Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm
Paper
•
2511.04570
•
Published
•
212
Mingzhe Li
Mubuky
·
AI & ML interests
RL & Agent
Recent Activity
upvoted
a
paper
10 days ago
ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking
upvoted
a
paper
18 days ago
MOSS Transcribe Diarize: Accurate Transcription with Speaker Diarization
Organizations
authored
a
paper
3 months ago