AI RESEARCH
Self-Consistent Latent Reasoning: Long Latent Sequence Reasoning for Vision-Language Model
arXiv CS.CV
•
ArXi:2605.12163v1 Announce Type: new In language reasoning, longer chains of thought consistently yield better performance, which naturally suggests that visual latent reasoning may likewise benefit from longer latent sequences. However, we discover a counterintuitive phenomenon: the performance of existing latent visual reasoning methods systematically degrades as the latent sequence grows longer. We reveal the root cause: Information Gain Collapse -- autoregressive generation makes each step highly dependent on prior outputs, so subsequent tokens can barely