2025-12-10
VeOmni
AI
2025-12-09
Pip Cache
Tutorials
2025-12-06
Training Data Usage
toLearn
2025-12-05
World Model/UFMs/Omni-Modal: AR vs DiT
Artificial Intelligence
2025-12-04
vllm-omni & DiT Inference Accelerate
2025-12-02
VeRL
Fast Debug: VeRL example
2025-11-26
Pytorch 7 ๏ผMemory Optimization(Freeing GPU/NPU Memory Early)
Programming
2025-11-25
Train Stages: Pretrain, Mid-Train(CT), SFT, RL
RL Algorithms: PPO-RLHF & GRPO-family
Shaojie Tan
๐๐ฐ๐ฎ๐ฑ๐ถ๐ต๐ฆ๐ณ ๐๐ณ๐ค๐ฉ๐ช๐ต๐ฆ๐ค๐ต๐ถ๐ณ๐ฆ & ๐๐๐
Anhui, Hefei, China
Posts
496
Categories
36
Tags
556
2026-02-02
My Digital Worker : Target 1
My Digital Worker
2026-01-27
AI Post Traning: DanceGRPO
AI Post Traning: DiffusionNFT
2026-01-17
260117 Step-3-VL 10B