Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization Paper • 2608.16072 • Published Aug 17 • 50
ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model Paper • 2603.22281 • Published Mar 23 • 22
Neural Discrete Token Representation Learning for Extreme Token Reduction in Video Large Language Models Paper • 2503.16980 • Published Mar 21, 2025 • 4
Dense Video Understanding with Gated Residual Tokenization Paper • 2509.14199 • Published Sep 17, 2025 • 3