cs.CL（2026-08-28）

📊 共 20 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) (16 🔗5) 支柱二：RL算法与架构 (RL & Architecture) (2) 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) (16 篇)

#题目一句话要点标签🔗⭐
1 When Linguistic and Internal Confidence Diverge in Large Language Models 研究语言模型信心报告与内部信心的差异 large language model
2 Benchmarking large language model agent societies against human behavioural distributions 提出SILICA工具以评估语言模型代理社会行为 large language model
3 Twin Worlds: Equivariance-Based Abstention for Evidence-Grounded Reasoning 提出Twin Worlds框架以解决知识密集型推理中的不确定性问题 large language model
4 OpenStamp: A Watermark for Open-Source Language Models 提出OpenStamp以解决开源语言模型水印问题 large language model
5 SimpCue: Cue-Based Prompting for Multilingual Text Simplification 提出SimpCue以解决多语言文本简化中的提示信息不足问题 large language model
6 LandingAgent: A Reference-Annotated Dataset and Agentic Generation Framework for Landing Pages 提出LandingAgent框架以优化目标导向的落地页生成 large language model ✅
7 A Formal Limitation on Learning Human Language From Textual Corpora 提出信息论框架以界定语言理解的极限 large language model
8 Phoneme- and Word-Level Metrics Using Self-Supervised Speech Representations for Forced Alignment Evaluation 提出基于自监督语音表示的无参考强对齐评估指标 TAMP ✅
9 ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL 提出ContextPilot以解决长时代理任务中的上下文管理问题 large language model ✅
10 CultureConverse: A Multilingual Multi-turn Simulation Harness for Culturally Grounded Assistance in East and Southeast Asia 提出CultureConverse以解决多轮文化背景对话的评估问题 large language model
11 PersonaForge: Realistic Multi-Turn User Simulation for Agentic Systems 提出PersonaForge以解决多轮用户交互模拟问题 large language model
12 H-Scale: Hessian-Guided Scale Refinement for NVFP4 Sub-Byte LLM Inference 提出H-Scale以解决NVFP4量化模型推理中的尺度选择问题 large language model
13 A Shaky Voice Is Not Always a Dodge: Benchmarking Textual and Vocal Evasion Detection in Earnings Calls 提出DualEvasion以解决财报电话会议中的多维规避检测问题 multimodal
14 Beyond Global Scalars: Synergizing Token-Level Statistics and Deep Semantics for Adversarial AIGC Text Detection 提出MOSAIC基准与NeuroStat框架以解决对抗性文本检测问题 large language model ✅
15 QUORUM: QUality-Optimized Routing Using Multiple annotators 提出QUORUM以解决数据标注质量与成本问题 large language model ✅
16 AI Writers Have a Consistent Stylometric Footprint, but AI Editors Do Not 揭示AI生成与编辑文本的风格特征差异 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🔗⭐
17 Sliding-window beats linear attention 提出滑动窗口注意力以解决大语言模型的内存消耗问题 linear attention large language model
18 Synthetic Linguistic Agency: How an Embodied Mortal Agent Learns Linguistic Affordances through Consequential Social Experience 提出合成语言代理模型以解决语言模型缺乏持续性的问题 reinforcement learning affordance

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
19 CNeo-Bench: Diagnosing Large Language Models on Chinese Neologisms 提出CNeo-Bench以解决中文新词识别与生成问题 manipulation large language model

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

#题目一句话要点标签🔗⭐
20 NL2AGBench: Benchmarking LLM Auto-Formalization for AlphaGeometry 提出NL2AGBench以解决自然语言几何问题的形式化转换难题 IMoS large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页