Token-Efficient Long Video Understanding for Multimodal LLMs Paper • 2503.04130 • Published Mar 6 • 94
Temporal Preference Optimization for Long-Form Video Understanding Paper • 2501.13919 • Published Jan 23 • 22
MM-Eureka: Exploring Visual Aha Moment with Rule-based Large-scale Reinforcement Learning Paper • 2503.07365 • Published Mar 10 • 61
