cs.LG（2024-02-18）

📊 共 11 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

#	题目	一句话要点	标签	🔗
1	Aligning Modalities in Vision Large Language Models via Preference Fine-tuning	提出POVID以解决视觉大语言模型的幻觉问题	RLHF direct preference optimization large language model	✅
2	Optimal Parallelization Strategies for Active Flow Control in Deep Reinforcement Learning-Based Computational Fluid Dynamics	提出优化并行策略以提升深度强化学习在流体控制中的效率	reinforcement learning deep reinforcement learning DRL
3	A Temporally Disentangled Contrastive Diffusion Model for Spatiotemporal Imputation	提出条件扩散模型C²TSD以解决时空数据缺失问题	contrastive learning spatiotemporal
4	Teacher as a Lenient Expert: Teacher-Agnostic Data-Free Knowledge Distillation	提出教师无关的数据无关知识蒸馏方法以提升稳定性	distillation
5	Programmatic Reinforcement Learning: Navigating Gridworlds	提出程序化强化学习方法以解决网格世界中的策略学习问题	reinforcement learning
6	PASCL: Supervised Contrastive Learning with Perturbative Augmentation for Particle Decay Reconstruction	提出PASCL以解决粒子衰变重建中的组合复杂性问题	contrastive learning

#	题目	一句话要点	标签	🔗
7	Towards Versatile Graph Learning Approach: from the Perspective of Large Language Models	提出基于大语言模型的多样化图学习方法以应对复杂挑战	large language model
8	BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation	提出BESA以解决大语言模型剪枝效率低的问题	large language model	✅
9	Large Language Model-driven Meta-structure Discovery in Heterogeneous Information Network	提出ReStruct框架以解决异构信息网络中的元结构发现问题	large language model	✅
10	Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark	提出无梯度优化方法以解决大规模语言模型微调中的内存效率问题	large language model	✅
11	ModelGPT: Unleashing LLM's Capabilities for Tailored Model Generation	提出ModelGPT以解决用户定制AI模型需求问题	large language model	✅