cs.LG（2025-05-11）

📊 共 8 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

#	题目	一句话要点	标签
1	Knowledge Distillation for Enhancing Walmart E-commerce Search Relevance Using Large Language Models	提出基于知识蒸馏的电商搜索排序优化框架，提升LLM排序能力并满足低延迟需求。	distillation large language model
2	Multi-Objective-Guided Discrete Flow Matching for Controllable Biological Sequence Design	MOG-DFM：多目标引导的离散流匹配用于可控生物序列设计	flow matching
3	Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures	研究揭示：卷积网络在学习分层语言结构时比Transformer具有更快的性能扩展。	representation learning
4	Reinforcement Learning (RL) Meets Urban Climate Modeling: Investigating the Efficacy and Impacts of RL-Based HVAC Control	结合城市气候模型的强化学习暖通空调控制策略评估与城市间迁移研究	reinforcement learning

#	题目	一句话要点	标签	🔗
5	GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance	GuidedQuant：利用末端损失引导的大语言模型量化方法	large language model	✅
6	Turning LLM Activations Quantization-Friendly	提出量化友好的LLM激活值转换方法，降低量化误差。	large language model
7	MMiC: Mitigating Modality Incompleteness in Clustered Federated Learning	MMiC：缓解聚类联邦学习中模态不完整性问题	multimodal	✅
8	Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety	利用良性数据中的异常样本微调可显著降低LLM安全性	large language model	✅