arxiv:2602.13515
Xiangchendong
Xiang-cd
AI & ML interests
pre-train models
Recent Activity
authored
a paper
4 days ago
SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning upvoted a paper 4 days ago
Geometry-Aware Rotary Position Embedding for Consistent Video World Model Organizations
None yet