cs.CL（2026-02-26）

📊 共 22 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) (17 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (17 篇)

#	题目	一句话要点	标签	🔗	⭐
1	TCM-DiffRAG: Personalized Syndrome Differentiation Reasoning Method for Traditional Chinese Medicine based on Knowledge Graph and Chain of Thought	TCM-DiffRAG：融合知识图谱与思维链的中医个性化辨证论治方法	large language model chain-of-thought
2	A Mixture-of-Experts Model for Multimodal Emotion Recognition in Conversations	提出MiSTER-E以解决多模态对话中的情感识别问题	large language model multimodal
3	Modality Collapse as Mismatched Decoding: Information-Theoretic Limits of Multimodal LLMs	多模态LLM模态坍塌源于解码不匹配，信息论角度揭示其根本限制	multimodal
4	Probing for Knowledge Attribution in Large Language Models	提出AttriWiki自监督数据管道，用于探究大语言模型知识归属问题。	large language model
5	Tokenization, Fusion and Decoupling: Bridging the Granularity Mismatch Between Large Language Models and Knowledge Graphs	KGT：通过专用实体令牌弥合LLM与知识图谱的粒度差异，实现高效知识图谱补全	large language model
6	Natural Language Declarative Prompting (NLD-P): A Modular Governance Method for Prompt Design Under Model Drift	提出自然语言声明式提示（NLD-P）方法，应对大语言模型漂移下的提示设计治理难题。	large language model instruction following
7	Imagination Helps Visual Reasoning, But Not Yet in Latent Space	质疑隐空间推理有效性，提出显式文本想象CapImagine提升视觉推理	large language model multimodal
8	Assessing Deanonymization Risks with Stylometry-Assisted LLM Agent	提出SALA方法，利用文体学特征辅助LLM代理评估和降低文本数据中的去匿名化风险。	large language model
9	TARAZ: Persian Short-Answer Question Benchmark for Cultural Evaluation of Language Models	提出TARAZ：波斯语短答案问题基准，用于评估语言模型的文化理解能力	large language model
10	Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching	提出基于奖励引导拼接的扩散语言模型测试时缩放方法，提升复杂推理任务性能。	large language model	✅
11	Towards Simulating Social Media Users with LLMs: Evaluating the Operational Validity of Conditioned Comment Prediction	提出条件化评论预测CCP任务，评估LLM模拟社交媒体用户行为的有效性	large language model
12	Ruyi2 Technical Report	Ruyi2：基于Familial Model的自适应深度计算加速方案	large language model
13	MTRAG-UN: A Benchmark for Open Challenges in Multi-Turn RAG Conversations	MTRAG-UN：多轮检索增强生成对话的开放挑战基准测试	large language model	✅
14	Rejection Mixing: Fast Semantic Propagation of Mask Tokens for Efficient DLLM Inference	提出ReMix，通过连续空间语义传播加速DLLM推理，解决组合矛盾问题。	large language model
15	IDP Accelerator: Agentic Document Intelligence from Extraction to Compliance Validation	IDP Accelerator：提出一种基于Agent的文档智能框架，用于端到端的文档理解与合规验证。	large language model multimodal
16	France or Spain or Germany or France: A Neural Account of Non-Redundant Redundant Disjunctions	利用神经机制解释非冗余重复析取现象，揭示上下文语义理解	large language model
17	CiteAudit: You Cited It, But Did You Read It? A Benchmark for Verifying Scientific References in the LLM Era	CiteAudit：构建LLM时代科学引用核查基准，解决虚假引用问题	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#	题目	一句话要点	标签	🔗	⭐
18	Fine-Tuning Without Forgetting In-Context Learning: A Theoretical Analysis of Linear Attention Models	针对线性注意力模型，提出一种在微调过程中保持上下文学习能力的方法	linear attention large language model
19	Search-P1: Path-Centric Reward Shaping for Stable and Efficient Agentic RAG Training	提出Search-P1以解决Agentic RAG训练中的稀疏奖励问题	reward shaping large language model
20	Towards Better RL Training Data Utilization via Second-Order Rollout	提出二阶Rollout，提升RL训练数据利用率，增强LLM生成与评价能力	reinforcement learning large language model
21	Truncated Step-Level Sampling with Process Rewards for Retrieval-Augmented Reasoning	SLATE：基于截断步级采样和过程奖励的检索增强推理框架	reinforcement 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	🔗	⭐
22	Replacing Multi-Step Assembly of Data Preparation Pipelines with One-Step LLM Pipeline Generation for Table QA	提出Operation-R1，单步生成数据准备流水线，提升表格问答效率并降低成本。	manipulation reinforcement learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页