cs.CL（2026-06-24）

📊 共 18 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (11 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗3) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#题目一句话要点标签🔗⭐
1 Same Evidence, Different Answer: Auditing Order Sensitivity in Multimodal Large Language Models 提出Facet-Probe以审计多模态大语言模型的顺序敏感性问题 large language model multimodal
2 Riazi-8B: An Urdu Large Language Model for Mathematical Reasoning 提出Riazi-8B以解决乌尔都语数学推理能力不足问题 large language model chain-of-thought
3 A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation 提出红队框架以评估大型语言模型的可信度问题 large language model
4 How Large Language Models Source Brand Reputation Across Languages and Markets 分析大型语言模型如何跨语言和市场获取品牌声誉信息 large language model
5 Evaluating Japanese Dialect Robustness Across Speech and Text-based Large Language Models 评估日语方言在语言模型中的鲁棒性以解决对话系统挑战 large language model
6 Weave of Formal Thought 提出WoFT以解决代码生成中的语法有效性问题 large language model
7 RAS: Measuring LLM Safety Through Refusal Alignment 提出SafeVec以解决大型语言模型安全评估问题 large language model
8 Improved Large Language Diffusion Models 提出iLLaDA以解决现有语言模型训练效率低的问题 large language model ✅
9 Overview of HIPE-2026: Person-Place Relation Extraction from Multilingual Historical Texts HIPE-2026提出多语言历史文本中的人物-地点关系提取方法 large language model
10 SFL-MTSC: Leveraging Semantic Frame-Level Multi-Task Self-Consistency for Robust Multi-Intent Spoken Language Understanding 提出SFL-MTSC以解决多意图语音理解中的一致性问题 large language model
11 A Survey of Toxicity Detection and Mitigation Strategies for Multilingual Language Models 综述多语言模型的毒性检测与减缓策略 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
12 Beyond Next-Observation Prediction: Agent-Authored World Modeling for Sequential Decision Making 提出Agent-Authored World Modeling以解决决策动态建模问题 world model world models large language model
13 PolicyAlign: Direct Policy-Based Safety Alignment for Large Language Models 提出PolicyAlign以解决大语言模型安全对齐问题 distillation large language model ✅
14 Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It 提出多种监督信号以解决多步骤工具使用强化学习的不稳定性问题 reinforcement learning large language model ✅
15 OPERA: Aligning Open-Ended Reasoning via Objective Perplexity-based Reinforcement Learning 提出OPERA以解决开放式推理任务中的不稳定监督问题 reinforcement learning ✅
16 Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing 提出局部分支路由以解决语言模型测试时间扩展问题 reinforcement learning chain-of-thought
17 BitNet Text Embeddings 提出BITEMBED以解决LLM文本嵌入的存储与效率问题 representation learning distillation

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
18 Security and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future Directions for Building Trustworthy Systems 提出全面框架以应对检索增强生成中的安全与隐私挑战 manipulation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页