cs.CL（2025-11-28）

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

🔬 支柱九：具身大模型 (Embodied Foundation Models) (15 篇)

#题目一句话要点标签🔗⭐
1 Optimizing Multimodal Language Models through Attention-based Interpretability 提出基于注意力机制可解释性的多模态语言模型优化方法，提升参数高效微调性能。 large language model multimodal
2 Every Token Counts: Generalizing 16M Ultra-Long Context in Large Language Models 提出HSA-UltraLong模型，实现16M超长上下文建模并具备长度泛化能力 large language model
3 Tourism Question Answer System in Indian Language using Domain-Adapted Foundation Models 提出基于领域自适应预训练模型的印地语旅游问答系统，解决文化背景下的语言资源匮乏问题。 foundation model
4 Multi-chain Graph Refinement and Selection for Reliable Reasoning in Large Language Models 提出多链图精炼与选择(MGRS)框架，提升大语言模型推理可靠性与效率。 large language model
5 Visual Puns from Idioms: An Iterative LLM-T2IM-MLLM Framework 提出基于迭代LLM-T2IM-MLLM框架的成语视觉双关语自动生成与评估方法 large language model multimodal
6 Mind Reading or Misreading? LLMs on the Big Five Personality Test 评估大语言模型在五因素人格测试中的表现，揭示其在人格预测中的局限性 large language model
7 Alleviating Choice Supportive Bias in LLM with Reasoning Dependency Generation 提出推理依赖生成框架，缓解大语言模型中的选择支持偏差 large language model
8 Minimal-Edit Instruction Tuning for Low-Resource Indic GEC 提出一种免增强的指令调优方法，用于低资源印度语的语法纠错。 large language model
9 Towards Corpus-Grounded Agentic LLMs for Multilingual Grammatical Analysis 提出基于语料库的Agentic LLM框架，用于多语言语法分析 large language model
10 Misalignment of LLM-Generated Personas with Human Perceptions in Low-Resource Settings 揭示LLM生成人物角色在低资源环境下与人类认知的不一致性，尤其在共情和可信度方面 large language model
11 MCP vs RAG vs NLWeb vs HTML: A Comparison of the Effectiveness and Efficiency of Different Agent Interfaces to the Web (Technical Report) 对比LLM Agent与Web交互的多种界面，揭示RAG、MCP和NLWeb优于HTML large language model
12 Are LLMs Good Safety Agents or a Propaganda Engine? 提出PSP数据集，揭示LLM在安全策略之外的政治审查行为 large language model
13 Social Perceptions of English Spelling Variation on Twitter: A Comparative Analysis of Human and LLM Responses 对比人类与LLM对Twitter英语拼写变体的社会感知差异 large language model
14 Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match 提出免训练的松散推测解码FLy，提升LLM推理速度并保持语义正确性。 large language model
15 FEANEL: A Benchmark for Fine-Grained Error Analysis in K-12 English Writing FEANEL：针对K-12英语写作的细粒度错误分析基准 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🔗⭐
16 Language-conditioned world model improves policy generalization by reading environmental descriptions 提出LED-WM，通过语言条件世界模型提升策略在未知环境中的泛化能力 reinforcement learning world model dreamer
17 OmniFusion: Simultaneous Multilingual Multimodal Translations via Modular Fusion OmniFusion：通过模块化融合实现同步多语种多模态翻译 PPO large language model foundation model ✅
18 Ambiguity Awareness Optimization: Towards Semantic Disambiguation for Direct Preference Optimization 提出歧义感知优化(AAO)，通过语义消歧提升直接偏好优化(DPO)效果 reinforcement learning RLHF DPO

⬅️ 返回 cs.CL 首页 · 🏠 返回主页