Align-TI Collection This is the official set of weights for the paper “Beyond Next-Token Alignment: Distilling Multimodal Large Language Models via Token Interactions.” • 4 items • Updated Oct 30 • 1
MR-Align: Meta-Reasoning Informed Factuality Alignment for Large Reasoning Models Paper • 2510.24794 • Published Oct 27 • 31
R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning Paper • 2508.21113 • Published Aug 28 • 110