cs.CL（2026-10-02）

📊 共 24 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (17 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (6) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (17 篇)

#题目一句话要点标签🔗⭐
1 CLIMB: Confidence-Guided Complementary Evidence for Multimodal Retrieval-Augmented Generation 提出CLIMB以解决多模态检索增强生成中的证据不足问题 large language model multimodal
2 The Geometry of Knowledge Accessibility in Large Language Models 提出几何结构以解决大语言模型知识可访问性问题 large language model chain-of-thought
3 Recursive Self-Improvement in Unified Multimodal Models 提出递归跨能力自我改进方法以提升统一多模态模型性能 multimodal
4 SyntaxBench: A Statistical Diagnostic Framework for Character-Level Reasoning in Large Language Models 提出SyntaxBench框架以解决大语言模型字符级推理评估问题 large language model
5 OLMo-Detect: A Multi-Stage, Confounder-Controlled Benchmark for Membership Inference on Large Language Models 提出OLMo-Detect以解决大语言模型的成员推断基准问题 large language model
6 A Guideline-Augmented Multi-Agent Framework for Schema-as-Code Biomedical Named Entity Recognition 提出GAMA框架以解决生物医学命名实体识别中的结构控制问题 large language model instruction following
7 HyperThink: Text-to-Parameter Hypernetworks for Efficient Reasoning 提出HyperThink以解决长思维链推理效率低下问题 large language model
8 RMCW: A Deletion-Robust Watermark Based on Reed--Muller Codes for Language Models 提出基于Reed-Muller码的水印方法以增强语言模型的删除鲁棒性 large language model ✅
9 WakeKV: Reactive, Reversible KV Residency for Heads That Change Their Minds 提出WakeKV以解决KV缓存固定分类问题 chain-of-thought
10 Improving Atomic-Fact Recall via Focused Views in Unstructured Knowledge Editing 提出FOVEATED框架以解决知识编辑中的上下文依赖问题 large language model
11 Structured Composition of Verifiable Atomic Insights for Table-to-Report Generation 提出ComInsight以解决表格到报告生成中的可验证洞察问题 large language model
12 Shrome at Touché: Soft-Vote Ensembling and Counter-Causal Augmentation for Causality Extraction 提出软投票集成与反因果增强以解决因果提取问题 large language model
13 Collective Bias Mitigation via Model Routing and Collaboration 提出集体偏见缓解框架以解决大语言模型的偏见问题 large language model
14 StanceEval 2026: The Second Stance Detection Shared Task 提出StanceEval 2026以解决阿拉伯社交媒体立场检测问题 large language model
15 Unmasking Propaganda: A Comparative Analysis of Masked and Causal Language Models 通过比较分析语言模型提升宣传检测能力 chain-of-thought
16 OmniConfess: Eliciting Token Confessions to Mitigate Omni-Modal Hallucination 提出OmniConfess以解决多模态幻觉问题 large language model ✅
17 Evaluating LLM-as-a-Judge Beyond Score Alignment: A Psychometric Analysis of Residual Judging Difficulty 提出心理测量分析方法以评估LLM作为评审的有效性 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
18 EpiWorld: Grounding LLM Policy Agents in Epidemiological World Models 提出EpiWorld以解决流行病政策推理问题 reinforcement learning world model world models
19 Adaptive Mutual Distillation for Balanced Multi-Task Post-Training of Large Language Models 提出自适应互蒸馏方法以解决多任务后训练不平衡问题 distillation large language model
20 Hindsight-Guided Rationale Distillation for Rare Disease Diagnosis 提出基于后见指导的蒸馏方法以改善罕见疾病诊断 distillation chain-of-thought
21 HARPO: Hallucination-Aware Reinforcement Learning for Faithful and Creative Language Generation 提出HARPO框架以解决语言生成中的幻觉问题 reinforcement learning large language model
22 Text-Centric Post-Training for Omni-Modal Reasoning 提出文本中心后训练以提升多模态推理能力 reinforcement learning large language model
23 Large Language Continuous Diffusion Models 提出Sigma以解决离散扩散语言模型的推理加速问题 distillation classifier-free guidance

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
24 How Robust Is Multimodal Claim Verification to LLM Rewriting? 研究多模态声明验证对LLM重写的鲁棒性 manipulation multimodal

⬅️ 返回 cs.CL 首页 · 🏠 返回主页