cs.CL（2024-09-29）

📊 共 17 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (15 🔗4) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (15 篇)

#	题目	一句话要点	标签	🔗	⭐
1	A multimodal LLM for the non-invasive decoding of spoken text from brain recordings	提出一种多模态LLM，用于从非侵入式脑部fMRI记录中解码口语文本	large language model foundation model multimodal	✅
2	CoTKR: Chain-of-Thought Enhanced Knowledge Rewriting for Complex Knowledge Graph Question Answering	提出CoTKR以解决复杂知识图谱问答中的知识重写问题	large language model chain-of-thought
3	Can Large Language Models Analyze Graphs like Professionals? A Benchmark, Datasets and Models	提出ProGraph基准测试，评估并提升大语言模型在图分析任务中的专业能力。	large language model	✅
4	Identifying Knowledge Editing Types in Large Language Models	提出KETI任务与KETIBench，用于识别大语言模型中的知识编辑类型，防范恶意篡改。	large language model	✅
5	Realtime, multimodal invasive ventilation risk monitoring using language models and BoXHED	提出结合语言模型和BoXHED的实时多模态侵入式通气风险监测方法	multimodal
6	Multimodal Misinformation Detection by Learning from Synthetic Data with Multimodal LLMs	提出基于多模态LLM合成数据学习的方法，用于提升真实场景下的多模态虚假信息检测性能。	multimodal
7	Can Models Learn Skill Composition from Examples?	通过示例学习技能组合：小模型也能涌现组合泛化能力	large language model
8	Balancing Cost and Effectiveness of Synthetic Data Generation Strategies for LLMs	研究不同合成数据生成策略对LLM微调的影响，优化资源受限场景下的模型性能。	large language model
9	PEAR: Position-Embedding-Agnostic Attention Re-weighting Enhances Retrieval-Augmented Generation with Zero Inference Overhead	PEAR：零推理开销的位置嵌入无关注意力重加权增强检索增强生成	large language model
10	Instruction Embedding: Latent Representations of Instructions Towards Task Identification	提出指令嵌入（Instruction Embedding）及基准，用于提升LLM任务识别能力	large language model
11	Transforming Hidden States into Binary Semantic Features	利用独立成分分析，将大型语言模型隐状态转化为二元语义特征	large language model
12	AstroMLab 2: AstroLLaMA-2-70B Model and Benchmarking Specialised LLMs for Astronomy	AstroLLaMA-2-70B：构建并评测面向天文学的专业化大语言模型	large language model
13	Revealing Personality Traits: A New Benchmark Dataset for Explainable Personality Recognition on Dialogues	提出CoPE框架与PersonalityEvd数据集，用于可解释的对话人格识别。	large language model	✅
14	CERD: A Comprehensive Chinese Rhetoric Dataset for Rhetorical Understanding and Generation in Essays	提出CERD：一个全面的中文修辞数据集，用于提升论⽂中的修辞理解与⽣成能力	large language model
15	Learning Attentional Mixture of LoRAs for Language Model Continual Learning	提出AM-LoRA，通过注意力混合LoRA解决LLM持续学习中的灾难性遗忘问题。	large language model

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
16	2D-TPE: Two-Dimensional Positional Encoding Enhances Table Understanding for Large Language Models	提出2D-TPE，增强大语言模型对表格理解的空间信息捕捉能力	spatial relationship large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
17	Assessment and manipulation of latent constructs in pre-trained language models using psychometric scales	提出基于自然语言推理提示的心理测量方法，评估并操控预训练语言模型的潜在心理结构。	manipulation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页