cs.CL（2025-05-02）

📊 共 17 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (14 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (14 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Synthesize-on-Graph: Knowledgeable Synthetic Data Generation for Continue Pre-training of Large Language Models	提出Synthetic-on-Graph框架，利用知识图谱生成合成数据，提升LLM在数据稀缺场景下的性能。	large language model chain-of-thought
2	Enhancing ML Model Interpretability: Leveraging Fine-Tuned Large Language Models for Better Understanding of AI	提出一种基于微调LLM的交互式XAI参考架构，提升模型可解释性	large language model
3	On the effectiveness of Large Language Models in the mechanical design domain	评估大型语言模型在机械设计领域的有效性，揭示领域特定失败模式	large language model
4	Towards High-Fidelity Synthetic Multi-platform Social Media Datasets via Large Language Models	提出基于大语言模型的多平台社交媒体数据集生成方法，解决数据获取难题。	large language model
5	Helping Large Language Models Protect Themselves: An Enhanced Filtering and Summarization System	提出一种无需重训练的过滤与总结系统，增强LLM对对抗攻击的防御能力	large language model
6	Multimodal Transformers are Hierarchical Modal-wise Heterogeneous Graphs	提出图结构交错掩码多模态Transformer（GsiT），提升多模态情感分析效率。	multimodal
7	Do We Need a Detailed Rubric for Automated Essay Scoring using Large Language Models?	针对LLM自动作文评分，研究表明简化评分细则可在保证准确率的同时降低token使用量。	large language model
8	Large Language Model-Driven Dynamic Assessment of Grammatical Accuracy in English Language Learner Writing	利用大型语言模型动态评估英语学习者写作中的语法准确性	large language model
9	AURA: A Diagnostic Framework for Tracking User Satisfaction of Interactive Planning Agents	AURA：用于追踪交互式规划Agent用户满意度的诊断框架	large language model instruction following
10	Always Tell Me The Odds: Fine-grained Conditional Probability Estimation	提出一种精细化条件概率估计模型，提升LLM在不确定信息下的概率预测精度。	large language model
11	PREMISE: Matching-based Prediction for Accurate Review Recommendation	提出PREMISE，一种基于匹配的架构，用于提升多模态评论推荐的准确性。	multimodal
12	Leveraging LLMs to Create Content Corpora for Niche Domains	利用大型语言模型为特定领域创建高质量内容语料库	large language model
13	MateICL: Mitigating Attention Dispersion in Large-Scale In-Context Learning	MateICL：缓解大规模上下文学习中的注意力分散问题	large language model	✅
14	Position: Enough of Scaling LLMs! Lets Focus on Downscaling	突破LLM规模瓶颈：提出一种关注模型小型化的新范式	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	🔗	⭐
15	Deliberate Planning in Language Models with Symbolic Representation	SymPlanner：利用符号表示增强语言模型在复杂规划任务中的能力	world model large language model
16	Llama-Nemotron: Efficient Reasoning Models	Llama-Nemotron系列：高效推理的开源异构模型，支持动态推理切换	reinforcement learning distillation

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
17	VTS-LLM: Domain-Adaptive LLM Agent for Enhancing Awareness in Vessel Traffic Services through Natural Language	VTS-LLM：领域自适应LLM Agent，通过自然语言增强船舶交通服务感知能力	spatiotemporal multimodal

⬅️ 返回 cs.CL 首页 · 🏠 返回主页