Jul 2026
Hierarchical Denoising For Multi-Step Visual Reasoning
This work proposes HDR (Hierarchical Denoising for Visual Reasoning), a unified framework that integrates hierarchical latents into causal video generation for multi-step reasoning and introduces a level-stratified multi-step video reasoning benchmark with out-of-distribution cases.
Ze-Zhong Qian, Xiao-Wei Chi, Chak-Wing Mak et al.
· arXiv.org · 1 citation