NJU course

avatar
Richard
If you can't explain it simply, you don't understand it well enough.
Articles
93
Tags
29
Categories
26
Follow Me
Announcement
blog is buliding!
Recent Post
生成式奖励模型的几种方法
Let’s Verify Step by Step
Generative Verifiers, Reward Modeling as Next-Token Prediction
LoRA
GRPO
Approximating KL Divergence
Iterated Denoising Energy Matching for Sampling from Boltzmann Densities
Offline Transition Modeling via Contrastive Energy Learning
Implicit Behavioral Cloning
RLHF and DPO
Categories
Tags
Metabit git resume HW GAN paper vim OS tool 机器学习 linux note DS algorithm LLM 实习 hexo math Quant diffusion ML GPT python c++ 神经网络 RL 随笔 catalog 实验报告
Archives
Info
Article :
93
Run time :
Total Count :
254.4k
Last Push :