cs.CL（2025-12-24）

📊 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) (9) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#题目一句话要点标签🔗⭐
1 Semi-Supervised Learning for Large Language Models Safety and Content Moderation 提出半监督学习方法，提升大语言模型安全性和内容审核能力 large language model
2 Neural Probe-Based Hallucination Detection for Large Language Models 提出基于神经探针的大语言模型幻觉检测框架，提升低误报率下的检测性能。 large language model
3 ClarifyMT-Bench: Benchmarking and Improving Multi-Turn Clarification for Conversational Large Language Models 提出ClarifyMT-Bench，用于评估和提升会话大语言模型的多轮澄清能力。 large language model
4 Foundation Model-based Evaluation of Neuropsychiatric Disorders: A Lifespan-Inclusive, Multi-Modal, and Multi-Lingual Study 提出FEND框架，用于基于多模态融合和预训练模型评估神经精神疾病。 foundation model
5 Rethinking Supervised Fine-Tuning: Emphasizing Key Answer Tokens for Improved LLM Accuracy SFTKey：通过强化关键答案token，提升LLM监督微调的准确率 large language model chain-of-thought
6 Reflection Pretraining Enables Token-Level Self-Correction in Biological Sequence Models 提出反射预训练，使生物序列模型具备token级自纠错能力 large language model chain-of-thought
7 ReaSeq: Unleashing World Knowledge via Reasoning for Sequential Modeling ReaSeq：通过推理释放世界知识，用于序列建模，提升淘宝推荐系统性能 large language model chain-of-thought
8 Architectural Trade-offs in Small Language Models Under Compute Constraints 研究计算约束下小型语言模型的架构权衡，揭示不同架构选择对性能的影响。 large language model
9 C2LLM Technical Report: A New Frontier in Code Retrieval via Adaptive Cross-Attention Pooling C2LLM：通过自适应跨注意力池化实现代码检索的新突破 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🔗⭐
10 Distilling the Essence: Efficient Reasoning Distillation via Sequence Truncation 提出基于序列截断的高效推理蒸馏方法，加速LLM知识迁移。 distillation large language model chain-of-thought ✅
11 MultiMind at SemEval-2025 Task 7: Crosslingual Fact-Checked Claim Retrieval via Multi-Source Alignment TriAligner：通过多源对齐实现跨语言的事实验证声明检索 representation learning contrastive learning large language model
12 Where Did This Sentence Come From? Tracing Provenance in LLM Reasoning Distillation 提出跨模型推理蒸馏溯源框架，分析学生模型能力来源并指导数据选择。 teacher-student distillation
13 Semantic Refinement with LLMs for Graph Representations 提出DAS框架，利用LLM进行图表示的语义精炼，解决图结构异构性问题。 representation learning large language model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
14 Decoding Predictive Inference in Visual Language Processing via Spatiotemporal Neural Coherence 提出基于时空神经相干性的视觉语言处理预测推理解码框架 optical flow spatiotemporal multimodal

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
15 Optimizing Decoding Paths in Masked Diffusion Models by Quantifying Uncertainty 提出基于不确定性量化的掩码扩散模型解码路径优化方法 MDM

⬅️ 返回 cs.CL 首页 · 🏠 返回主页