cs.CL（2025-12-11）

📊 共 16 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) (12 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#题目一句话要点标签🔗⭐
1 The FACTS Leaderboard: A Comprehensive Benchmark for Large Language Model Factuality 提出FACTS Leaderboard，全面评估大型语言模型的事实准确性，覆盖多模态、参数知识、搜索和文档 grounding 四个场景。 large language model multimodal
2 Computational emotion analysis with multimodal LLMs: Current evidence on an emerging methodological opportunity 评估多模态LLM在政治视频情感分析中的可靠性，揭示实验室与实际场景的性能差距。 large language model multimodal
3 Decoding Student Minds: Leveraging Conversational Agents for Psychological and Learning Analysis 提出一种心理感知对话Agent，用于提升学生学习表现和情感健康 large language model multimodal
4 SWAA: Sliding Window Attention Adaptation for Efficient Long-Context LLMs Without Pretraining 提出SWAA，无需预训练即可高效适配长文本LLM的滑动窗口注意力机制 large language model chain-of-thought ✅
5 LabelFusion: Learning to Fuse LLMs and Transformer Classifiers for Robust Text Classification LabelFusion：融合LLM与Transformer分类器，实现鲁棒文本分类 large language model
6 CompanionCast: A Multi-Agent Conversational AI Framework with Spatial Audio for Social Co-Viewing Experiences CompanionCast：利用空间音频的多智能体对话AI框架，提升社交共 viewing 体验 multimodal
7 From Data Scarcity to Data Care: Reimagining Language Technologies for Serbian and other Low-Resource Languages 提出数据关怀框架以解决低资源语言技术发展问题 large language model
8 RoleRMBench & RoleRM: Towards Reward Modeling for Profile-Based Role Play in Dialogue Systems 提出RoleRMBench与RoleRM，提升角色扮演对话系统中奖励模型的性能。 large language model
9 Causal Reasoning Favors Encoders: On The Limits of Decoder-Only Models 因果推理更青睐编码器：解码器模型的局限性研究 large language model
10 XDoGE: Multilingual Data Reweighting to Enhance Language Inclusivity in LLMs 提出XDoGE多语言数据重加权方法，提升LLM在低资源语言上的性能 large language model
11 Grammaticality Judgments in Humans and Language Models: Revisiting Generative Grammar with LLMs 利用大型语言模型重新审视生成语法：LLM在语法判断任务中的表现 large language model
12 Multilingual VLM Training: Adapting an English-Trained VLM to French 探索多语言VLM训练：将英语VLM适配到法语 multimodal

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
13 OPV: Outcome-based Process Verifier for Efficient Long Chain-of-Thought Verification 提出基于结果的过程验证器OPV，用于高效验证长链思维推理过程 reinforcement learning large language model chain-of-thought
14 AgriGPT-Omni: A Unified Speech-Vision-Text Framework for Multilingual Agricultural Intelligence AgriGPT-Omni：构建统一的多语言农业智能语音-视觉-文本框架 reinforcement learning large language model multimodal
15 Long-horizon Reasoning Agent for Olympiad-Level Mathematical Problem Solving 提出Intern-S1-MO，一种用于解决奥林匹克数学题的长程推理Agent reinforcement learning IMoS chain-of-thought

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
16 Textual Data Bias Detection and Mitigation -- An Extensible Pipeline with Experimental Evaluation 提出可扩展的文本数据偏见检测与缓解流程，并进行实验评估 manipulation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页