cs.CL（2026-07-13）

📊 共 24 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) (19) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱六：视频提取与匹配 (Video Extraction) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (19 篇)

#	题目	一句话要点	标签	🔗	⭐
1	The In-Car Sign Language Corpus (ICSL): A Multi-Modal Resource for Constrained-Space Sign Language Recognition	提出车载手语语料库以解决共享出行中的手语识别问题	multimodal
2	A Durability and Cross-Language Transfer Benchmark for a Validated Teaching-Feedback Classification Protocol	提出耐用性与跨语言迁移基准以优化教学反馈分类	large language model
3	Agentic Routing: The Harness-Native Data Flywheel	提出Harness-Native代理路由以解决模型选择问题	large language model
4	Beyond Sally-Anne: Evaluating Theory of Mind in LLMs using Epistemic Schelling Points	提出EAST任务以评估LLMs的心智理论能力	large language model
5	ProgramTab: Boosting Table Reasoning of LLMs via Programmatic Paradigm	提出ProgramTab以解决大规模表格推理问题	large language model
6	AdvancedMathBench: A Benchmark Suite for Advanced Mathematical Proof Generation and Verification	提出AdvancedMathBench以评估高级数学证明生成与验证能力	large language model
7	How Temperature Shapes Ideological Discourse in Retrieval-Augmented Generation?	研究RAG框架中温度对意识形态话语的影响	large language model
8	JobHop v2: A Large-Scale Career Trajectory Dataset from Unstructured Resumes	提出JobHop v2以解决职业轨迹数据不足问题	large language model
9	Production and Perception in LLMs: A Token Probability Approach	通过令牌概率方法揭示LLMs中的生成与感知差异	large language model
10	GEIS: A Generation-Evaluation-Improvement Loop of Agent Skills for Long-Form Article Generation	提出GEIS以解决长篇文章生成中的信息覆盖与质量提升问题	large language model
11	Are LLMs ready for HardChoices?	检验大型语言模型在社会问题上的立场一致性	large language model
12	UMoE:Unlocking Every Expert in Domain-Specific Training	提出UMoE以优化领域特定训练中的专家池配置	large language model
13	Relational Positioning as a Measurable Risk Object: History-Carried Lock-in and Self-Confabulation in Multi-Turn Human-AI Dialogue	提出关系定位度量以解决多轮人机对话中的风险问题	large language model
14	ToFu: A White-Box, Token-Efficient Agent Harness for Researchers	提出ToFu以提升研究工作流的效率与灵活性	large language model
15	RefineEvo: Planning-Guided Heuristic Evolution with Bidirectional Experience	提出RefineEvo以解决组合优化问题的自动启发式设计	large language model
16	Amplitude-Only FFN Intervention for Tool-Structured LLM Inference Method: Gated Evaluation Protocol, and Cross-Model Empirical Results	提出幅度仅干预方法以优化工具结构化LLM推理	large language model
17	Do LLMs Fabricate Legal Citations? A Bilingual Benchmark on Saudi Data Protection Law and the GDPR	提出双语基准以评估大型语言模型在法律引用中的准确性	large language model
18	MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment	提出DC-GRPO框架以解决多轮对话中的信用分配问题	large language model
19	Dimensionality in Satisfaction Ratings	利用大语言模型分解客户满意度以提升体验分析	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	🔗	⭐
20	Direct Image-to-Modern Vietnamese Translation of Han-Nom Manuscripts via Multimodal RLHF Preference Alignment	提出多模态RLHF偏好对齐框架以解决汉字文献翻译问题	PPO RLHF DPO
21	EasyOPD: An Easy-to-use On-Policy Distillation Framework for Large Language Models	提出EasyOPD框架以解决语言模型蒸馏中的数据覆盖问题	reinforcement learning distillation large language model
22	TIGER: Text-Conditioned Visual Gated Routing with Acceptance Alignment for Multimodal Speculative Decoding	提出TIGER框架以解决多模态推理中的视觉内容不一致问题	distillation multimodal
23	Extending LLM Context via Associative Recurrent Memory	提出关联递归记忆变换器以解决长上下文处理问题	curriculum learning large language model

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
24	LightMem-Ego: Your AI Memory for Everyday Life	提出LightMem-Ego以解决日常生活中的多模态记忆问题	egocentric multimodal	✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页