Token-Efficient Long Video Understanding for Multimodal LLMs Paper • 2503.04130 • Published Mar 6, 2025 • 96
Temporal Preference Optimization for Long-Form Video Understanding Paper • 2501.13919 • Published Jan 23, 2025 • 23
MM-Eureka: Exploring Visual Aha Moment with Rule-based Large-scale Reinforcement Learning Paper • 2503.07365 • Published Mar 10, 2025 • 61
