cs.CL（2026-08-24）

📊 共 19 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (13 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗2) 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) (13 篇)

#题目一句话要点标签🔗⭐
1 Credal Large Language Models for Semantic Commitment under Uncertainty 提出Credal大型语言模型以解决不确定性下的语义承诺问题 large language model
2 Beyond Factual Knowledge: Benchmarking and Learning Step-Level Procedural Rule Reasoning in Large Language Models 提出DynaRule框架以提升大语言模型的程序规则推理能力 large language model ✅
3 A Source-Grounded Framework for Constructing and Evaluating Progressive Multimodal Diagnostic Dialogues from Clinical Case Reports 提出源基础框架以构建和评估渐进式多模态诊断对话 multimodal
4 Language Chain in Alignment: Cross-Lingual Ranking Preference Optimization 提出跨语言排名偏好优化框架以提升多语言模型性能 large language model instruction following
5 FormuEvo: LLM-Guided Evolution for Discovering Solver-Efficient Mixed-Integer Programming Formulations 提出FormuEvo以自动发现高效的混合整数规划模型 large language model zero-shot transfer
6 Don't Repeat Yourself: Stopping Verbatim Loops at Sampling Time 提出DRY方法以解决语言模型中的逐字循环问题 large language model
7 Unlearning Is Not Just Erasing: Temporal Decoupling via Generation Inequality 提出ADU框架以解决大语言模型的有效遗忘问题 large language model
8 What Proves You Wrong: Benchmarking Language Models on Falsifiable Research Ideation 提出Lit2Test基准以评估语言模型的研究创意质量 large language model
9 Do Spoken Language Models Hear Speech as They Read Text? Bridging Structural Gaps Between Speech and Text 提出框架以解决语音与文本表示之间的结构差异问题 instruction following ✅
10 A Multi-Domain and Multi-Task Generative Framework with Explicit Task and Domain Conditioning for Cross-Domain Event Extraction 提出多域多任务生成框架以解决跨域事件提取问题 large language model
11 LongWoF-Bench: Evaluating EvoMap Genes for Verifiable Long-Workflow Tasks 提出LongWoF-Bench以评估EvoMap基因在长流程任务中的可验证性 large language model
12 Meta-Moderator: Empowering Multi-Agent Debate with Meta-Cognition 提出Meta-Moderator以解决多智能体辩论中的调节不足问题 large language model
13 Knowing Isn't Always Saying: When Do Spatial Encodings Reach Answers in Vision-Language Models? 提出方向补丁以解决视觉语言模型中的编码与推理问题 chain-of-thought

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
14 Future Querying: Can LLMs Serve as Implicit Medical World Models? 提出未来查询以解决传统临床预测模型的局限性 world model world models large language model
15 SelFusion: Self-distillation for Diffusion Language Models 提出SelFusion以解决扩散语言模型生成质量问题 distillation large language model instruction following ✅
16 DIAG: Diagnostic Iterative Alignment and Generation for Data-Efficient Mathematical Preference Distillation 提出DIAG框架以解决数学推理任务中的数据稀缺问题 distillation large language model
17 Cross-Domain, Multi-Task Data-to-Text Generation without In-Domain Training Data 提出跨域多任务数据到文本生成方法以解决缺乏训练数据的问题 distillation large language model
18 Beyond the Stability-Exploration Dilemma: Environmental Regularization for LLM Policy Optimization 提出环境正则化方法以解决大语言模型策略优化中的稳定性与探索性困境 PPO 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🔗⭐
19 CaRGo-T: Causal Reasoning Graph-of-Thought improves Multimodal Humor Comprehension 提出CaRGo-T以解决多模态幽默理解问题 HuMoR multimodal chain-of-thought ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页