cs.CL（2026-01-28）

📊 共 18 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) (14 🔗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) (14 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Harnessing Large Language Models for Precision Querying and Retrieval-Augmented Knowledge Extraction in Clinical Data Science	利用大型语言模型进行临床数据科学中的精确查询和检索增强知识提取	large language model
2	Efficient Multimodal Planning Agent for Visual Question-Answering	提出多模态规划Agent，高效解决视觉问答任务中的多阶段检索增强生成问题	multimodal
3	AgentIF-OneDay: A Task-level Instruction-Following Benchmark for General AI Agents in Daily Scenarios	提出AgentIF-OneDay基准，评估通用AI Agent在日常场景下的任务级指令遵循能力	instruction following
4	Beyond Divergent Creativity: A Human-Based Evaluation of Creativity in Large Language Models	提出条件发散联想任务以评估语言模型的创造力	large language model
5	MuVaC: AVariational Causal Framework for Multimodal Sarcasm Understanding in Dialogues	提出MuVaC：一个变分因果框架，用于对话中的多模态讽刺理解。	multimodal
6	SpeechMapper: Speech-to-text Embedding Projector for LLMs	SpeechMapper：一种高效的语音到文本嵌入投影方法，用于连接语音基础模型和LLM。	foundation model instruction following
7	Unit-Based Agent for Semi-Cascaded Full-Duplex Dialogue Systems	提出基于单元的Agent，用于半级联全双工对话系统	large language model multimodal	✅
8	QueerGen: How LLMs Reflect Societal Norms on Gender and Sexuality in Sentence Completion Tasks	QueerGen：揭示LLM在句子补全任务中对性别和性取向的社会偏见	large language model
9	MobileBench-OL: A Comprehensive Chinese Benchmark for Evaluating Mobile GUI Agents in Real-World Environment	MobileBench-OL：一个全面的中文移动GUI Agent真实环境评测基准	instruction following
10	AgentLongBench: A Controllable Long Benchmark For Long-Contexts Agents via Environment Rollouts	AgentLongBench：通过环境交互评估长文本Agent的基准测试	large language model
11	ShieldedCode: Learning Robust Representations for Virtual Machine Protected Code	ShieldedCode：学习虚拟机保护代码的鲁棒表示，提升软件防御能力	large language model
12	A Dialectic Pipeline for Improving LLM Robustness	提出一种辩证pipeline，通过自对话提升LLM的鲁棒性和输出质量。	chain-of-thought
13	Can We Improve Educational Diagram Generation with In-Context Examples? Not if a Hallucination Spoils the Bunch	利用上下文示例改进教育图表生成？警惕幻觉问题	large language model
14	Beyond Accuracy: A Cognitive Load Framework for Mapping the Capability Boundaries of Tool-use Agents	提出基于认知负荷理论的工具使用Agent能力边界评估框架	large language model

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

#	题目	一句话要点	标签	🔗	⭐
15	PEARL: Plan Exploration and Adaptive Reinforcement Learning for Multihop Tool Use	PEARL：探索式规划与自适应强化学习提升多步工具使用能力	reinforcement learning large language model
16	PsychePass: Calibrating LLM Therapeutic Competence via Trajectory-Anchored Tournaments	PsychePass：通过轨迹锚定竞赛校准LLM的心理治疗能力	reinforcement learning large language model
17	Me-Agent: A Personalized Mobile Agent with Two-Level User Habit Learning for Enhanced Interaction	Me-Agent：一种基于双层用户习惯学习的个性化移动Agent，增强交互体验	preference learning large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
18	Dissecting Multimodal In-Context Learning: Modality Asymmetries and Circuit Dynamics in modern Transformers	揭示多模态上下文学习机制：Transformer中的模态不对称性和回路动态	manipulation large language model multimodal

⬅️ 返回 cs.CL 首页 · 🏠 返回主页