T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT
Paper
•
2505.00703
•
Published
•
44
shilinyan
shilinyan
·
AI & ML interests
LLM, MLLM
Recent Activity
upvoted
a
paper
about 13 hours ago
AdaptMMBench: Benchmarking Adaptive Multimodal Reasoning for Mode Selection and Reasoning Process
upvoted
a
paper
2 months ago
You Only Forward Once: An Efficient Compositional Judging Paradigm
updated
a dataset
7 months ago
shilinyan/data_cache
Organizations
authored
a
paper
9 months ago