cs.CL（2025-12-19）

📊 共 10 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (8) 支柱一：机器人控制 (Robot Control) (1) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (8 篇)

#题目一句话要点标签🔗⭐
1 CIFE: Code Instruction-Following Evaluation CIFE：提出代码指令遵循评估基准，衡量LLM在代码生成中对开发者约束的遵守程度 large language model instruction following
2 UCoder: Unsupervised Code Generation by Internal Probing of Large Language Models UCoder：通过内部探测大语言模型实现无监督代码生成 large language model
3 Governance-Aware Hybrid Fine-Tuning for Multilingual Large Language Models 提出一种治理感知的混合微调框架，用于多语言大语言模型的低资源自适应。 large language model
4 Confidence-Credibility Aware Weighted Ensembles of Small LLMs Outperform Large LLMs in Emotion Detection 提出置信度-可信度加权的小LLM集成方法，在情感检测任务上超越大LLM large language model
5 AncientBench: Towards Comprehensive Evaluation on Excavated and Transmitted Chinese Corpora 提出AncientBench，用于全面评估模型对出土和传世古汉语语料的理解能力 large language model
6 DEER: A Comprehensive and Reliable Benchmark for Deep-Research Expert Reports DEER：一个全面可靠的深度研究专家报告评估基准 large language model
7 When the Gold Standard isn't Necessarily Standard: Challenges of Evaluating the Translation of User-Generated Content 针对用户生成内容翻译评估标准不统一问题，提出一套非标准现象分类和翻译行为规范。 large language model
8 Linear Personality Probing and Steering in LLMs: A Big Five Study 利用线性探针和引导实现LLM性格控制：基于大五人格的研究 large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
9 Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon Layers 提出Canon Layers，增强语言模型水平信息流动与推理能力 manipulation Mamba linear attention

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
10 Seed-Prover 1.5: Mastering Undergraduate-Level Theorem Proving via Learning from Experience Seed-Prover 1.5：通过经验学习掌握本科水平定理证明 reinforcement learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页