cs.CL（2026-06-18）

📊 共 15 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (11 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#	题目	一句话要点	标签	🔗	⭐
1	MedRLM: Recursive Multimodal Health Intelligence for Long-Context Clinical Reasoning, Sensor-Guided Screening, Evidence-Grounded Decision Support, and Community-to-Tertiary Referral Optimization	提出MedRLM框架以解决临床决策支持中的多模态信息处理问题	large language model multimodal
2	Self-Preference Is Weak or Absent in Verifiable Instruction-Following Revision: A Four-Model Test Under Genuine Authorship	验证自我偏好在指令跟随修订中的弱或缺失	large language model instruction following
3	From Texts to Scores: Tracing the Emergence of Essay Quality Representations in Large Language Models	揭示大语言模型中论文质量表征的演变机制	large language model
4	Large Language Models Do Not Always Need Readable Language	提出BabelTele以实现模型间的高效信息传递	large language model
5	StylisticBias: A Few Human Visual Cues Drive Most Social Biases in MLLMs	提出StylisticBias基准以评估多模态大语言模型中的社会偏见	large language model multimodal	✅
6	NRITYAM: Language Models Meet Art and Heritage of Dance	提出NRITYAM以评估语言模型在舞蹈文化理解中的能力	large language model multimodal	✅
7	FineREX: Fine-Tuned NER-RE for Human Smuggling Knowledge Graphs	提出FineREX以解决人类走私知识图谱构建问题	large language model
8	PsyScore: A Psychometrically-Aware Framework for Trait-Adaptive Essay Scoring and ZPD-Scaffolded Feedback	提出PsyScore框架以解决自动化作文评分与反馈的整合问题	large language model
9	Generative Engine Optimization at Scale: Measuring Brand Visibility Across AI Search Engines	提出品牌可见性测量方法以应对AI搜索引擎挑战	large language model
10	The Almost Intelligent Revolution: Options for Scaling Up Deliberation and Empowering People with AI	探讨如何利用大语言模型提升民主协商的包容性与参与度	large language model
11	AtomMem: Building Simple and Effective Memory System for LLM Agents via Atomic Facts	提出AtomMem以解决LLM代理的长期记忆问题	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	🔗	⭐
12	Beyond Uniform Forgetting: A Study of Sequential Direct Preference Optimization Across Preference Settings	提出序列直接偏好优化以解决偏好遗忘问题	DPO direct preference optimization
13	Segment-Level Mandarin Chinese Speech-Based Cognitive Impairment Detection via an Autoencoder with Contrastive Learning	提出基于自编码器和对比学习的段级普通话语音认知障碍检测方法	representation learning contrastive learning
14	Your Mouse and Eyes Secretly Leak Your Preference: LLM Alignment using Implicit Feedback from Users	通过隐式反馈提升大语言模型的对齐效果	DPO large language model	✅
15	HydraHead: From Head-Level Functional Heterogeneity to Specialized Attention Hybridization	提出HydraHead以解决长上下文处理中的注意力瓶颈问题	linear attention distillation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页