cs.CL（2024-09-07）

📊 共 11 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (9) 支柱二：RL算法与架构 (RL & Architecture) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Introducing MeMo: A Multimodal Dataset for Memory Modelling in Multiparty Conversations	提出MeMo：一个用于多人对话中记忆建模的多模态数据集。	multimodal
2	Selective Self-Rehearsal: A Fine-Tuning Approach to Improve Generalization in Large Language Models	提出选择性自复现(SSR)微调方法，提升大语言模型泛化能力。	large language model
3	TracrBench: Generating Interpretability Testbeds with Large Language Models	提出TracrBench，利用LLM生成可解释性测试集，加速Transformer模型理解。	large language model
4	Achieving Peak Performance for Large Language Models: A Systematic Review	系统性回顾大型语言模型优化方法，提升性能并降低计算成本	large language model
5	Just ASR + LLM? A Study on Speech Large Language Models' Ability to Identify and Understand Speaker in Spoken Dialogue	揭示语音大语言模型在口语对话中识别和理解说话者能力的局限性	large language model
6	DiVA-DocRE: A Discriminative and Voice-Aware Paradigm for Document-Level Relation Extraction	提出DiVA-DocRE，一种判别式和语音感知的文档级关系抽取方法。	large language model
7	Exploring Straightforward Conversational Red-Teaming	探索利用现成LLM进行直接对话式红队测试，评估其攻击有效性	large language model
8	Untie the Knots: An Efficient Data Augmentation Strategy for Long-Context Pre-Training in Language Models	提出UtK数据增强策略，提升LLM在长文本建模中的效率与性能	large language model
9	Good Idea or Not, Representation of LLM Could Tell	利用大语言模型表征进行科研idea价值评估	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	🔗	⭐
10	Constrained Multi-Layer Contrastive Learning for Implicit Discourse Relationship Recognition	提出约束多层对比学习方法，提升隐式篇章关系识别性能	representation learning contrastive learning
11	LoCa: Logit Calibration for Knowledge Distillation	提出LoCa：一种用于知识蒸馏的Logit校准方法，解决教师模型误导问题。	distillation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页