XDU微积冯

科研经历简介
科研经历简介
发表于|myself|myself
关于大学三年科研经历的总结
Proximal Policy Optimization(PPO)
Proximal Policy Optimization(PPO)
发表于|Reinforcement Learning|RL
ChatGPT进行RLHF的核心方法！简要推导一下该模型
Post Tuned Hashing - A New Approach to Indexing High-dimensional Data
Post Tuned Hashing - A New Approach to Indexing High-dimensional Data
发表于|夏令营经历Data Indexing|DeepLearning•papers reproduced
PTH，一个新的步骤，重建二值空间！
Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation
Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation
发表于|夏令营经历Semantic segmentation|DeepLearning•papers reproduced
FixMatch即可接近SOTA！那我要是优化一下思路呢？
Instance-wise Hard Negative Example Generation for Contrastive Learning in Unpaired Image-to-Image Translation
Instance-wise Hard Negative Example Generation for Contrastive Learning in Unpaired Image-to-Image Translation
发表于|夏令营经历Contrastive LearningImage-to-Image Translation|DeepLearning•papers reproduced
要在图像翻译领域使用对比学习？请用足够强悍的负样本！
Contrastive Learning based Vision-Language Pre-Training
Contrastive Learning based Vision-Language Pre-Training
发表于|multi-modal夏令营经历|DeepLearning
基于对比学习的多模态预训练方法，以Vision-Language PTMs为例
Large-Language-Model For Math
Large-Language-Model For Math
发表于|llm|DeepLearning
让LLM大模型解决数学问题！ -- \#TODO
Image2Poem
Image2Poem
发表于|multi-modal|DeepLearning
此情此景，何不吟诗一首？Image-to-Poem帮你完成！
avatar
weiji-Feng
数学鬼才
文章
8
标签
4
分类
9
Follow Me
公告
This is my Blog
最新文章
科研经历简介
科研经历简介
Proximal Policy Optimization(PPO)
Proximal Policy Optimization(PPO)
Post Tuned Hashing - A New Approach to Indexing High-dimensional Data
Post Tuned Hashing - A New Approach to Indexing High-dimensional Data
Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation
Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation
Instance-wise Hard Negative Example Generation for Contrastive Learning in Unpaired Image-to-Image Translation
Instance-wise Hard Negative Example Generation for Contrastive Learning in Unpaired Image-to-Image Translation
分类
标签
papers reproduced myself DeepLearning RL
归档
网站资讯
文章数目 :
8
本站总字数 :
23.5k
本站访客数 :
本站总访问量 :
最后更新时间 :