cs.CL（2025-04-12）

📊 共 9 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 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱六：视频提取与匹配 (Video Extraction) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Improving the Accuracy and Efficiency of Legal Document Tagging with Large Language Models and Instruction Prompts	提出Legal-LLM，通过指令微调LLM解决法律文档多标签分类的准确性和效率问题。	large language model instruction following
2	Efficient and Asymptotically Unbiased Constrained Decoding for Large Language Models	提出DISC算法，通过动态重要性采样实现大语言模型高效且无偏的约束解码。	large language model
3	VisuoThink: Empowering LVLM Reasoning with Multimodal Tree Search	VisuoThink：多模态树搜索赋能LVLM进行视觉推理	multimodal
4	Reconstructing Sepsis Trajectories from Clinical Case Reports using LLMs: the Textual Time Series Corpus for Sepsis	利用LLM从临床病例报告重建脓毒症轨迹，构建脓毒症文本时间序列语料库	large language model multimodal
5	A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future	全面综述奖励模型：分类、应用、挑战与未来展望	large language model	✅
6	QUDsim: Quantifying Discourse Similarities in LLM-Generated Text	提出QUDsim，量化LLM生成文本中基于篇章结构的相似性，揭示其重复性问题。	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
7	Feature-Aware Malicious Output Detection and Mitigation	提出特征感知恶意输出检测与缓解方法，提升大语言模型安全性。	reinforcement learning large language model
8	Langformers: Unified NLP Pipelines for Language Models	Langformers：统一NLP流水线，简化大型语言模型应用	distillation large language model

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
9	From Punchlines to Predictions: A Metric to Assess LLM Performance in Identifying Humor in Stand-Up Comedy	提出一种评估LLM在单口喜剧幽默识别能力的新指标	HuMoR large language model	✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页