cs.CL（2026-06-05）

📊 共 19 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) (14 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱一：机器人控制 (Robot Control) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (14 篇)

#题目一句话要点标签🔗⭐
1 M$^3$Exam: Benchmarking Multimodal Memory for Realistic User-Agent Interactions 提出M$^3$Exam以解决多模态用户代理交互中的记忆评估问题 multimodal
2 Are Large Language Models Suitable for Graph Computation? Progress and Prospects 提出基于角色的分类法以评估大语言模型在图计算中的适用性 large language model
3 The Dark Regulome: Disentangling Predictability from Regulation in Genomic Foundation Models 提出残差与置换诊断以解析基因组基础模型中的调控与可预测性问题 foundation model
4 How reliable are LLMs when it comes to playing dice? 评估大型语言模型在概率推理中的可靠性 large language model chain-of-thought
5 The Masked Advantage: Uncovering Local-Language Access to Cultural Knowledge in LLMs 提出新框架以揭示大语言模型中文化知识获取的语言优势 large language model language conditioned
6 SigmaScale: LLM Compression with SVD-based Low-Rank Decomposition and Learned Scaling Matrices 提出SigmaScale以优化大语言模型压缩问题 large language model
7 ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM Reasoning 提出ThinkBooster以解决大语言模型推理的计算资源分配问题 large language model
8 OpenHalDet: A Unified Benchmark for Hallucination Detection across Diverse Generation Scenarios 提出OpenHalDet以解决幻觉检测评估不一致问题 large language model ✅
9 Auditing Training Data in Domain-adapted LLMs: LoRA-MINT 提出LoRA-MINT以解决LLMs训练数据审计问题 large language model
10 Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings 提出EmbedFilter以解决文本嵌入模型性能不足问题 large language model ✅
11 Phun-Bench: Evaluating LLMs on Phonological Understanding in Chinese 提出Phun-Bench以评估LLMs的汉语音韵理解能力 large language model
12 MMAE: A Massive Multitask Audio Editing Benchmark 提出MMAE基准以解决音频编辑评估不足问题 instruction following
13 Adversarial Creation and Detection of AI-Generated Social Bot Content 提出对抗性方法以检测AI生成的社交机器人内容 large language model
14 TA-RAG: Tone-Aware Retrieval-Augmented Generation for Peer-Support Health Communication 提出TA-RAG框架以解决敏感健康沟通中的语气问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
15 Progress-SQL: Improving Reinforcement Learning for Text-to-SQL via Progressive Rewards 提出Progress-SQL以解决Text-to-SQL生成中的奖励优化问题 reinforcement learning large language model
16 Translate-R1: Cost-Aware Translation Tool Use via Reinforcement Learning 提出Translate-R1以优化翻译工具使用的成本效益 reinforcement learning
17 Korean Culture into LLM Alignment: Toward Cultural Coherence 提出文化一致性框架以提升韩语LLM的安全性 DPO large language model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
18 When Large Language Models Fail in Healthcare: Evaluating Sensitivity to Prompt Variations 评估大型语言模型在医疗中的敏感性以应对安全风险 manipulation large language model
19 Explain Like I'm 5 or Whatever I Choose: Evaluating the Interactive Potential of Language Model Responses 提出新评估框架以提升语言模型的互动潜力 manipulation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页