cs.CL（2026-09-21）

📊 共 11 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (8) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (8 篇)

#题目一句话要点标签🔗⭐
1 TAC-Time: Texts as Channels For Multimodal Time Series Forecasting 提出TAC-Time以解决多模态时间序列预测中的文本信息利用不足问题 large language model multimodal
2 AURA: Uncertainty-Routed Activation Editing for Acoustic Grounding in Speech Foundation Models 提出AURA以解决语音基础模型中的不确定性问题 foundation model
3 Assessing Readability with LLMs: The Role of Reasoning and Few-Shot Prompting 利用大语言模型提升多语言可读性评估的准确性 large language model chain-of-thought
4 URA-NER: A Unified Retrieval-Augmented Framework with Retrieval Alignment and Uncertainty Reduction for Low-Resource NER 提出URA-NER框架以解决低资源NER中的检索对齐与生成不确定性问题 large language model
5 From Content Generation to Learning Support: Pedagogy-Guided Generative Video Tutors for STEM Learning 提出PIVOT框架以解决教育视频生成中的学习支持问题 multimodal
6 MSI-Bench: Evaluating Multi-Speaker Voice Interaction for Collaborative AI Agents 提出MSI-Bench以评估多语音交互中的协作AI代理 instruction following
7 LLJ Cards: Best practices for the Use of LLMs as Judges 提出LLJ Cards以解决LLM评估标准化问题 large language model
8 Calibrated Decisions at Scale: Converting Police Crash Narratives into Probabilistic Crash Variables with a System One Model (Jev) 提出基于Jev模型的叙述编码方法以解决交通事故数据分析问题 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🔗⭐
9 ToneCL: Contrastive Learning for Few-Shot Syllable-Level Tone Classification 提出ToneCL以解决低资源音节级声调分类问题 contrastive learning
10 Efficient LLM Distillation for Bangladesh Legal Context: A Smartphone-Compatible Retrieval-Augmented Generation Model 提出高效法律语言模型蒸馏方法以解决孟加拉国法律信息获取难题 distillation

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
11 Taramandal-GPT: Enhancing Astrodynamics Problem-Solving with Knowledge Retrieval and Structured Thinking 提出Taramandal-GPT以解决天体动力学问题 manipulation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页