technical Report 提出K-EXAONE 2.0以提升多语言模型能力 foundation model
18 Social Pressure Breaks Majority Voting in LLM Safety Panels 研究社交压力对大型语言模型安全评估的影响 large language model
19 EdgeLM: Edge Demonstrations for Language Models' Table Understanding 提出EdgeLM以解决语言模型表格理解中的演示选择问题 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🔗⭐
20 Pun Intended: Multi-Agent Translation of Wordplay with Contrastive Learning and Phonetic-Semantic Embeddings 提出多代理翻译方法以解决语言间双关语翻译问题 contrastive learning HuMoR large language model
21 Breaking the Curse ofMultilinguality inMany-to-Many Speech-to-Text Translation via a Resource-AwareMixture of Speech Encoders 提出资源感知的混合语音编码器以解决多语言语音转文本翻译问题 curriculum learning large language model multimodal
22 FinReportBench: Measuring and Improving Institution-Grade Financial Report Generation 提出FinReportBench以解决机构级财务报告生成问题 distillation large language model multimodal ✅
23 Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs 提出能效与内存高效的PEFT方法以实现个性化设备部署 Mamba SSM large language model
24 Evaluating Theory of Mind in Reasoning Models: Robustness over Reasoning 评估推理模型中的心智理论：增强推理的鲁棒性 reinforcement learning 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🔗⭐
25 Searching for Sound-Meaning Collisions: Graph-Based Affordance Retrieval and Multi-Evaluator Ranking for Pun Translation at CLEF 2026 JOKER Task 2 提出基于图的翻译方法以解决双关语翻译问题 affordance

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
26 Reading Between the Frames: Interpreting Implicit and Non-literal Meaning in Social Media Videos 提出DrivelHub+以解决社交媒体视频隐含意义理解问题 HuMoR multimodal

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
27 State2State: Environment-Derived Mid-Training for LLM Agents 提出State2State以解决LLM代理训练中的任务依赖问题 manipulation reinforcement learning

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

#题目一句话要点标签🔗⭐
28 Language Models Generalize to Human-like Word Order Preferences 研究语言模型在贫乏输入下的词序偏好 OMOMO

⬅️ 返回 cs.CL 首页 · 🏠 返回主页