cs.CL（2025-10-01）
📊 共 6 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) (6 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Training Large Language Models To Reason In Parallel With Global Forking Tokens | 提出SSFT方法，通过全局Forking Tokens训练LLM进行并行推理，提升复杂问题求解能力。 | large language model | ||
| 2 | TokMem: Tokenized Procedural Memory for Large Language Models | 提出TokMem：一种用于大型语言模型的Token化过程记忆，提升任务泛化与效率。 | large language model | ||
| 3 | Characterizing Model Behavior Under Synthetic Data Training: An Empirical Study Across Scales and Mixing Ratios | 研究合成数据比例对不同规模NLP模型行为的影响，为实际应用提供指导。 | large language model instruction following | ||
| 4 | Rationale-Augmented Retrieval with Constrained LLM Re-Ranking for Task Discovery | 提出混合语义检索系统以解决任务发现问题 | large language model | ||
| 5 | Enhancing Rating Prediction with Off-the-Shelf LLMs Using In-Context User Reviews | 利用上下文用户评论，增强现成LLM的评分预测能力 | large language model | ✅ | |
| 6 | KnowledgeSmith: Uncovering Knowledge Updating in LLMs with Model Editing and Unlearning | KnowledgeSmith：通过模型编辑与遗忘揭示LLM中的知识更新机制 | large language model | ✅ |