cs.CL（2025-12-03）

📊 共 15 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) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1)

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

#	题目	一句话要点	标签	🔗	⭐
1	Adapting Large Language Models to Low-Resource Tibetan: A Two-Stage Continual and Supervised Fine-Tuning Study	提出两阶段微调方法，提升大语言模型在低资源藏语上的性能	large language model foundation model
2	AugServe: Adaptive Request Scheduling for Augmented Large Language Model Inference Serving	AugServe：为增强型大语言模型推理服务设计自适应请求调度框架	large language model
3	Is Lying Only Sinful in Islam? Exploring Religious Bias in Multilingual Large Language Models Across Major Religions	BRAND数据集揭示多语言大模型在宗教理解上对伊斯兰教的偏见	large language model
4	Enhancing Instruction-Following Capabilities in Seq2Seq Models: DoLA Adaptations for T5	针对T5模型，提出基于梯度的激活调控方法，显著提升指令遵循能力	instruction following
5	Different types of syntactic agreement recruit the same units within large language models	揭示大型语言模型中不同句法一致性现象共享的表征单元	large language model
6	Evaluating Hydro-Science and Engineering Knowledge of Large Language Models	提出Hydro-SE Bench评估水科学与工程领域大语言模型的知识和应用能力	large language model
7	Improving Alignment Between Human and Machine Codes: An Empirical Assessment of Prompt Engineering for Construct Identification in Psychology	提出一种基于提示工程的框架，提升LLM在心理学构念识别任务中的性能。	large language model chain-of-thought
8	A Preliminary Study on the Promises and Challenges of Native Top-$k$ Sparse Attention	提出原生Top-$k$稀疏注意力机制，加速长文本建模并提升LLM推理效率。	large language model multimodal
9	Understanding LLM Reasoning for Abstractive Summarization	研究LLM推理能力在抽象摘要中的应用，揭示推理策略与摘要质量、忠实度之间的权衡关系。	large language model
10	Dual LoRA: Enhancing LoRA with Magnitude and Direction Updates	提出Dual LoRA，通过解耦幅度和方向更新增强LoRA微调大语言模型性能	large language model
11	From Hypothesis to Premises: LLM-based Backward Logical Reasoning with Selective Symbolic Translation	提出基于LLM的假设驱动逆向逻辑推理框架，提升推理准确性和效率。	large language model
12	Modeling Topics and Sociolinguistic Variation in Code-Switched Discourse: Insights from Spanish-English and Spanish-Guaraní	提出LLM辅助的标注流程，用于分析双语语篇中的主题和社会语言变异。	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	🔗	⭐
13	SkillFactory: Self-Distillation For Learning Cognitive Behaviors	SkillFactory：通过自蒸馏学习认知行为，提升模型推理能力	reinforcement learning distillation
14	Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspective	提出ESPO，解决扩散LLM中序列层面强化学习的难题	reinforcement learning large language model	✅
15	PretrainZero: Reinforcement Active Pretraining	提出PretrainZero，通过强化主动学习框架提升预训练模型通用推理能力。	reinforcement learning foundation model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页