cs.CL（2026-09-22）

📊 共 19 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) (13 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (13 篇)

#题目一句话要点标签🔗⭐
1 On the Lexical Superstition of Large Language Models for Code Comprehension: Re-evaluation on Code of Low Lexical Quality 提出Face/Off框架以解决大语言模型对代码标识符的过度依赖问题 large language model
2 Capable yet Parsimonious: Extracting and Characterizing Hidden Chain-of-Thought in Frontier Models 提出一种新方法以提取和表征前沿模型中的隐性推理链 chain-of-thought
3 Semantic Abstraction for Natural Language Inference: a Methodological Framework for Discovering and Compensating Semantic Knowledge and Reasoning Gaps in Large Language Models 提出语义抽象方法以解决大语言模型推理中的知识缺口问题 large language model
4 Qwen3.8-Omni: Towards Native Omni-Modal Agents 提出Qwen3.8-Omni以解决多模态智能体的理解与推理问题 multimodal
5 Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs 提出Flash-dLLM以解决扩散大语言模型推理效率问题 large language model
6 PERSONAWEAVER: Controllable Diversity Beyond Conventional Archetypes in Procedural Character Generation 提出PersonaWeaver以解决角色生成中的同质化问题 large language model ✅
7 A retrospective analysis on the use of LLMs to study infant syntax learning 反思大型语言模型在婴儿句法学习研究中的应用 large language model
8 Transcribe, Translate, and Optimize: Joint Reward Learning for Speech Translation 提出联合奖励学习以解决语音翻译中的训练推理不匹配问题 chain-of-thought
9 Behavior is Not Enough: A Mechanism-Based Evaluation of Social Norm Emergence in LLM Societies 提出机制基础评估框架以揭示LLM社会中的社会规范形成 large language model
10 Combining Hierarchical Cognitive Process with Process Supervision for Interpretable Scene Safety Understanding 提出层次认知过程与过程监督结合以提升场景安全理解 large language model
11 ClusterFewshot: Improving Few-shot Optimization for LLMs workflow 提出ClusterFewshot以优化LLM工作流中的少量示例选择问题 large language model
12 ARAFA: An LLM-Generated Arabic Fact-Checking Dataset 提出ARAFA数据集以解决阿拉伯语事实核查数据稀缺问题 large language model
13 Reply to comments arXiv:2512.07881 and arXiv:2601.06104 on quantum structure in human and AI-generated language 回应关于人类与AI生成语言中的量子结构的评论 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🔗⭐
14 Informed Masking: Structure-Aware Perturbation for Reinforcement Learning in Diffusion Large Language Models 提出知情掩蔽以优化扩散大语言模型中的强化学习 reinforcement learning large language model
15 Syndrome, Synergy, and Safety: Structured Reasoning and Knowledge-Driven Alignment for TCM Prescription Generation 提出四阶段框架以解决中医处方生成中的关键问题 DPO distillation large language model
16 Beyond Repeated Sampling: Learning Search Policies for LLM Reasoning 提出语义引导的搜索策略以提升LLM推理能力 reinforcement learning large language model
17 Compressing Long Context into Answer-Aligned Memory Embeddings for LLM Inference 提出上下文到答案对齐的内存压缩框架以优化LLM推理 distillation large language model

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
18 Enriching Speech Emotion Representations with Conversational Context 提出ACERT模块以解决语音情感识别中的上下文缺失问题 motion representation

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
19 Truth for Believable AI: Expressed Doubt, Provenance, and Belief Revision as an Engineerable Stance 提出不确定性表达与信念修正机制以增强对话代理的可信度 manipulation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页