cs.CL（2025-01-13）

📊 共 15 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) (13 🔗1) 支柱五：交互与反应 (Interaction & Reaction) (1 🔗1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (13 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Imagine while Reasoning in Space: Multimodal Visualization-of-Thought	提出多模态思维可视化(MVoT)，增强MLLM在空间推理任务中的表现	large language model multimodal chain-of-thought
2	Audio-CoT: Exploring Chain-of-Thought Reasoning in Large Audio Language Model	探索大型音频语言模型中的思维链推理，提升跨模态音频理解能力	instruction following chain-of-thought
3	A Heterogeneous Multimodal Graph Learning Framework for Recognizing User Emotions in Social Networks	提出HMG-Emo框架，利用异构多模态图学习进行社交网络用户情绪识别。	multimodal
4	Emergent effects of scaling on the functional hierarchies within large language models	通过分析LLM内部激活，揭示模型规模对功能层级结构涌现的影响	large language model
5	Investigating Large Language Models in Inferring Personality Traits from User Conversations	利用大语言模型从用户对话中推断人格特质，中间步骤提升准确性	large language model
6	Boosting Text-To-Image Generation via Multilingual Prompting in Large Multimodal Models	提出PMT2I，利用多语言提示增强大型多模态模型中的文本到图像生成能力	multimodal	✅
7	LLMic: Romanian Foundation Language Model	LLMic：面向罗马尼亚语的开源基础语言模型，性能媲美大型模型	large language model foundation model
8	GPT as a Monte Carlo Language Tree: A Probabilistic Perspective	提出基于蒙特卡洛语言树的GPT概率视角分析框架，揭示LLM的模式匹配本质	large language model chain-of-thought
9	The Lessons of Developing Process Reward Models in Mathematical Reasoning	针对数学推理中过程奖励模型，提出共识过滤机制并改进评估框架，提升模型性能和数据效率。	large language model
10	TiEBe: Tracking Language Model Recall of Notable Worldwide Events Through Time	TiEBe：通过时间追踪语言模型对全球重大事件的记忆能力	large language model
11	Advancing Student Writing Through Automated Syntax Feedback	提出Essay-Syntax-Instruct数据集，微调LLM以提升学生写作语法能力	large language model
12	Enhancing Talent Employment Insights Through Feature Extraction with LLM Finetuning	利用LLM微调提取职位信息特征，提升人才就业洞察	large language model
13	FinerWeb-10BT: Refining Web Data with LLM-Based Line-Level Filtering	提出基于LLM的行级过滤方法FinerWeb-10BT，提升LLM训练数据质量和效率	large language model

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
14	Leveraging ASIC AI Chips for Homomorphic Encryption	提出CROSS框架，利用AI芯片加速同态加密，实现ASIC级别的能效。	OMOMO	✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
15	Exploring the encoding of linguistic representations in the Fully-Connected Layer of generative CNNs for Speech	探索语音生成CNN全连接层中语言表征的编码方式	manipulation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页