cs.CL（2025-09-06）

📊 共 11 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) (5 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱七：动作重定向 (Motion Retargeting) (1 🔗1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian	Llama-GENBA-10B：面向德语、英语和巴伐利亚语的三语大型语言模型	large language model foundation model
2	Icon$^{2}$: Aligning Large Language Models Using Self-Synthetic Preference Data via Inherent Regulation	提出Icon²以高效构建人类偏好数据集	large language model
3	Cross-Question Method Reuse in Large Language Models: From Word-Level Prediction to Rational Logical-Layer Reasoning	提出跨问题方法复用框架，扩展大语言模型在低相似度问题上的应用	large language model
4	Enhancing Factual Accuracy and Citation Generation in LLMs via Multi-Stage Self-Verification	VeriFact-CoT：多阶段自验证提升大语言模型的事实准确性和引用生成	large language model chain-of-thought
5	LM-Searcher: Cross-domain Neural Architecture Search with LLMs via Unified Numerical Encoding	LM-Searcher：利用LLM和统一数值编码实现跨领域神经架构搜索	large language model	✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#	题目	一句话要点	标签	🔗	⭐
6	Mitigating Spurious Correlations Between Question and Answer via Chain-of-Thought Correctness Perception Distillation	提出CoPeD，通过纠正性感知蒸馏缓解CoT数据中的虚假相关性问题	distillation large language model chain-of-thought
7	Using Contrastive Learning to Improve Two-Way Reasoning in Large Language Models: The Obfuscation Task as a Case Study	提出对比学习微调方法，提升大语言模型在代码混淆任务中的双向推理能力	contrastive learning large language model
8	A Survey of the State-of-the-Art in Conversational Question Answering Systems	综述性研究：对话式问答系统（ConvQA）的最新技术进展与未来方向	reinforcement learning contrastive learning large language model
9	LatinX: Aligning a Multilingual TTS Model with Direct Preference Optimization	LatinX：通过直接偏好优化对齐多语种TTS模型，实现跨语种语音克隆	DPO direct preference optimization

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
10	From Joy to Fear: A Benchmark of Emotion Estimation in Pop Song Lyrics	提出流行歌曲歌词情感估计基准，评估LLM在情感属性预测中的表现。	motion estimation large language model	✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
11	AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs	AntiDote：面向抗篡改LLM的双层对抗训练方法	manipulation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页