arxiv:2504.10479
Jiapeng Luo
woolpeeker
·
AI & ML interests
None yet
Recent Activity
authored
a paper
10 days ago
InternVL3: Exploring Advanced Training and Test-Time Recipes for
Open-Source Multimodal Models
commented on
an
article
13 days ago
Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment
Organizations
None yet
Papers
3
spaces
1
models
1
datasets
None public yet