Wait, We Don't Need to "Wait"! Removing Thinking Tokens Improves Reasoning Efficiency Paper • 2506.08343 • Published Jun 10 • 54
CODESYNC: Synchronizing Large Language Models with Dynamic Code Evolution at Scale Paper • 2502.16645 • Published Feb 23 • 22
Perception Tokens Enhance Visual Reasoning in Multimodal Language Models Paper • 2412.03548 • Published Dec 4, 2024 • 17