cs.CL（2025-06-27）

📊 共 20 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (17 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (3)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (17 篇)

#题目一句话要点标签🔗⭐
1 A Large Language Model-Empowered Agent for Reliable and Robust Structural Analysis 提出LLM驱动的代理以解决结构分析的可靠性与鲁棒性问题 large language model chain-of-thought
2 VERA: Variational Inference Framework for Jailbreaking Large Language Models 提出VERA框架以解决大型语言模型的黑箱越狱问题 large language model
3 The Consistency Hypothesis in Uncertainty Quantification for Large Language Models 提出一致性假设以提升大语言模型的不确定性量化 large language model
4 Assessing the feasibility of Large Language Models for detecting micro-behaviors in team interactions during space missions 利用大型语言模型检测太空任务团队互动中的微行为 large language model
5 Detection of Personal Data in Structured Datasets Using a Large Language Model 提出基于GPT-4o的个人数据检测方法以解决结构化数据集中的隐私问题 large language model
6 PapersPlease: A Benchmark for Evaluating Motivational Values of Large Language Models Based on ERG Theory 提出PapersPlease基准以评估大型语言模型的动机价值 large language model ✅
7 DeepOmni: Towards Seamless and Smart Speech Interaction with Adaptive Modality-Specific MoE 提出DeepTalk以解决多模态大语言模型的遗忘与性能下降问题 large language model multimodal ✅
8 Lost at the Beginning of Reasoning 提出高效采样策略以优化推理初步步骤 large language model chain-of-thought
9 Optimal Estimation of Watermark Proportions in Hybrid AI-Human Texts 提出最优估计方法以解决混合来源文本水印比例问题 large language model
10 Temperature Matters: Enhancing Watermark Robustness Against Paraphrasing Attacks 提出新水印方法以增强对抗改写攻击的鲁棒性 large language model
11 QuickSilver -- Speeding up LLM Inference through Dynamic Token Halting, KV Skipping, Contextual Token Fusion, and Adaptive Matryoshka Quantization 提出QuickSilver以加速大型语言模型推理过程 large language model
12 RExBench: Can coding agents autonomously implement AI research extensions? 提出RExBench以评估AI代理的研究扩展能力 large language model
13 Refining Czech GEC: Insights from a Multi-Experiment Approach 提出基于Transformer的捷克语语法错误纠正系统 large language model ✅
14 Towards Fair Rankings: Leveraging LLMs for Gender Bias Detection and Measurement 利用大型语言模型检测和测量性别偏见以实现公平排名 large language model
15 A Dual-Layered Evaluation of Geopolitical and Cultural Bias in LLMs 提出双层评估框架以分析LLMs中的地缘政治与文化偏见 large language model
16 WildSpeech-Bench: Benchmarking End-to-End SpeechLLMs in the Wild 提出WildSpeech-Bench以解决语音LLM评估不足问题 large language model
17 RiverEcho: Real-Time Interactive Digital System for Ancient Yellow River Culture 提出RiverEcho系统以实时互动传承黄河文化 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🔗⭐
18 HyperCLOVA X THINK Technical Report 提出HyperCLOVA X THINK以增强推理能力的语言模型 reinforcement learning distillation large language model
19 Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation 提出两阶段框架评估视觉语言模型的内部世界模型能力 world model
20 Evaluating Scoring Bias in LLM-as-a-Judge 提出评估LLM作为评判者中的评分偏差的方法 preference learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页